feat(phased-execution): push each phase commit after it is made

The harness now pushes the phase commit right after committing it (PHASE_PUSH=1 default, new push_phase in lib.sh): upstream when set, else 'git push -u <first remote> <branch>'; no remote = skip with a notice. A push failure keeps the commit local, prints the same loud ERROR contract as a commit failure, and stops the run — the next phase's push sweeps the unpushed commit in. PHASE_PUSH=0 opts out with a loud notice. SKILL.md (Commits + config table + exit codes) and the executor prompts document the new behavior.
feat(phased-execution): harness commits each completed phase atomically
2026-09-10 07:56:30 -04:00 · 2026-09-07 12:42:59 -04:00 · 2026-09-05 10:52:37 -04:00
26 changed files with 481 additions and 231 deletions
@@ -1,13 +1,13 @@
 ---
 name: convert-to-phased
-description: Converts an existing project to the .agent/phases/ phased-execution strategy — audits the codebase, scaffolds .agent/PLAN.md, AGENTS.md, and .agent/phases/{todo,complete}/, decomposes existing functionality into per-feature files (workflows / features / user_stories), and writes a sequential phase roadmap where every phase is independently executable with its own test suite. Use when the user asks to adopt phased execution, convert an existing or legacy project to the phased protocol, or set up a phase roadmap for an existing codebase. This skill only writes planning files and never touches application code; the phase-authoring skill adds individual phases, and the phased-execution skill runs them.
+description: Converts an existing project to the .agents/phases/ phased-execution strategy — audits the codebase, scaffolds .agents/PLAN.md, AGENTS.md, and .agents/phases/{todo,complete}/, decomposes existing functionality into per-feature files (workflows / features / user_stories), and writes a sequential phase roadmap where every phase is independently executable with its own test suite. Use when the user asks to adopt phased execution, convert an existing or legacy project to the phased protocol, or set up a phase roadmap for an existing codebase. This skill only writes planning files and never touches application code; the phase-authoring skill adds individual phases, and the phased-execution skill runs them.
 ---

 # Convert to Phased

 You are the **Conversion Architect** — a senior engineer responsible for
 adopting an *existing* project into the phased-execution strategy. You audit
-the codebase, scaffold the `.agent/` planning structure, and write a phase
+the codebase, scaffold the `.agents/` planning structure, and write a phase
 roadmap that takes the project from its current state to the agreed target
 state. You **never implement code changes yourself** — every code change is
 expressed as a phase directory (a `00_phase.md` overview plus small task
@@ -17,24 +17,24 @@ never add individual phases to an already-converted project — that is the

 Phase state lives in files, not chat:

- `.agent/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
- `.agent/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
- `.agent/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)
- `.agent/validate.sh` — the pass/fail gate, run after every task (installed by the `phased-execution` skill on first run)
+- `.agents/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
+- `.agents/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
+- `.agents/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)
+- `.agents/validate.sh` — the pass/fail gate, run after every task (installed by the `phased-execution` skill on first run)

 ## Choosing the mode

- **Not phased** (no `.agent/phases/todo/`) → run the conversion protocol below.
- **Already phased** (`.agent/phases/todo/` exists) → stop; do not
+- **Not phased** (no `.agents/phases/todo/`) → run the conversion protocol below.
+- **Already phased** (`.agents/phases/todo/` exists) → stop; do not
  re-convert. Point the user at the `phase-authoring` skill.
- **Partially phased** (some `.agent/` artifacts exist) → convert only the
+- **Partially phased** (some `.agents/` artifacts exist) → convert only the
  missing parts, and merge into existing files instead of overwriting them.

 ## Phase 1 — Audit (change nothing yet)

 1. Run `bash scripts/project-audit.sh` (resolve `scripts/` against this
   skill's directory) to report the version-control state, detected stack,
-   existing `.agent/` artifacts, test tooling, and the next free phase number.
+   existing `.agents/` artifacts, test tooling, and the next free phase number.
 2. Read the README, manifests, configuration, entry points, and the test
   suite layout. Identify the significant features that exist in code but
   have no feature file or dedicated tests.
@@ -46,7 +46,7 @@ Phase state lives in files, not chat:
     floor is, existing failures.
   - **Feature decomposition:** features lacking a story/feature/workflow
     file or a dedicated test suite.
-   - **Existing `.agent/` artifacts:** what exists, what is missing.
+   - **Existing `.agents/` artifacts:** what exists, what is missing.
 4. **Wait for confirmation.** Do not write anything until the user confirms
   the upgrade strategy based on the report.

@@ -69,61 +69,61 @@ matches the project's domain:

 | Domain     | Directory                 | File content |
 |------------|---------------------------|--------------|
-| CLI tool   | `.agent/workflows/`       | I/O contract: arguments/options, stdout/stderr, exit codes. Source of truth for the CliRunner contract tests. |
-| Library    | `.agent/features/`        | Public API sketch + exception contracts. Source of truth for the capability test modules. |
-| Web app    | `.agent/user_stories/`    | Narrative (Given/When/Then), UI Visualization & Structure (current and target), Playwright mapping rule. |
-| Anything else | `.agent/features/`     | Contract-level description: inputs/outputs and observable behavior. |
+| CLI tool   | `.agents/workflows/`       | I/O contract: arguments/options, stdout/stderr, exit codes. Source of truth for the CliRunner contract tests. |
+| Library    | `.agents/features/`        | Public API sketch + exception contracts. Source of truth for the capability test modules. |
+| Web app    | `.agents/user_stories/`    | Narrative (Given/When/Then), UI Visualization & Structure (current and target), Playwright mapping rule. |
+| Anything else | `.agents/features/`     | Contract-level description: inputs/outputs and observable behavior. |

 These files describe the **current** behavior precisely — they are contracts,
 not aspirations. The refactor to reach a contract becomes a phase.

-## Phase 4 — Scaffold the `.agent/` structure
+## Phase 4 — Scaffold the `.agents/` structure

 Create (or merge into what already exists) with file tools:

- **`.agent/PLAN.md`** — from `assets/plan-template.md`: assumptions & design
+- **`.agents/PLAN.md`** — from `assets/plan-template.md`: assumptions & design
  principles, the anchors table, high-level architecture (mirroring the
  actual code), data model, validation workflow, the domain section (CLI/UX
  strategy, public-API principles, or UI/UX guidelines), and the phase roadmap.
 - **`AGENTS.md`** — the five base rules below, plus the domain additions.
- **`.agent/phases/todo/`** — the roadmap from Phase 5.
- **`.agent/phases/complete/`** — create the directory, leave it empty (it mirrors `todo/` as phases complete).
- **`.gitignore`** — add `.agent/phase-sessions/` and `.agent/pipeline.log` if missing (never `.agent/` itself — the planning tree is tracked and committed); if an existing `.gitignore` has a `.agent/` ignore line, remove it.
+- **`.agents/phases/todo/`** — the roadmap from Phase 5.
+- **`.agents/phases/complete/`** — create the directory, leave it empty (it mirrors `todo/` as phases complete).
+- **`.gitignore`** — add `.agents/phase-sessions/` and `.agents/pipeline.log` if missing (never `.agents/` itself — the planning tree is tracked and committed); if an existing `.gitignore` has a `.agents/` ignore line, remove it.

 **AGENTS.md base rules:**

-1. "Always read `.agent/PLAN.md` first to understand the project context and goals."
-2. "Follow the phased execution protocol in `.agent/phases/`."
-3. "Never modify `.agent/PLAN.md` or any files in `.agent/phases/complete/`."
-4. "If you need to update any file in `.agent/phases/todo/`, you must ask the user for permission first."
-5. "Strictly adhere to the **LOCKED DECISIONS** listed in `.agent/PLAN.md`."
+1. "Always read `.agents/PLAN.md` first to understand the project context and goals."
+2. "Follow the phased execution protocol in `.agents/phases/`."
+3. "Never modify `.agents/PLAN.md` or any files in `.agents/phases/complete/`."
+4. "If you need to update any file in `.agents/phases/todo/`, you must ask the user for permission first."
+5. "Strictly adhere to the **LOCKED DECISIONS** listed in `.agents/PLAN.md`."

 **Domain additions:**

- **CLI:** "One Workflow, One Phase": each `.agent/workflows/` file
+- **CLI:** "One Workflow, One Phase": each `.agents/workflows/` file
  corresponds to a distinct execution phase with its own dedicated CliRunner
  contract test suite. "Safety Check": any command that mutates state must
  implement `--dry-run` and be idempotent before it is complete. "Options
  over Arguments": new parameters are typed options.
- **Library:** "One Capability, One Phase": each `.agent/features/` file
+- **Library:** "One Capability, One Phase": each `.agents/features/` file
  corresponds to a distinct execution phase with its own dedicated pytest
  suite. "Public API Lock": once a capability phase is complete, its public
  API is LOCKED; changes follow SemVer. "Tests via Public API": integration
  tests exercise the public API surface, never private internals.
- **Web:** "One Story, One Phase": each `.agent/user_stories/` file
+- **Web:** "One Story, One Phase": each `.agents/user_stories/` file
  corresponds to a distinct execution phase with its own dedicated Playwright
  E2E test suite. "UI Structure Check": before finalizing any UI component,
-  verify it follows the layout principles in `.agent/PLAN.md` and meets WCAG
+  verify it follows the layout principles in `.agents/PLAN.md` and meets WCAG
  accessibility basics. "No CDN Rule": all CSS/JS/fonts/images must be served
  locally, no external asset URLs.

-**Do not create `.agent/validate.sh`** — the `phased-execution` skill
+**Do not create `.agents/validate.sh`** — the `phased-execution` skill
 installs it from its template on first run and it must be adapted to the
 project's real checks (the foundation phase does that).

 ## Phase 5 — The Phase Roadmap

-Write sequential phase **directories** into `.agent/phases/todo/` — each
+Write sequential phase **directories** into `.agents/phases/todo/` — each
 `NN_name/` holds a `00_phase.md` overview (from `assets/phase-template.md`)
 and its task files (from `assets/task-template.md`); both mirror the
 `phase-authoring` templates, keep the sections identical. Numbering starts
@@ -132,7 +132,7 @@ together. Never reuse or collide a number.

 Roadmap shape:

-1. **`01_…` foundation/rectification phase** — adapt `.agent/validate.sh` to
+1. **`01_…` foundation/rectification phase** — adapt `.agents/validate.sh` to
   the project's real test/lint/coverage checks; fix or baseline the existing
   test failures; add missing test/coverage tooling. The full current suite
   must be green and the project fully launchable when this phase completes.
@@ -149,8 +149,8 @@ Every phase directory must contain:
  logic, with coverage **>90%** on new/modified code, plus the domain block
  below. Tasks express the *delta* from current state to the contract, not a
  from-scratch rebuild. The header line references the corresponding feature
-  file (`.agent/workflows/…`, `.agent/features/…`, or
-  `.agent/user_stories/…`).
+  file (`.agents/workflows/…`, `.agents/features/…`, or
+  `.agents/user_stories/…`).
 - **Task files `01_…`, `02_…`, …** — small, quick units (one focused change,
  roughly ≤30 minutes of executor work; a phase typically holds 2–8):
  Objective, Work (file-level steps), Testing & Quality, Completion
@@ -189,7 +189,7 @@ final pass is where they are verified end-to-end):
 ## Phase 6 — Version Control & Hand-Off

 - Git is mandatory: `git init` if the project is not a repository.
- Commit the conversion — `AGENTS.md`, `.gitignore`, the whole `.agent/`
+- Commit the conversion — `AGENTS.md`, `.gitignore`, the whole `.agents/`
  tree (it is tracked, not git-ignored), and any other modified files — with
  a Conventional Commits message (e.g. `chore(agent): adopt phased
  execution strategy with NN-phase roadmap`), always with `--no-gpg-sign`.
@@ -206,13 +206,13 @@ and the phase list (number, name, one-line objective). Then hand off:

 ## Strict Operational Rules

- The conversion writes **planning files only**: `.agent/**`, `AGENTS.md`,
+- The conversion writes **planning files only**: `.agents/**`, `AGENTS.md`,
  and `.gitignore`. **Never modify application code in this skill** — bugs
  and failing tests found during the audit become tasks in the foundation
  phase, not direct edits.
- Never overwrite existing `.agent/` content — merge into it.
- Never modify anything in `.agent/phases/complete/`.
- Do not create `.agent/validate.sh` (the `phased-execution` skill installs
+- Never overwrite existing `.agents/` content — merge into it.
+- Never modify anything in `.agents/phases/complete/`.
+- Do not create `.agents/validate.sh` (the `phased-execution` skill installs
  it on first run).
 - Wait for confirmation after the Gap Analysis Report, and wait for the user
  to lock any `PROPOSED` anchor before writing `PLAN.md`.
@@ -1,6 +1,6 @@
 # Phase {{NN}} — {{Short Title}}

-**Feature:** `{{.agent/workflows/<name>.md | .agent/features/<name>.md | .agent/user_stories/<name>.md | "n/a"}}`
+**Feature:** `{{.agents/workflows/<name>.md | .agents/features/<name>.md | .agents/user_stories/<name>.md | "n/a"}}`
 **Context:** `{{PLAN.md sections / files this phase builds on}}`

 ## Objective
@@ -31,4 +31,4 @@ accessibility, asset policy) — whichever matches the project's domain.}}
 | # | Phase | Feature file | Objective (one line) |
 |---|-------|--------------|----------------------|
 | 01 | {{NN_name}} | — | foundation: adapt validate.sh, green test baseline |
-| 02 | {{NN_name}} | `.agent/{{workflows\|features\|user_stories}}/{{name}}.md` | {{...}} |
+| 02 | {{NN_name}} | `.agents/{{workflows\|features\|user_stories}}/{{name}}.md` | {{...}} |
@@ -1,6 +1,6 @@
 # Task {{NN}} — {{Short Title}}

-**Phase:** `{{NN_phase}}` · **Feature:** `{{.agent/workflows/<name>.md | .agent/features/<name>.md | .agent/user_stories/<name>.md | "n/a"}}`
+**Phase:** `{{NN_phase}}` · **Feature:** `{{.agents/workflows/<name>.md | .agents/features/<name>.md | .agents/user_stories/<name>.md | "n/a"}}`

 ## Objective
 {{1–2 sentences: what this task delivers (the delta from current state to the contract)}}
@@ -2,8 +2,8 @@
 # project-audit.sh — stack & phased-readiness probe for the Conversion Architect.
 #
 # Prints: project root, version-control state, detected manifests, domain
-# hints, existing .agent/ artifacts, test tooling, and the next free phase
-# number NN (counting .agent/phases/todo/ and complete/ together,
+# hints, existing .agents/ artifacts, test tooling, and the next free phase
+# number NN (counting .agents/phases/todo/ and complete/ together,
 # zero-padded to 2 digits).
 #
 # Usage: bash project-audit.sh          # from anywhere in the project tree
@@ -72,29 +72,29 @@ fi
 if (( ! hint )); then echo "  (none — classify from the manifests above)"; fi

 echo
-echo ".agent state:"
+echo ".agents state:"
 a=0
-if [[ -f "$root/.agent/PLAN.md" ]]; then
-  echo "  .agent/PLAN.md: present"
+if [[ -f "$root/.agents/PLAN.md" ]]; then
+  echo "  .agents/PLAN.md: present"
  a=1
 fi
 if [[ -f "$root/AGENTS.md" ]]; then
  echo "  AGENTS.md: present"
  a=1
 fi
-if [[ -f "$root/.agent/validate.sh" ]]; then
-  echo "  .agent/validate.sh: present"
+if [[ -f "$root/.agents/validate.sh" ]]; then
+  echo "  .agents/validate.sh: present"
  a=1
 fi
 for d in workflows features user_stories; do
-  if [[ -d "$root/.agent/$d" ]]; then
-    n="$(find "$root/.agent/$d" -maxdepth 1 -name '*.md' 2>/dev/null | wc -l | tr -d ' ')"
-    echo "  .agent/$d/: present ($n file(s))"
+  if [[ -d "$root/.agents/$d" ]]; then
+    n="$(find "$root/.agents/$d" -maxdepth 1 -name '*.md' 2>/dev/null | wc -l | tr -d ' ')"
+    echo "  .agents/$d/: present ($n file(s))"
    a=1
  fi
 done
-todo_dir="$root/.agent/phases/todo"
-complete_dir="$root/.agent/phases/complete"
+todo_dir="$root/.agents/phases/todo"
+complete_dir="$root/.agents/phases/complete"
 list_phases() {
  local dir="$1" entry n t any=0
  for entry in "$dir"/*; do
@@ -113,16 +113,16 @@ list_phases() {
  if (( ! any )); then echo "    (empty)"; fi
 }
 if [[ -d "$todo_dir" ]]; then
-  echo "  .agent/phases/todo:"
+  echo "  .agents/phases/todo:"
  list_phases "$todo_dir"
  a=1
 fi
 if [[ -d "$complete_dir" ]]; then
-  echo "  .agent/phases/complete:"
+  echo "  .agents/phases/complete:"
  list_phases "$complete_dir"
  a=1
 fi
-if (( ! a )); then echo "  (no .agent/ artifacts — full conversion needed)"; fi
+if (( ! a )); then echo "  (no .agents/ artifacts — full conversion needed)"; fi

 max=0
 for d in "$todo_dir" "$complete_dir"; do
@@ -1,6 +1,6 @@
 ---
 name: new-project
-description: Initialises a new Python project and its high-rigor, phased-execution roadmap for a chosen project type. Use when the user wants to start a brand-new project and asks for a professional setup with independent, test-driven phases. Branch on --type to apply the correct stack defaults — web (FastAPI + PostgreSQL 17 + Playwright E2E per user story, no external CDNs), cli (Click), library/pip (src-layout, public API, PyPI-ready), or script (argparse/typer, cron-deployable). This skill scaffolds the environment AND writes the .agent/phases roadmap; the phase-authoring skill adds phases later and the phased-execution skill runs them.
+description: Initialises a new Python project and its high-rigor, phased-execution roadmap for a chosen project type. Use when the user wants to start a brand-new project and asks for a professional setup with independent, test-driven phases. Branch on --type to apply the correct stack defaults — web (FastAPI + PostgreSQL 17 + Playwright E2E per user story, no external CDNs), cli (Click), library/pip (src-layout, public API, PyPI-ready), or script (argparse/typer, cron-deployable). This skill scaffolds the environment AND writes the .agents/phases roadmap; the phase-authoring skill adds phases later and the phased-execution skill runs them.
 ---

 # New Project
@@ -28,9 +28,9 @@ Determine `--type` from the chat context (or ask once if genuinely absent):

 ## Phase state in files

- `.agent/PLAN.md` — master design; **LOCKED DECISIONS** are binding.
- `.agent/phases/todo/NN_name/` — pending phase: `00_phase.md` + `NN_task.md` files.
- `.agent/phases/complete/` — finished phases (mirrors `todo/`, read-only history).
+- `.agents/PLAN.md` — master design; **LOCKED DECISIONS** are binding.
+- `.agents/phases/todo/NN_name/` — pending phase: `00_phase.md` + `NN_task.md` files.
+- `.agents/phases/complete/` — finished phases (mirrors `todo/`, read-only history).
 - `AGENTS.md` — project operating rules derived from this skill's mandates.

 ## Protocol — New Project
@@ -60,7 +60,7 @@ applying **only your branch's** stack section.

 #### Common (all types)
 - `uv` project: `pyproject.toml`, `src/<name>/` package layout, `[project.scripts]` entry point where a CLI/library applies.
- `.gitignore` that **includes `.agent/phase-sessions/` and `.agent/pipeline.log`** — but never `.agent/` itself (the phase roadmap is tracked and committed).
+- `.gitignore` that **includes `.agents/phase-sessions/` and `.agents/pipeline.log`** — but never `.agents/` itself (the phase roadmap is tracked and committed).
 - Multi-stage `Containerfile` (assumes `podman`/`docker`).
 - `README.md` with `uv` + configuration instructions.
 - **Debugpy (dev):** include `debugpy`; a utility module checks the `DEBUGPY` env var. Default (`DEBUGPY=0`/unset) → **not** imported, minimal overhead. `DEBUGPY=1` → import and listen (e.g. port 5678) without blocking.
@@ -117,17 +117,17 @@ anchors are the only technologies phases may use. Cover:

 Create with file tools:

- **`.agent/PLAN.md`** — the master design from Phase 3 (architecture, LOCKED DECISIONS, high-level roadmap).
- **`AGENTS.md`** — initialized with: read `.agent/PLAN.md` first; follow the phased protocol in `.agent/phases/`; never modify `PLAN.md` or anything in `.agent/phases/complete/`; ask before editing `todo/`; adhere to the LOCKED DECISIONS.
- **`.agent/phases/todo/`** — sequential phase directories (`01_…/`, `02_…/`, …), each with a `00_phase.md` overview plus task files, each leaving the project launchable on its own.
- **`.agent/phases/complete/`** — create, leave empty.
+- **`.agents/PLAN.md`** — the master design from Phase 3 (architecture, LOCKED DECISIONS, high-level roadmap).
+- **`AGENTS.md`** — initialized with: read `.agents/PLAN.md` first; follow the phased protocol in `.agents/phases/`; never modify `PLAN.md` or anything in `.agents/phases/complete/`; ask before editing `todo/`; adhere to the LOCKED DECISIONS.
+- **`.agents/phases/todo/`** — sequential phase directories (`01_…/`, `02_…/`, …), each with a `00_phase.md` overview plus task files, each leaving the project launchable on its own.
+- **`.agents/phases/complete/`** — create, leave empty.

-Do **not** create `.agent/validate.sh` — the `phased-execution` skill installs it
+Do **not** create `.agents/validate.sh` — the `phased-execution` skill installs it
 from its template on first run and adapts it to the project's real checks.

 - **Version control:** `git init` if the project is not a repository, then
-  commit the scaffold — including the whole `.agent/` tree (tracked, never
-  git-ignored; only `.agent/phase-sessions/` and `.agent/pipeline.log` are
+  commit the scaffold — including the whole `.agents/` tree (tracked, never
+  git-ignored; only `.agents/phase-sessions/` and `.agents/pipeline.log` are
  ignored) — with a Conventional Commits message, always `--no-gpg-sign`.

 Finish by summarizing the Architectural Anchors and how to start execution with
@@ -141,6 +141,6 @@ Extract before asking: what the user asked for and why, explicit decisions/const

 - **You scaffold and design; you do not implement the roadmap.** Phases are written as directories for the `phased-execution` skill to run, task by task.
 - **Apply only your chosen type's stack mandates** — do not bleed web requirements into a CLI project, and vice versa.
- **Never** create or edit files inside `.agent/PLAN.md`, `AGENTS.md`, or `.agent/phases/complete/` after this skill hands off (the `phase-authoring` skill owns later changes).
+- **Never** create or edit files inside `.agents/PLAN.md`, `AGENTS.md`, or `.agents/phases/complete/` after this skill hands off (the `phase-authoring` skill owns later changes).
 - **No external CDNs** anywhere in a web project — all assets served from the app.
 - Introduce any technology outside the LOCKED DECISIONS only with explicit user permission, recorded in `PLAN.md`.
@@ -1,6 +1,6 @@
 ---
 name: phase-authoring
-description: The required entry point for ANY new work on a .agent/phases/ project. Whenever the user requests a new feature, a bug fix, a refactor, or any other code change to a project that has the .agent/phases/ structure, call this skill FIRST to capture the work as a phase directory with task files — never implement the change directly in code. Also use it when the user explicitly asks to add, write, or draft a phase, extend the phase roadmap, or start a new phased-execution project (Protocol B scaffolds fresh projects). Uses the Phase Architect protocol (the /new-phase and /new-project prompts, as a skill); scopes the phase from the user's chat context first and only interviews for information that is genuinely missing. This skill writes phase directories (a 00_phase.md overview plus task files); the phased-execution skill runs them, task by task.
+description: The required entry point for ANY new work on a .agents/phases/ project. Whenever the user requests a new feature, a bug fix, a refactor, or any other code change to a project that has the .agents/phases/ structure, call this skill FIRST to capture the work as a phase directory with task files — never implement the change directly in code. Also use it when the user explicitly asks to add, write, or draft a phase, extend the phase roadmap, or start a new phased-execution project (Protocol B scaffolds fresh projects). Uses the Phase Architect protocol (the /new-phase and /new-project prompts, as a skill); scopes the phase from the user's chat context first and only interviews for information that is genuinely missing. This skill writes phase directories (a 00_phase.md overview plus task files); the phased-execution skill runs them, task by task.
 ---

 # Phase Authoring
@@ -14,10 +14,10 @@ master plan.

 Phase state lives in files, not chat:

- `.agent/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
- `.agent/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
- `.agent/phases/todo/NN_name.md` — legacy single-file phase (still valid; migrate or split it)
- `.agent/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)
+- `.agents/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
+- `.agents/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
+- `.agents/phases/todo/NN_name.md` — legacy single-file phase (still valid; migrate or split it)
+- `.agents/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)

 Legacy flat phases (`todo/NN_name.md`) are still executed as a single unit.
 `bash scripts/migrate-phases-to-tasks.sh [project-root]` (resolve `scripts/`
@@ -29,8 +29,8 @@ into real task files is this skill's job.

 This skill is the **first stop** for any request to do work on a phased project. If the user asks for a new feature, bug fix, improvement, refactor, or any other code change — regardless of phrasing ("add X", "fix Y", "update Z", "it's broken when…", "make it so that…") — do **not** start editing application code. Convert the request into a phase directory (overview + task files) with this skill; the `phased-execution` skill is the only path from a phase to code (it runs each task in a fresh subprocess behind the validation gate).

- **Phased project** (`.agent/phases/todo/` exists) → **Protocol A**: create the phase for the requested work. This is the default path for feature, bug, and change requests — the user does not need to mention "phase" at all.
- **Fresh project** (no `.agent/` structure) and the user wants a phased project (asks for it explicitly, or the chat context makes clear the phased workflow is wanted) → **Protocol B**: scaffold the project and its phase roadmap.
+- **Phased project** (`.agents/phases/todo/` exists) → **Protocol A**: create the phase for the requested work. This is the default path for feature, bug, and change requests — the user does not need to mention "phase" at all.
+- **Fresh project** (no `.agents/` structure) and the user wants a phased project (asks for it explicitly, or the chat context makes clear the phased workflow is wanted) → **Protocol B**: scaffold the project and its phase roadmap.
 - **Not phased and no sign of phased intent** → this skill does not apply; do the work normally, and if the work is substantial, suggest the `convert-to-phased` skill.
 - Only if the user **explicitly** asks to bypass the phase workflow should code be edited directly — in that case note that the change skips the phase's test and validation gates.

@@ -59,10 +59,10 @@ Rules:

 Before writing anything, you must:

-1. Read `.agent/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS**.
+1. Read `.agents/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS**.
 2. Read `AGENTS.md` if present — project rules may add requirements (e.g. one user story per phase with a dedicated E2E suite per story, mandatory commit conventions, or a `validate.sh` gate).
 3. Run `bash scripts/phase-status.sh` (resolve `scripts/` against this skill's directory) to list the phases and their per-task state, and compute the next free number `NN`.
-4. Read the `00_phase.md` files in `.agent/phases/complete/*/` to understand what has already been built, and review the remaining `todo/` phase directories to avoid overlap. Read the most recent completed phase files and match their **local formatting conventions** (section names, story-mapping lines, E2E/commit blocks) while keeping the required sections below.
+4. Read the `00_phase.md` files in `.agents/phases/complete/*/` to understand what has already been built, and review the remaining `todo/` phase directories to avoid overlap. Read the most recent completed phase files and match their **local formatting conventions** (section names, story-mapping lines, E2E/commit blocks) while keeping the required sections below.

 ### Phase 2: Scope the New Phase (context first, interview only if needed)

@@ -86,7 +86,7 @@ Derive from the chat context (see "Scoping from chat context" above):

 ### Phase 3: Design & Create the Phase

-Create **exactly one** new phase directory at `.agent/phases/todo/NN_name/`,
+Create **exactly one** new phase directory at `.agents/phases/todo/NN_name/`,
 where `NN` comes from Phase 1 (next free number, counting `todo/` and
 `complete/` together) and `name` is a short `snake_case` description. It
 contains the phase overview and the phase's task files:
@@ -112,7 +112,7 @@ earlier ones within the phase.
 **Design Mandates:**

 - **Independent Viability:** the phase must leave the project functional and launchable on its own once complete.
- **Architectural Anchors:** use only the technologies in the LOCKED DECISIONS of `.agent/PLAN.md`. Never introduce new technology without explicit permission.
+- **Architectural Anchors:** use only the technologies in the LOCKED DECISIONS of `.agents/PLAN.md`. Never introduce new technology without explicit permission.
 - **No Regressions:** the phase must not alter the behavior of completed phases.
 - **Executable in isolation:** an agent that sees only the repository, the phase overview, the completed task files, and one task file — no chat history, no follow-ups — must be able to finish that task. No hidden assumptions.

@@ -153,7 +153,7 @@ Derive from the chat context (see "Scoping from chat context" above):
 - Use `uv` for all package management.
 - **Mandatory Dependencies:** `python-dotenv` (production); `debugpy`, `ruff`, `pyright`, `pytest`, `pytest-cov` (dev).
 - **Web Projects:** add `fastapi`, `alembic`, `pydantic`; prefer `httpx`.
- **Scaffold Files:** a comprehensive `.gitignore` (must include `.agent/phase-sessions/` and `.agent/pipeline.log` — but **never** `.agent/` itself: the planning tree is tracked and committed), a multi-stage `Containerfile` (assuming `podman`/`docker`), and a `README.md` with `uv` and configuration instructions.
+- **Scaffold Files:** a comprehensive `.gitignore` (must include `.agents/phase-sessions/` and `.agents/pipeline.log` — but **never** `.agents/` itself: the planning tree is tracked and committed), a multi-stage `Containerfile` (assuming `podman`/`docker`), and a `README.md` with `uv` and configuration instructions.

 ### Phase 3: Strategic Architectural Design

@@ -174,12 +174,12 @@ phases may use. The design must cover:

 Use file tools to create (not just describe):

- **`.agent/PLAN.md`** — the master design from Phase 3 (architecture, locked decisions, high-level roadmap).
- **`AGENTS.md`** — initialized with: always read `.agent/PLAN.md` first; follow the phased protocol in `.agent/phases/`; never modify `.agent/PLAN.md` or anything in `.agent/phases/complete/`; ask the user before editing files in `.agent/phases/todo/`; strictly adhere to the **LOCKED DECISIONS**.
- **`.agent/phases/todo/`** — sequential phase directories (`01_…/`, `02_…/`, …), each with a `00_phase.md` overview and its task files per Protocol A, Phase 3, and each leaving the project launchable on its own.
- **`.agent/phases/complete/`** — create the directory, leave it empty.
+- **`.agents/PLAN.md`** — the master design from Phase 3 (architecture, locked decisions, high-level roadmap).
+- **`AGENTS.md`** — initialized with: always read `.agents/PLAN.md` first; follow the phased protocol in `.agents/phases/`; never modify `.agents/PLAN.md` or anything in `.agents/phases/complete/`; ask the user before editing files in `.agents/phases/todo/`; strictly adhere to the **LOCKED DECISIONS**.
+- **`.agents/phases/todo/`** — sequential phase directories (`01_…/`, `02_…/`, …), each with a `00_phase.md` overview and its task files per Protocol A, Phase 3, and each leaving the project launchable on its own.
+- **`.agents/phases/complete/`** — create the directory, leave it empty.

-Do **not** create `.agent/validate.sh` — the `phased-execution` skill
+Do **not** create `.agents/validate.sh` — the `phased-execution` skill
 installs it from its template on first run and it must be adapted to the
 project's real checks.

@@ -189,7 +189,7 @@ execution with `phased-execution` (`auto-phase.sh`).
 ## Strict Operational Rules

 - **Work requests become phase directories.** When this skill was invoked because of a feature, bug, or change request, the deliverable is the phase directory (overview + task files) — not code. Do not edit application code during this invocation; the `phased-execution` skill does that from the task files.
- **Never** modify `.agent/PLAN.md`, `AGENTS.md`, or any file in `.agent/phases/complete/`.
- **Never** modify existing phase directories or their files in `.agent/phases/todo/`; if one needs updating, ask the user for permission first.
+- **Never** modify `.agents/PLAN.md`, `AGENTS.md`, or any file in `.agents/phases/complete/`.
+- **Never** modify existing phase directories or their files in `.agents/phases/todo/`; if one needs updating, ask the user for permission first.
 - Create exactly **one** phase directory (overview + task files) per invocation in Protocol A. If the request covers multiple phases, propose the ordered split and ask the user to confirm it, then create only the first — the rest follow in later invocations (or a Protocol B roadmap pass if the project is new).
 - Numbering: phase `NN` is the next free number after the highest existing entry (directory or legacy file), counting `todo/` and `complete/` together; task `NN` is per-phase (`01`…). Never reuse or collide a number.
@@ -1,6 +1,6 @@
 # Phase {{NN}} — {{Short Title}}

-**Story:** `{{.agent/user_stories/<story>.md or "n/a"}}`
+**Story:** `{{.agents/user_stories/<story>.md or "n/a"}}`
 **Context:** `{{PLAN.md sections / files this phase builds on}}`

 ## Objective
@@ -1,6 +1,6 @@
 # Task {{NN}} — {{Short Title}}

-**Phase:** `{{NN_phase}}` · **Story:** `{{.agent/user_stories/<story>.md or "n/a"}}`
+**Phase:** `{{NN_phase}}` · **Story:** `{{.agents/user_stories/<story>.md or "n/a"}}`

 ## Objective
 {{1–2 sentences: what this task delivers}}
@@ -17,7 +17,7 @@
 #
 # Usage: bash migrate-phases-to-tasks.sh [project-root]
 #   project-root defaults to the nearest ancestor containing
-#   .agent/phases/todo or agent/phases/todo (older projects).
+#   .agents/phases/todo or agent/phases/todo (older projects).
 set -euo pipefail

 root="${1:-}"
@@ -26,14 +26,14 @@ if [[ -n "$root" ]]; then
 else
  root="$(pwd)"
  while :; do
-    if [[ -d "$root/.agent/phases/todo" || -d "$root/agent/phases/todo" ]]; then break; fi
+    if [[ -d "$root/.agents/phases/todo" || -d "$root/agent/phases/todo" ]]; then break; fi
    [[ "$root" == "/" ]] && { echo "✗ ERROR: no phases/todo found at or above $(pwd)" >&2; exit 1; }
    root="$(dirname "$root")"
  done
 fi

-if [[ -d "$root/.agent/phases" ]]; then
-  phases="$root/.agent/phases"
+if [[ -d "$root/.agents/phases" ]]; then
+  phases="$root/.agents/phases"
 elif [[ -d "$root/agent/phases" ]]; then
  phases="$root/agent/phases"
 else
@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 # phase-status.sh — phase/task pipeline state for the Phase Architect.
 #
-# Finds the project root (nearest ancestor with .agent/phases/todo), prints
+# Finds the project root (nearest ancestor with .agents/phases/todo), prints
 # the todo/ and complete/ phase listings with per-task state, the next free
 # phase number NN (counting both directories together, zero-padded to 2
 # digits), and the next pending unit in pipeline order.
@@ -15,12 +15,12 @@ set -euo pipefail

 root="$(pwd)"
 while :; do
-  if [[ -d "$root/.agent/phases/todo" ]]; then break; fi
-  [[ "$root" == "/" ]] && { echo "✗ ERROR: no .agent/phases/todo found at or above $(pwd)" >&2; exit 1; }
+  if [[ -d "$root/.agents/phases/todo" ]]; then break; fi
+  [[ "$root" == "/" ]] && { echo "✗ ERROR: no .agents/phases/todo found at or above $(pwd)" >&2; exit 1; }
  root="$(dirname "$root")"
 done

-phases="$root/.agent/phases"
+phases="$root/.agents/phases"

 # --- todo: per-task state ------------------------------------------------------
 echo "todo:"
@@ -1,26 +1,28 @@
 ---
 name: phased-execution
-description: Runs the .agent/phases/ phased-execution pipeline (ported from opencode's next-phase/auto-phase commands). Use when the user asks to run the next task, run the next phase, run all phases, run the phase pipeline, or check pipeline status. Each task executes in a separate pi subprocess so this chat's context stays small.
+description: Runs the .agents/phases/ phased-execution pipeline (ported from opencode's next-phase/auto-phase commands). Use when the user asks to run the next task, run the next phase, run all phases, run the phase pipeline, or check pipeline status. Each task executes in a separate pi subprocess so this chat's context stays small.
 ---

 # Phased Execution

 Phase state lives in files, not chat:

- `.agent/PLAN.md` — master plan; LOCKED DECISIONS are binding
- `.agent/phases/todo/NN_name/` — a pending phase: `00_phase.md` (objective, dependencies, task index, testing & quality, completion criteria) plus `NN_task.md` task files (task sort order = execution order)
- `.agent/phases/todo/NN_name.md` — legacy single-file phase (still executable as one unit)
- `.agent/phases/complete/` — finished phases; mirrors the `todo/` layout (completed task files and the phase overview move here)
- `.agent/reports/<phase>/<task>.a<N>.{md,err,validate}` — per-task executor reports, stderr, and validation logs (legacy phases: `.agent/reports/<phase>.a<N>.*`)
- `.agent/validate.sh` — the pass/fail gate, run after **every task**
+- `.agents/PLAN.md` — master plan; LOCKED DECISIONS are binding
+- `.agents/phases/todo/NN_name/` — a pending phase: `00_phase.md` (objective, dependencies, task index, testing & quality, completion criteria) plus `NN_task.md` task files (task sort order = execution order)
+- `.agents/phases/todo/NN_name.md` — legacy single-file phase (still executable as one unit)
+- `.agents/phases/complete/` — finished phases; mirrors the `todo/` layout (completed task files and the phase overview move here)
+- `.agents/reports/<phase>/<task>.a<N>.{md,err,validate}` — per-task executor reports, stderr, and validation logs (legacy phases: `.agents/reports/<phase>.a<N>.*`)
+- `.agents/validate.sh` — the pass/fail gate, run after **every task**

 The unit of execution is the **task**: each task runs in a **separate pi
 process** (fresh context) with bounded fixer retries. A task only moves to
 `complete/` after the child exits 0, the child's stream ends with a clean
-final report, **and** `.agent/validate.sh` passes. When all of a phase's tasks
+final report, **and** `.agents/validate.sh` passes. When all of a phase's tasks
 are done, `00_phase.md` runs as the phase's **final pass** (remaining inline
 work + completion criteria + phase-level verification); moving it completes
-the phase and is the `PHASE_COMMIT` commit point. This chat only dispatches
+the phase and is the `PHASE_COMMIT` commit point (one atomic commit — code +
+phase files + reports — pushed right after when the repo has a remote;
+children never commit; see Commits below). This chat only dispatches
 and relays results — do not implement task code yourself; that is what the
 subprocesses are for.

@@ -31,7 +33,7 @@ the terminal: tool calls, assistant text, `◐ thinking…` / `◑ thought for N
 indicators, yellow `⧉ compacting context` lines (these can take minutes —
 not a hang), and provider auto-retry notices. If the child dies mid-flush and
 the stream loses the final message, the report is recovered from the
-child's session file (`.agent/phase-sessions/`), so a completed phase is
+child's session file (`.agents/phase-sessions/`), so a completed phase is
 never lost to a truncated stream.

 ## Commands
@@ -64,8 +66,9 @@ Re-running `auto-phase.sh` after a failure continues where it stopped.

 ## After a run

-Exit codes: `0` = success (or nothing to run), `1` = task/phase failed after all
-attempts, `130`/`143` = interrupted (Ctrl+C / SIGTERM).
+Exit codes: `0` = success (or nothing to run), `1` = task failed after all
+attempts, or the phase commit/push failed, `130`/`143` = interrupted
+(Ctrl+C / SIGTERM).
 Failures always print a `✗ ERROR:` line with the last error output — if the
 script's output looks like it ended abruptly, re-run it; the failed executor's
 session is resumed automatically (retries continue the child's own session,
@@ -73,10 +76,46 @@ keeping its work).

 Relay to the user: the task (or phase) name, its executor report (printed at
 the end of the script output), and the validation outcome. On failure, point
-the user at `.agent/reports/<phase>/<task>.a*.{md,err,validate}` (legacy
-phases: `.agent/reports/<phase>.a*.*`) — the script also prints a ready to run
+the user at `.agents/reports/<phase>/<task>.a*.{md,err,validate}` (legacy
+phases: `.agents/reports/<phase>.a*.*`) — the script also prints a ready to run
 `pi --session … -c “…”` command to continue the failed session manually.

+## Commits
+
+Children never commit — their prompts forbid `git add`/`git commit`
+(overriding any project “commit per phase” instruction), which is what keeps
+the commit deterministic instead of intermittent. By default
+(`PHASE_COMMIT=1`) the harness makes **ONE atomic commit per completed
+phase** at its commit point: the phase's code changes, the
+`todo/`→`complete/` file move, and the executor reports, together.
+`PHASE_COMMIT=0` opts out — the phase is then left uncommitted with a loud
+warning, never silently.
+
+- **Scoped staging**: a snapshot of the worktree taken at the phase's first
+  unit (`.agents/phase-sessions/dirty-<phase>`, gitignored runtime storage)
+  is subtracted, so the owner's pre-existing uncommitted work is left alone;
+  pipeline runtime artifacts (`phase-sessions/`, `pipeline.log`) are never
+  staged. The commit output prints exactly what went in.
+- **Verified**: the moved phase file (and the executor report, unless the
+  project gitignores reports) is checked against the index *before*
+  committing — the artifacts that used to go missing silently.
+- **Loud on failure**: a commit failure prints a `✗ ERROR:` block with the
+  git error and the exact hand-fix command, and **stops the run**. The phase
+  stays complete (the work passed validation) — re-running will not
+  re-execute it, and a later phase's commit will not sweep the miss in: fix
+  the commit first, then re-run.
+- Subject: `PHASE_COMMIT_SUBJECT` (default `phase: {{PHASE}}`); the
+  executor's final report becomes the commit body. `--no-gpg-sign` is always
+  passed.
+- **Pushed**: with `PHASE_PUSH=1` (default) the commit is pushed right after
+  it is made — to the branch's upstream when one is set, otherwise
+  `git push -u <first remote> <branch>`. A repo with no remote skips the
+  push with a notice (the commit stays local). A push failure gets the same
+  `✗ ERROR:` contract as a commit failure: the commit is local and safe, the
+  run stops, and the next phase's push sweeps the unpushed commit in once
+  the push works. `PHASE_PUSH=0` opts out — each phase commit is left local
+  with a loud notice.
+
 ## Configuration (environment variables)

 | Var | Default | Meaning |
@@ -84,7 +123,9 @@ phases: `.agent/reports/<phase>.a*.*`) — the script also prints a ready to run
 | `MAX_FIX_ATTEMPTS` | `3` | Fixer retries per phase |
 | `PHASE_MODEL` | session default | `--model` for child executors (e.g. `anthropic/claude-sonnet-4-5`) |
 | `PHASE_THINKING` | session default | `--thinking` level for child executors |
-| `PHASE_COMMIT` | `0` | `1` = `git commit --no-gpg-sign` after each completed **phase** (when its `00_phase.md` final pass passes; legacy: when its file moves) |
+| `PHASE_COMMIT` | `1` | `1` (default) = the harness commits each completed **phase** as one atomic commit (code changes + the file move + executor reports) when its `00_phase.md` final pass passes (legacy: when its file moves). `0` = opt out: the phase is left uncommitted with a loud warning. See Commits above |
+| `PHASE_COMMIT_SUBJECT` | `phase: {{PHASE}}` | Commit subject template for `PHASE_COMMIT=1` (`{{PHASE}}` = the phase directory name); the executor's final report becomes the commit body |
+| `PHASE_PUSH` | `1` | `1` (default) = push each phase commit right after it is made (upstream when set, else `git push -u <first remote> <branch>`); no remote = skip with a notice; a failure stops the run (the commit stays local — the next phase's push sweeps it in). `0` = leave commits local with a loud notice. See Commits above |
 | `PI_TRUST` | `0` | `1` = pass `--approve` (load project `.pi/` settings/skills into children) |
 | `FRESH_FIX` | `0` | `1` = fixer retries start fresh instead of resuming the failed session |
 | `QUIET` | `0` | `1` = suppress live progress display (reports are still written) |
@@ -92,7 +133,7 @@ phases: `.agent/reports/<phase>.a*.*`) — the script also prints a ready to run

 ## Setup notes

- First run creates `.agent/validate.sh` from `assets/validate.sh` if missing.
+- First run creates `.agents/validate.sh` from `assets/validate.sh` if missing.
  It must be adapted to the project's real checks — it is the authoritative
  quality gate.
 - Phase directories are created by the `phase-authoring` skill or the
@@ -101,9 +142,10 @@ phases: `.agent/reports/<phase>.a*.*`) — the script also prints a ready to run
 - Legacy flat phase files (`todo/NN_name.md`) are still executed as a single
  unit; `phase-authoring`'s `migrate-phases-to-tasks.sh` converts them to the
  directory layout (the phase's final pass then picks up any inline task list).
- Child executor sessions are kept in `.agent/phase-sessions/` (plus
-  `pipeline.log` in `.agent/`); if the project is versioned, git-ignore those
-  runtime artifacts only — `.agent/` itself is tracked and committed.
+- Child executor sessions are kept in `.agents/phase-sessions/` (plus
+  `pipeline.log` in `.agents/`); if the project is versioned, git-ignore those
+  runtime artifacts only — `.agents/` itself is tracked and committed.
+  (The per-phase worktree snapshot `dirty-<phase>` is always kept there too.)
 - If you keep non-skill markdown (e.g. a `README.md`) in a skills directory
  (like `~/.pi/agent/skills/`), pi warns “description is required” for it.
  Add a `.gitignore` in that directory listing the file — pi's skill scanner
@@ -1,11 +1,11 @@
 You are a phase executor in a phased build pipeline. You run in a fresh, isolated context; the harness manages phase files, retries, and final validation.

-Target phase file: `.agent/phases/todo/{{PHASE}}`
+Target phase file: `.agents/phases/todo/{{PHASE}}`

 ## Steps
-1. Read `.agent/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
+1. Read `.agents/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
 2. Read `AGENTS.md` if present.
-3. Read the completed phase files so your work stays architecturally consistent with what is already built: every `00_phase.md` in `.agent/phases/complete/*/`, plus any legacy flat phase files directly in `.agent/phases/complete/`.
+3. Read the completed phase files so your work stays architecturally consistent with what is already built: every `00_phase.md` in `.agents/phases/complete/*/`, plus any legacy flat phase files directly in `.agents/phases/complete/`.
 4. Read the target phase file and complete **every** task in it, in order.
 5. Write the unit and integration tests required by the phase's Testing & Quality section. Do not omit parts of the code to inflate coverage.
 6. Run the project's full test suite and linter. If anything fails — including the phase's coverage criterion — fix it and re-run until green.
@@ -13,7 +13,8 @@ Target phase file: `.agent/phases/todo/{{PHASE}}`

 ## Rules
 - Work only on the target phase; never start work from other files in `todo/`.
- Do **not** move, rename, or edit the phase file, other files in `.agent/phases/todo/`, `.agent/PLAN.md`, or anything in `.agent/phases/complete/`. The harness moves the phase file on success.
+- Do **not** move, rename, or edit the phase file, other files in `.agents/phases/todo/`, `.agents/PLAN.md`, or anything in `.agents/phases/complete/`. The harness moves the phase file on success.
+- Do **not** run `git add` or `git commit` — leave every change in the working tree. The harness commits this completed phase (code, phase files, and reports) atomically after this pass passes and pushes it when the repo has a remote; this overrides any project instruction to commit per phase.
 - Do not assume the code is correct; fix any errors you find while testing.
 - Leave the repository functional when you finish.

@@ -1,19 +1,20 @@
 You are the phase-completion executor in a phased build pipeline. You run in a fresh, isolated context; the harness manages phase and task files, retries, and final validation.

-Phase overview: `.agent/phases/todo/{{PHASE}}/00_phase.md`
+Phase overview: `.agents/phases/todo/{{PHASE}}/00_phase.md`

 ## Steps
-1. Read `.agent/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
+1. Read `.agents/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
 2. Read `AGENTS.md` if present.
-3. Read the phase overview `.agent/phases/todo/{{PHASE}}/00_phase.md`.
-4. Check the phase's task index against `.agent/phases/complete/{{PHASE}}/`: if any task is missing from there, the overview itself still carries work (a legacy phase with an inline task list) — implement that remaining work now, in order, including its tests.
+3. Read the phase overview `.agents/phases/todo/{{PHASE}}/00_phase.md`.
+4. Check the phase's task index against `.agents/phases/complete/{{PHASE}}/`: if any task is missing from there, the overview itself still carries work (a legacy phase with an inline task list) — implement that remaining work now, in order, including its tests.
 5. Otherwise every task is done: this is the final verification pass. Verify **each** completion criterion in the phase overview (commands to run, endpoints to hit, artifacts to exist), and execute any phase-level verification blocks it defines (e.g. a dedicated E2E or contract test suite).
 6. Run the project's full test suite and linter. If anything fails — including the phase's coverage criterion or a completion criterion — fix it and re-run until green.
 7. If you find defects in previously completed work (failing tests, lint errors, bugs), fix those as part of this pass.

 ## Rules
 - Never start work from other files in `todo/`.
- Do **not** move, rename, or edit the phase overview, other files in `.agent/phases/todo/`, `.agent/PLAN.md`, or anything in `.agent/phases/complete/`. The harness moves the phase file on success.
+- Do **not** move, rename, or edit the phase overview, other files in `.agents/phases/todo/`, `.agents/PLAN.md`, or anything in `.agents/phases/complete/`. The harness moves the phase file on success.
+- Do **not** run `git add` or `git commit` — leave every change in the working tree. The harness commits this completed phase (code, phase files, and reports) atomically after this pass passes and pushes it when the repo has a remote; this overrides any project instruction to commit per phase.
 - Do not assume the code is correct; fix any errors you find while testing.
 - Leave the repository functional when you finish.

@@ -1,12 +1,12 @@
 You are a task executor in a phased build pipeline. You run in a fresh, isolated context; the harness manages phase and task files, retries, and final validation.

-Target task file: `.agent/phases/todo/{{PHASE}}/{{TASK}}`
+Target task file: `.agents/phases/todo/{{PHASE}}/{{TASK}}`

 ## Steps
-1. Read `.agent/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
+1. Read `.agents/PLAN.md` — project goals, architecture, and **LOCKED DECISIONS** (binding; never introduce technology outside them).
 2. Read `AGENTS.md` if present.
-3. Read the phase overview `.agent/phases/todo/{{PHASE}}/00_phase.md` — objective, dependencies, testing & quality mandate, and completion criteria.
-4. Read this phase's completed task files (`.agent/phases/complete/{{PHASE}}/*.md`, excluding `00_phase.md`) and the `00_phase.md` overviews of other completed phases (`.agent/phases/complete/*/00_phase.md`) so your work stays architecturally consistent with what is already built.
+3. Read the phase overview `.agents/phases/todo/{{PHASE}}/00_phase.md` — objective, dependencies, testing & quality mandate, and completion criteria.
+4. Read this phase's completed task files (`.agents/phases/complete/{{PHASE}}/*.md`, excluding `00_phase.md`) and the `00_phase.md` overviews of other completed phases (`.agents/phases/complete/*/00_phase.md`) so your work stays architecturally consistent with what is already built.
 5. Read the target task file and complete it fully, in order.
 6. Write the unit and integration tests required by the task. Do not omit parts of the code to inflate coverage.
 7. Run the project's full test suite and linter. If anything fails — including the task's coverage criterion — fix it and re-run until green.
@@ -14,7 +14,8 @@ Target task file: `.agent/phases/todo/{{PHASE}}/{{TASK}}`

 ## Rules
 - Work only on the target task; never start the next task or work from other files in `todo/`.
- Do **not** move, rename, or edit the task file, `00_phase.md`, other files in `.agent/phases/todo/`, `.agent/PLAN.md`, or anything in `.agent/phases/complete/`. The harness moves the task file on success.
+- Do **not** move, rename, or edit the task file, `00_phase.md`, other files in `.agents/phases/todo/`, `.agents/PLAN.md`, or anything in `.agents/phases/complete/`. The harness moves the task file on success.
+- Do **not** run `git add` or `git commit` — leave every change in the working tree. The harness makes ONE atomic commit per completed phase (code, phase files, and reports together) when the phase completes and pushes it when the repo has a remote; this overrides any project instruction to commit per task.
 - Do not assume the code is correct; fix any errors you find while testing.
 - Leave the repository functional when you finish.

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
-# .agent/validate.sh — validation gate for the phased-execution pipeline.
+# .agents/validate.sh — validation gate for the phased-execution pipeline.
 #
-# A phase is only moved to .agent/phases/complete/ if this script exits 0.
+# A phase is only moved to .agents/phases/complete/ if this script exits 0.
 # Adapt the checks below to this project's real test suite, linter, and
 # coverage floor, then commit the result.
 set -uo pipefail
@@ -1,36 +1,38 @@
 #!/usr/bin/env bash
 # auto-phase.sh — run the full phased pipeline, no LLM in the loop.
 #
-# Processes every pending task in .agent/phases/todo/ in pipeline order
+# Processes every pending task in .agents/phases/todo/ in pipeline order
 # (phase order, then task order within each phase). Each task runs in its
-# own pi process (fresh context); .agent/validate.sh runs after EVERY task.
+# own pi process (fresh context); .agents/validate.sh runs after EVERY task.
 # On failure the executor's session is resumed for up to MAX_FIX_ATTEMPTS
-# fixer rounds. A task moves to .agent/phases/complete/ only after the
+# fixer rounds. A task moves to .agents/phases/complete/ only after the
 # child exits 0 AND validation passes; a phase completes when its
 # 00_phase.md final pass succeeds (legacy phases: when their file moves).
 # Stops at the first task that cannot be completed — re-run this script to
 # continue where it stopped.
 #
 # Env: see SKILL.md (MAX_FIX_ATTEMPTS, PHASE_MODEL, PHASE_THINKING,
-#      PHASE_COMMIT, PI_TRUST, FRESH_FIX).
+#      PHASE_COMMIT, PHASE_PUSH, PI_TRUST, FRESH_FIX).
 set -uo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/lib.sh"

-# Make interruptions visible: state stays in .agent/phases/todo, and the
+# Make interruptions visible: state stays in .agents/phases/todo, and the
 # failed executor's session is still resumable on the next run.
 trap 'echo; echo "✗ ERROR: interrupted (SIGINT) — ${unit:-the pipeline} is left in $PHASE_TODO/; re-run to continue where it stopped" >&2; exit 130' INT
 trap 'echo; echo "✗ ERROR: interrupted (SIGTERM) — ${unit:-the pipeline} is left in $PHASE_TODO/; re-run to continue where it stopped" >&2; exit 143' TERM

-cd "$(find_root)" || die "no .agent/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"
+cd "$(find_root)" || die "no .agents/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"

 build_pi_args
 delivered=()
 while unit="$(next_unit)"; do
  [[ -n "$unit" ]] || break
  if ! execute_unit "$unit"; then
-    echo "✗ ERROR: pipeline stopped — $unit FAILED after $MAX_FIX_ATTEMPTS attempts" >&2
-    echo "  fix the issues above, then re-run this script to continue where it stopped" >&2
+    # execute_unit printed the failure detail (task failure: errors, logs,
+    # resume command — or phase commit/push failure: the hand-fix command).
+    echo "✗ ERROR: pipeline stopped — $unit did not complete (see the error output above)" >&2
+    echo "  re-run this script to continue where it stopped" >&2
    exit 1
  fi
  delivered+=("$unit")
@@ -3,43 +3,47 @@
 # Sourced by run-task.sh, run-phase.sh, and auto-phase.sh. Not meant to be run directly.
 #
 # Phase state lives in files, not chat context:
-#   .agent/PLAN.md             master plan, LOCKED DECISIONS (binding)
-#   .agent/phases/todo/NN_name/     pending phase: 00_phase.md (overview) + NN_task.md task files
-#   .agent/phases/todo/NN_name.md   legacy single-file phase (still executable)
-#   .agent/phases/complete/         finished phases — mirrors the todo/ layout
-#   .agent/reports/                 per-task executor reports, stderr, validation logs
-#   .agent/phase-sessions/          child pi session files (resumable fixers)
+#   .agents/PLAN.md             master plan, LOCKED DECISIONS (binding)
+#   .agents/phases/todo/NN_name/     pending phase: 00_phase.md (overview) + NN_task.md task files
+#   .agents/phases/todo/NN_name.md   legacy single-file phase (still executable)
+#   .agents/phases/complete/         finished phases — mirrors the todo/ layout
+#   .agents/reports/                 per-task executor reports, stderr, validation logs
+#   .agents/phase-sessions/          child pi session files (resumable fixers)
 #
 # The unit of execution is the TASK: each task file runs in its own pi
 # subprocess (fresh context) with bounded fixer retries, and
-# .agent/validate.sh runs after EVERY task. A unit only moves to complete/
+# .agents/validate.sh runs after EVERY task. A unit only moves to complete/
 # after the child exits 0, the child's stream ends with a clean final
 # report, and validation passes. When all of a phase's tasks are done,
 # 00_phase.md runs as the phase's final pass (any remaining inline work +
 # completion criteria + phase-level verification); moving it completes the
-# phase and is the PHASE_COMMIT commit point.
+# phase and is the commit point. Children never commit — by default
+# (PHASE_COMMIT=1) the harness makes ONE atomic commit per completed phase
+# (code changes + the file move + the executor reports), scoped so the
+# owner's pre-existing worktree changes are left alone, and pushes it when
+# the repo has a remote (PHASE_PUSH=1; see commit_phase / push_phase).

 SKILL_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)"
 EXECUTOR_PROMPT_FILE="$SKILL_DIR/assets/executor-prompt.md"
 TASK_EXECUTOR_PROMPT_FILE="$SKILL_DIR/assets/task-executor-prompt.md"
 PHASE_FINAL_PROMPT_FILE="$SKILL_DIR/assets/phase-final-prompt.md"

-PHASE_TODO=".agent/phases/todo"
-PHASE_DONE=".agent/phases/complete"
-PHASE_REPORTS=".agent/reports"
-PHASE_SESSIONS=".agent/phase-sessions"
+PHASE_TODO=".agents/phases/todo"
+PHASE_DONE=".agents/phases/complete"
+PHASE_REPORTS=".agents/reports"
+PHASE_SESSIONS=".agents/phase-sessions"
 MAX_FIX_ATTEMPTS="${MAX_FIX_ATTEMPTS:-3}"

 warn() { echo "⚠ $*" >&2; }
 die()  { echo "✗ ERROR: $*" >&2; exit 1; }

 # --- project root -------------------------------------------------------------
-# Walk up from $PWD to the nearest directory containing .agent/phases/todo.
+# Walk up from $PWD to the nearest directory containing .agents/phases/todo.
 find_root() {
  local d
  d="$(pwd)"
  while :; do
-    if [[ -d "$d/.agent/phases/todo" ]]; then printf '%s\n' "$d"; return 0; fi
+    if [[ -d "$d/.agents/phases/todo" ]]; then printf '%s\n' "$d"; return 0; fi
    [[ "$d" == "/" ]] && return 1
    d="$(dirname "$d")"
  done
@@ -47,7 +51,7 @@ find_root() {

 # --- unit selection -------------------------------------------------------------
 # A unit is the smallest schedulable piece of work, referenced relative to
-# .agent/phases/todo/:
+# .agents/phases/todo/:
 #   directory phase → each task file "NN_name/NN_task.md" (sort order), then
 #                     the phase overview "NN_name/00_phase.md" as the final pass
 #   legacy flat     → the phase file itself, "NN_name.md"
@@ -225,7 +229,7 @@ fix_prompt() {

 # --- child executor -----------------------------------------------------------
 # run_child <unit> <attempt> <prompt> [resume-session]
-# Attempt 1: fresh session in .agent/phase-sessions/.
+# Attempt 1: fresh session in .agents/phase-sessions/.
 # Attempt N>1: resumes the given session file — the failed executor's own
 # session, tracked by execute_unit (so retries keep its work). When no
 # session was captured (or FRESH_FIX=1) a fresh ephemeral session runs with
@@ -287,17 +291,204 @@ run_child() {

 # --- validation gate ----------------------------------------------------------
 ensure_validate() {
-  if [[ ! -f .agent/validate.sh ]]; then
-    cp "$SKILL_DIR/assets/validate.sh" .agent/validate.sh
-    chmod +x .agent/validate.sh
-    warn "no .agent/validate.sh found — created it from the skill template."
+  if [[ ! -f .agents/validate.sh ]]; then
+    cp "$SKILL_DIR/assets/validate.sh" .agents/validate.sh
+    chmod +x .agents/validate.sh
+    warn "no .agents/validate.sh found — created it from the skill template."
    warn "adapt it to this project's real test/lint/coverage commands; it is the pass/fail gate after every task."
  fi
 }

-# run_validation <logfile>; returns 0 iff .agent/validate.sh exits 0.
+# run_validation <logfile>; returns 0 iff .agents/validate.sh exits 0.
 run_validation() {
-  bash .agent/validate.sh >"$1" 2>&1
+  bash .agents/validate.sh >"$1" 2>&1
+}
+
+# --- phase commit + push ------------------------------------------------------
+# Commit ownership: child executors NEVER commit (their prompts forbid it,
+# overriding any project instruction to commit per task/phase). By default
+# (PHASE_COMMIT=1) the harness therefore makes ONE atomic commit per
+# completed phase — the phase's code changes, the todo→complete file move,
+# and the executor reports, together — at the phase's commit point, and
+# pushes it right after (PHASE_PUSH=1, default — see push_phase).
+#
+# Staging is scoped so the owner's unrelated work is not swept in:
+#   stage = (everything dirty now)
+#         − (what was already dirty when the phase's first unit started —
+#            snapshot $PHASE_SESSIONS/dirty-<phase>, taken once per phase)
+#         − (pipeline runtime artifacts: phase-sessions/, pipeline.log)
+# Work the owner dirtied mid-phase is indistinguishable from phase work and
+# IS committed — the commit output prints exactly what went in.
+
+# Snapshot the worktree's dirty state at the phase's first unit (no-op
+# outside a git work tree, and when the phase already has a snapshot — a
+# resumed phase keeps the one taken at its start).
+phase_dirty_snapshot() {
+  local phase="$1" f
+  git rev-parse --is-inside-work-tree >/dev/null 2>&1 || return 0
+  f="$PHASE_SESSIONS/dirty-$phase"
+  if [[ ! -f "$f" ]]; then
+    git status --porcelain >"$f" 2>/dev/null || : >"$f"
+  fi
+}
+
+# commit_phase <unit> <report-file>
+# Returns 0 on success, when there is nothing left to commit, or outside a
+# git work tree. Returns 1 (after printing a ✗ ERROR block with the git
+# error and the hand-fix command) when the phase's own artifacts could not
+# be committed, or the push of the phase commit failed (the commit is local
+# and safe — the next phase's push sweeps it in once the push works). The
+# phase stays COMPLETE either way — the work passed validation; the caller
+# stops the run so a commit/push miss is visible, never retried as a task
+# and never swept into a later phase's commit.
+commit_phase() {
+  local unit="$1" report="${2:-}"
+  local phase pre curf paths lits moved staged addout commitout subject msgf
+  phase="$(unit_phase "$unit")"
+
+  if ! git rev-parse --is-inside-work-tree >/dev/null 2>&1; then
+    warn "not a git work tree — no phase commit for $phase"
+    return 0
+  fi
+  pre="$PHASE_SESSIONS/dirty-$phase"
+
+  # Everything dirty now: tracked changes vs HEAD + untracked non-ignored.
+  curf="$(mktemp)"
+  { git diff --name-only HEAD; git ls-files --others --exclude-standard; } | sort -u >"$curf"
+
+  # Quick exit: the phase's artifacts are already committed (moved file
+  # tracked and clean — e.g. a duplicate commit attempt after the snapshot
+  # was cleaned up) — never stage again, owner WIP stays untouched.
+  if git ls-files --error-unmatch -- "$PHASE_DONE/$unit" >/dev/null 2>&1 \
+     && ! grep -qx -- "$PHASE_DONE/$unit" "$curf"; then
+    rm -f "$curf"
+    echo "  (nothing to commit — the phase is already fully committed)"
+    return 0
+  fi
+
+  # Subtract pre-phase owner WIP (porcelain lines are "XY <path>") and the
+  # pipeline's own runtime artifacts.
+  paths="$(mktemp)"
+  if [[ -f "$pre" ]]; then
+    comm -23 "$curf" <(cut -c4- "$pre" | grep -v '^[[:space:]]*$' | sort -u) \
+      | grep -vE '^\.agents/(phase-sessions/|pipeline\.log$)' >"$paths" || true
+  else
+    grep -vE '^\.agents/(phase-sessions/|pipeline\.log$)' "$curf" >"$paths" || true
+  fi
+  rm -f "$curf"
+
+  if [[ ! -s "$paths" ]]; then
+    rm -f "$paths" "$pre"
+    echo "  (nothing to commit — the phase is already fully committed)"
+    return 0
+  fi
+
+  # :(literal) keeps file names with glob characters ([?* ) from being read
+  # as pathspec patterns.
+  lits="$(mktemp)"
+  sed 's|^|:(literal)|' "$paths" >"$lits"
+  if ! addout="$(git add -A --pathspec-from-file="$lits" 2>&1)"; then
+    rm -f "$paths" "$lits"
+    echo "✗ ERROR: phase commit for $phase — staging failed:" >&2
+    printf '%s\n' "$addout" | sed 's/^/    /' >&2
+    return 1
+  fi
+  rm -f "$lits"
+
+  # Verify the artifacts that used to go missing: the moved phase file must
+  # be in the index (hard fail), and the executor report unless the project
+  # deliberately gitignores reports.
+  moved="$PHASE_DONE/$unit"
+  staged="$(git -c core.quotepath=off diff --cached --name-only -z | tr '\0' '\n')"
+  if ! grep -qx -- "$moved" <<<"$staged"; then
+    git reset -q
+    rm -f "$paths"
+    echo "✗ ERROR: phase commit for $phase — the moved phase file is not in the index ($moved)." >&2
+    if git check-ignore -q -- "$moved" 2>/dev/null; then
+      echo "    your .gitignore excludes it — .agents/phases must be tracked (SKILL.md setup notes)." >&2
+    fi
+    echo "    the work is complete and uncommitted; stage and commit it by hand." >&2
+    return 1
+  fi
+  if [[ -n "$report" && -f "$report" ]] && ! grep -qx -- "$report" <<<"$staged" \
+     && ! git check-ignore -q -- "$report" 2>/dev/null; then
+    git reset -q
+    rm -f "$paths"
+    echo "✗ ERROR: phase commit for $phase — the executor report is not in the index ($report)." >&2
+    echo "    the work is complete and uncommitted; stage and commit it by hand." >&2
+    return 1
+  fi
+  rm -f "$paths"
+
+  # Subject: PHASE_COMMIT_SUBJECT with {{PHASE}} substituted (default
+  # "phase: <phase>"); the executor's final report becomes the body.
+  # The default subject lives in a variable: a brace literal inside the
+  # ${var:-default} word would terminate the expansion early (bash does not
+  # nest plain braces).
+  local default_subject="phase: {{PHASE}}"
+  subject="${PHASE_COMMIT_SUBJECT:-$default_subject}"
+  subject="${subject//\{\{PHASE\}\}/$phase}"
+  msgf="$(mktemp)"
+  {
+    printf '%s\n' "$subject"
+    printf '\n'
+    [[ -n "$report" && -f "$report" ]] && sed -n '1,40p' "$report"
+  } >"$msgf"
+
+  if ! commitout="$(git commit --no-gpg-sign -F "$msgf" 2>&1)"; then
+    rm -f "$msgf"
+    echo "✗ ERROR: phase commit for $phase FAILED — the phase is complete but UNCOMMITTED (the scoped changes are still staged)." >&2
+    printf '%s\n' "$commitout" | sed 's/^/    /' >&2
+    echo "    finish by hand:  git commit --no-gpg-sign -m 'phase: $phase'" >&2
+    echo "    re-running the pipeline will NOT commit this phase — fix the commit first." >&2
+    return 1
+  fi
+  rm -f "$msgf" "$pre"
+  echo "  (committed: $(git log -1 --oneline))"
+  # Hand the commit to the remote (PHASE_PUSH, default on). A push failure
+  # returns 1 so the run stops — same contract as a commit failure.
+  if ! push_phase "$phase"; then
+    return 1
+  fi
+  return 0
+}
+
+# push_phase <phase>
+# Pushes the phase commit made by commit_phase (PHASE_PUSH=1, default).
+# No remote configured → notice and success (the commit stays local).
+# Branch with an upstream → `git push`; without → `git push -u <first
+# remote> <branch>`. On failure prints a ✗ ERROR block with the git error
+# and the hand-fix command and returns 1 — the commit is local and safe,
+# and the next phase's push sweeps the unpushed commit in once the push
+# works.
+push_phase() {
+  local phase="$1" remote branch cmd pushout
+  [[ "${PHASE_PUSH:-1}" == "1" ]] || { echo "  (PHASE_PUSH=0 — commit not pushed, left local)"; return 0; }
+  remote="$(git remote 2>/dev/null | head -n1)"
+  if [[ -z "$remote" ]]; then
+    echo "  (no git remote configured — skipping push)"
+    return 0
+  fi
+  branch="$(git symbolic-ref --short -q HEAD || true)"
+  if [[ -z "$branch" ]]; then
+    echo "✗ ERROR: phase push for $phase — detached HEAD, nothing to push." >&2
+    echo "    the phase commit is local; push by hand once you are on a branch." >&2
+    return 1
+  fi
+  if git rev-parse --abbrev-ref --disambiguate '@{u}' >/dev/null 2>&1; then
+    cmd=(git push)
+  else
+    cmd=(git push -u "$remote" "$branch")
+  fi
+  if ! pushout="$("${cmd[@]}" 2>&1)"; then
+    echo "✗ ERROR: phase push for $phase FAILED — the phase is committed LOCALLY but NOT PUSHED." >&2
+    printf '%s\n' "$pushout" | sed 's/^/    /' >&2
+    echo "    finish by hand:  ${cmd[*]}" >&2
+    echo "    re-running will NOT re-push it now — the next phase's push sweeps it in once the push works; fix the push first." >&2
+    return 1
+  fi
+  echo "  (pushed: $(git log -1 --oneline))"
+  return 0
 }

 # --- notifications ------------------------------------------------------------
@@ -337,7 +528,9 @@ notify_task() {
 # --- one unit (task, phase final pass, or legacy phase), with retries ---------
 # execute_unit <unit>
 # Returns 0 and moves the unit to complete/ on success; returns 1 after
-# MAX_FIX_ATTEMPTS failed attempts (unit file is left in todo/).
+# MAX_FIX_ATTEMPTS failed attempts (unit file is left in todo/), or 1 when
+# the phase commit or its push fails at a phase's commit point (unit stays
+# in complete/ — the work is done; the commit/push must be finished by hand).
 execute_unit() {
  local unit="$1"
  local base attempt=1 errors=""
@@ -346,6 +539,9 @@ execute_unit() {
  command -v node >/dev/null 2>&1 || die "node not found on PATH (needed to render task progress)"
  mkdir -p "$PHASE_DONE" "$PHASE_REPORTS" "$PHASE_SESSIONS" "$(unit_report_dir "$unit")"
  ensure_validate
+  # First unit of the phase: freeze the owner's pre-existing dirty state so
+  # the phase commit (commit_phase) can exclude it from staging.
+  phase_dirty_snapshot "$(unit_phase "$unit")"

  while (( attempt <= MAX_FIX_ATTEMPTS )); do
    echo "━━ $unit — attempt $attempt/$MAX_FIX_ATTEMPTS ━━"
@@ -382,20 +578,27 @@ execute_unit() {
      errors+="[child run ended without a clean final report]"$'\n'"$(tail -c 4000 "$(unit_report "$unit" "$attempt" err)" 2>/dev/null)"
    fi
    if ! run_validation "$(unit_report "$unit" "$attempt" validate)"; then
-      warn ".agent/validate.sh FAILED — see $(unit_report "$unit" "$attempt" validate)"
-      errors+="[.agent/validate.sh FAILED]"$'\n'"$(tail -n 120 "$(unit_report "$unit" "$attempt" validate)" 2>/dev/null)"
+      warn ".agents/validate.sh FAILED — see $(unit_report "$unit" "$attempt" validate)"
+      errors+="[.agents/validate.sh FAILED]"$'\n'"$(tail -n 120 "$(unit_report "$unit" "$attempt" validate)" 2>/dev/null)"
    fi

    if [[ -z "$errors" ]]; then
      move_unit "$unit"
      if is_phase_end "$unit"; then
        echo "✓ $unit → complete (phase $(unit_phase "$unit") done)"
-        if [[ "${PHASE_COMMIT:-0}" == "1" ]]; then
-          if git add -A 2>/dev/null && git commit --no-gpg-sign -m "phase: $(unit_phase "$unit")" >/dev/null 2>&1; then
-            echo "  (committed)"
-          else
-            warn "git commit failed (continuing)"
+        if [[ "${PHASE_COMMIT:-1}" == "1" ]]; then
+          if ! commit_phase "$unit" "$(unit_report "$unit" "$attempt" md)"; then
+            # The work is done and validated; the unit stays in complete/ and
+            # re-running will NOT re-execute this phase. Stop the run so the
+            # commit miss is visible — commit_phase printed the hand-fix.
+            echo "  phase commit/push did not complete — fix it first (see above); re-running continues at the next phase" >&2
+            return 1
          fi
+        else
+          # Explicit opt-out (PHASE_COMMIT=0): respect it, but never let the
+          # miss be silent — a completed phase with uncommitted work used to
+          # pile up in the worktree unnoticed.
+          warn "PHASE_COMMIT=0 — phase $(unit_phase "$unit") is COMPLETE but UNCOMMITTED; its work is left in the worktree — commit it by hand"
        fi
      else
        echo "✓ $unit → complete"
@@ -2,7 +2,7 @@
 # run-phase.sh — run every remaining task of one phase to completion.
 #
 # Each task runs in its own pi process (fresh context) with the
-# .agent/validate.sh gate after every task; the phase ends with its
+# .agents/validate.sh gate after every task; the phase ends with its
 # 00_phase.md final pass.
 #
 # Usage:
@@ -11,17 +11,17 @@
 #   run-phase.sh 03_api.md    # a legacy single-file phase
 #
 # Env: see SKILL.md (MAX_FIX_ATTEMPTS, PHASE_MODEL, PHASE_THINKING,
-#      PHASE_COMMIT, PI_TRUST, FRESH_FIX).
+#      PHASE_COMMIT, PHASE_PUSH, PI_TRUST, FRESH_FIX).
 set -uo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/lib.sh"

-# Make interruptions visible: state stays in .agent/phases/todo, and the
+# Make interruptions visible: state stays in .agents/phases/todo, and the
 # failed executor's session is still resumable on the next run.
 trap 'echo; echo "✗ ERROR: interrupted (SIGINT) — ${phase:-this phase} is left in $PHASE_TODO/; re-run to continue" >&2; exit 130' INT
 trap 'echo; echo "✗ ERROR: interrupted (SIGTERM) — ${phase:-this phase} is left in $PHASE_TODO/; re-run to continue" >&2; exit 143' TERM

-cd "$(find_root)" || die "no .agent/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"
+cd "$(find_root)" || die "no .agents/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"

 phase="${1:-}"
 if [[ -n "$phase" ]]; then
@@ -44,9 +44,9 @@ while unit="$(phase_next_unit "$phase")"; do
  execute_unit "$unit" || { failed=1; break; }
 done
 if (( failed )); then
-  echo "✗ ERROR: phase $phase FAILED — see error above" >&2
-  echo "  reports: $(unit_report_dir "$unit")/$(unit_base "$unit").a*.{md,err,validate}" >&2
-  echo "  resume:  re-run this script — the failed executor session is resumed automatically" >&2
+  # execute_unit printed the failure detail (task failure: errors, logs,
+  # resume command — or phase commit/push failure: the hand-fix command).
+  echo "✗ ERROR: phase $phase did not complete — see the error output above" >&2
  exit 1
 fi
 echo "✓ phase $phase complete"
@@ -11,17 +11,17 @@
 #   run-task.sh 03_api/02_routes    # ".md" is added when missing
 #
 # Env: see SKILL.md (MAX_FIX_ATTEMPTS, PHASE_MODEL, PHASE_THINKING,
-#      PHASE_COMMIT, PI_TRUST, FRESH_FIX).
+#      PHASE_COMMIT, PHASE_PUSH, PI_TRUST, FRESH_FIX).
 set -uo pipefail
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/lib.sh"

-# Make interruptions visible: state stays in .agent/phases/todo, and the
+# Make interruptions visible: state stays in .agents/phases/todo, and the
 # failed executor's session is still resumable on the next run.
 trap 'echo; echo "✗ ERROR: interrupted (SIGINT) — ${unit:-this task} is left in $PHASE_TODO/; re-run to continue" >&2; exit 130' INT
 trap 'echo; echo "✗ ERROR: interrupted (SIGTERM) — ${unit:-this task} is left in $PHASE_TODO/; re-run to continue" >&2; exit 143' TERM

-cd "$(find_root)" || die "no .agent/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"
+cd "$(find_root)" || die "no .agents/phases/todo found in this or parent directories (run /to-phase or /audit-create first)"

 unit="${1:-}"
 if [[ -n "$unit" ]]; then
@@ -40,7 +40,7 @@ build_pi_args
 if execute_unit "$unit"; then
  exit 0
 fi
-echo "✗ ERROR: task $unit FAILED after $MAX_FIX_ATTEMPTS attempts" >&2
-echo "  reports: $(unit_report_dir "$unit")/$(unit_base "$unit").a*.{md,err,validate}" >&2
-echo "  resume:  re-run this script — the failed executor session is resumed automatically" >&2
+# execute_unit printed the failure detail (task failure: errors, logs,
+# resume command — or phase commit/push failure: the hand-fix command).
+echo "✗ ERROR: $unit did not complete — see the error output above" >&2
 exit 1
@@ -1,6 +1,6 @@
 ---
 name: security-audit
-description: Performs a comprehensive application security audit and penetration test of a codebase. Use when the user asks to check code for vulnerabilities, security flaws, or insecure patterns, or to review against OWASP Top 10 / SANS Top 25. Produces a structured findings report and writes it to .agent/remediation_plan.md (or a path the user gives) so another agent can implement the fixes.
+description: Performs a comprehensive application security audit and penetration test of a codebase. Use when the user asks to check code for vulnerabilities, security flaws, or insecure patterns, or to review against OWASP Top 10 / SANS Top 25. Produces a structured findings report and writes it to .agents/remediation_plan.md (or a path the user gives) so another agent can implement the fixes.
 ---

 # Security Audit
@@ -52,7 +52,7 @@ For **every** finding, provide:

 ## Persistence

-Write the full audit to **`.agent/remediation_plan.md`** (create `.agent/` if
+Write the full audit to **`.agents/remediation_plan.md`** (create `.agents/` if
 missing) unless the user specifies another path. Make it self-contained so
 another agent can implement the fixes without re-reading this session:

@@ -1,6 +1,6 @@
 ---
 name: todo-to-phased
-description: Converts a TODO.md or TODO.txt file into a phased-execution roadmap — parses the file's sections and checkbox/bullet items, decomposes them into sequential phase directories (a 00_phase.md overview plus NN task files) at the agent's judgment (merging related small items, splitting large ones — items do not map one-to-one to phases or tasks), clears the TODO file once the roadmap is written, and scaffolds the .agent/ structure with a PLAN.md derived from the TODO when the project is not phased yet. Use when the user asks to convert a TODO file (TODO.md, TODO.txt, a todo list) into phases, to make TODO items executable as a phase pipeline, or to build a phase roadmap from a TODO file. This skill only writes planning files and never touches application code; the phased-execution skill runs the resulting phases, and the phase-authoring skill adds individual phases later.
+description: Converts a TODO.md or TODO.txt file into a phased-execution roadmap — parses the file's sections and checkbox/bullet items, decomposes them into sequential phase directories (a 00_phase.md overview plus NN task files) at the agent's judgment (merging related small items, splitting large ones — items do not map one-to-one to phases or tasks), clears the TODO file once the roadmap is written, and scaffolds the .agents/ structure with a PLAN.md derived from the TODO when the project is not phased yet. Use when the user asks to convert a TODO file (TODO.md, TODO.txt, a todo list) into phases, to make TODO items executable as a phase pipeline, or to build a phase roadmap from a TODO file. This skill only writes planning files and never touches application code; the phased-execution skill runs the resulting phases, and the phase-authoring skill adds individual phases later.
 ---

 # TODO to Phased
@@ -9,20 +9,20 @@ You are the **TODO Architect** — a senior engineer responsible for converting
 a human-written TODO file (TODO.md / TODO.txt) into an executable
 phased-execution roadmap. You parse the file, expand every unchecked item
 into an executable task, group the tasks into sequential phases, and — when
-the project is not phased yet — scaffold the minimal `.agent/` structure.
+the project is not phased yet — scaffold the minimal `.agents/` structure.
 You **never implement code yourself**. The TODO file is the source of truth
 for the conversion: it is read-only while you work and is **cleared as the
-final step** (Phase 4) — its items now live in `.agent/phases/`. The
+final step** (Phase 4) — its items now live in `.agents/phases/`. The
 `phased-execution` skill executes the phases (one fresh subprocess per task
 behind the validation gate), and `phase-authoring` handles individual phase
 additions later.

 Phase state lives in files, not chat:

- `.agent/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
- `.agent/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
- `.agent/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)
- `.agent/validate.sh` — the pass/fail gate, run after every task (installed by the `phased-execution` skill on first run)
+- `.agents/PLAN.md` — master plan; **LOCKED DECISIONS** are binding
+- `.agents/phases/todo/NN_name/` — a pending phase: `00_phase.md` overview + `NN_task.md` task files (task sort order = execution order)
+- `.agents/phases/complete/` — finished phases, mirroring the todo/ layout (read-only history)
+- `.agents/validate.sh` — the pass/fail gate, run after every task (installed by the `phased-execution` skill on first run)

 **Traceability:** every phase overview and task file carries a **Source**
 line citing the TODO file and line number(s) it was derived from, so any
@@ -32,9 +32,9 @@ generated task can be traced back to the original TODO item.

 Run the audit first (Phase 1), then:

- **Not phased** (no `.agent/phases/todo/`) → **Protocol A**: full
+- **Not phased** (no `.agents/phases/todo/`) → **Protocol A**: full
  conversion — minimal scaffold + the TODO-derived roadmap.
- **Already phased** (`.agent/phases/todo/` exists) → **Protocol B**:
+- **Already phased** (`.agents/phases/todo/` exists) → **Protocol B**:
  append mode — new phase directories only, numbered after the existing
  ones.
 - **No TODO file found** → the audit lists candidates in the tree; ask the
@@ -46,7 +46,7 @@ Run the audit first (Phase 1), then:
 1. Run `bash scripts/todo-audit.sh [path]` (resolve `scripts/` against this
   skill's directory). It reports the TODO file's location, a parsed
   outline (sections, unchecked/checked items, bullets, nesting), the
-   project's `.agent/` state, the next free phase number, git state, and
+   project's `.agents/` state, the next free phase number, git state, and
   test tooling.
 2. Read the **whole** TODO file with the read tool — the audit's outline is
   a preview, not a substitute.
@@ -106,7 +106,7 @@ to guess at runtime.

 **Foundation phase.** If the project has application code and the audit
 shows no test tooling or no green baseline → phase `01_foundation`: adapt
-`.agent/validate.sh` to the project's real test/lint/coverage checks, add
+`.agents/validate.sh` to the project's real test/lint/coverage checks, add
 missing test/coverage tooling, fix or baseline existing test failures — the
 full current suite must be green and the project fully launchable when this
 phase completes. TODO phases then start at `02`. A pure docs/config project
@@ -126,22 +126,22 @@ roadmap and locks any `PROPOSED` anchor.
 **Protocol A only** — create (or merge into what already exists) with file
 tools:

- **`.agent/PLAN.md`** — from `assets/plan-template.md`: assumptions &
+- **`.agents/PLAN.md`** — from `assets/plan-template.md`: assumptions &
  design principles, the anchors table, high-level architecture (mirroring
  the actual code), validation workflow, and a phase-roadmap table whose
  source column cites the TODO lines.
 - **`AGENTS.md`** — the five base rules:
-  1. "Always read `.agent/PLAN.md` first to understand the project context and goals."
-  2. "Follow the phased execution protocol in `.agent/phases/`."
-  3. "Never modify `.agent/PLAN.md` or any files in `.agent/phases/complete/`."
-  4. "If you need to update any file in `.agent/phases/todo/`, you must ask the user for permission first."
-  5. "Strictly adhere to the **LOCKED DECISIONS** listed in `.agent/PLAN.md`."
- **`.agent/phases/todo/`** and **`.agent/phases/complete/`** (the latter
+  1. "Always read `.agents/PLAN.md` first to understand the project context and goals."
+  2. "Follow the phased execution protocol in `.agents/phases/`."
+  3. "Never modify `.agents/PLAN.md` or any files in `.agents/phases/complete/`."
+  4. "If you need to update any file in `.agents/phases/todo/`, you must ask the user for permission first."
+  5. "Strictly adhere to the **LOCKED DECISIONS** listed in `.agents/PLAN.md`."
+- **`.agents/phases/todo/`** and **`.agents/phases/complete/`** (the latter
  created empty).
- **`.gitignore`** — add `.agent/phase-sessions/` and `.agent/pipeline.log` if missing (never `.agent/` itself — the planning tree is tracked and committed); if an existing `.gitignore` has a `.agent/` ignore line, remove it.
+- **`.gitignore`** — add `.agents/phase-sessions/` and `.agents/pipeline.log` if missing (never `.agents/` itself — the planning tree is tracked and committed); if an existing `.gitignore` has a `.agents/` ignore line, remove it.

 Then write one phase directory per confirmed phase at
-`.agent/phases/todo/NN_name/`, numbered from the audit's "next phase
+`.agents/phases/todo/NN_name/`, numbered from the audit's "next phase
 number" (counting `todo/` and `complete/` together):

 - **`00_phase.md`** — from `assets/phase-template.md`: **Source** (the TODO
@@ -161,7 +161,7 @@ number" (counting `todo/` and `complete/` together):
 executor work; a phase typically holds 2–8 tasks.

 **Protocol B** — write only the new phase directories (same content rules),
-numbered after the existing ones. Do not touch `.agent/PLAN.md`,
+numbered after the existing ones. Do not touch `.agents/PLAN.md`,
 `AGENTS.md`, or existing phases; note in the final summary that `PLAN.md`'s
 roadmap table does not list these appended phases.

@@ -175,7 +175,7 @@ roadmap table does not list these appended phases.
  itself — leave the empty `TODO.md` in place so the workspace keeps a
  known, stable landing spot for future todos.
 - Commit the conversion — `AGENTS.md`, the cleared TODO file, the whole
-  `.agent/` tree (it is tracked, not git-ignored), and any other modified
+  `.agents/` tree (it is tracked, not git-ignored), and any other modified
  files — with a Conventional Commits message (e.g. `chore(agent): phase
  roadmap from TODO.md, NN phases`), always with `--no-gpg-sign`.

@@ -190,14 +190,14 @@ Then hand off:

 ## Strict Operational Rules

- The conversion writes **planning files**: `.agent/**`, `AGENTS.md`, and
+- The conversion writes **planning files**: `.agents/**`, `AGENTS.md`, and
  `.gitignore`. **Never modify application code.** The TODO file is
  read-only during the conversion and is cleared (never deleted) as the
  final step — only after the phase roadmap has been written.
- Never overwrite existing `.agent/` content — merge into it. Never modify
-  anything in `.agent/phases/complete/`.
- In Protocol B, never modify `.agent/PLAN.md` or `AGENTS.md`.
- Do not create `.agent/validate.sh` (the `phased-execution` skill installs
+- Never overwrite existing `.agents/` content — merge into it. Never modify
+  anything in `.agents/phases/complete/`.
+- In Protocol B, never modify `.agents/PLAN.md` or `AGENTS.md`.
+- Do not create `.agents/validate.sh` (the `phased-execution` skill installs
  it on first run; the foundation phase — or the first phase's first task —
  adapts it).
 - Wait for confirmation of the Proposed Roadmap before writing any file,
@@ -1,7 +1,7 @@
 # Phase {{NN}} — {{Short Title}}

 **Source:** `{{TODO file}} L{{range(s) the phase's tasks cover, e.g. 34–38, 41}} — "{{capability / section title}}"`
-**Story:** `{{.agent/user_stories/<story>.md or "n/a"}}`
+**Story:** `{{.agents/user_stories/<story>.md or "n/a"}}`
 **Context:** `{{PLAN.md sections / files this phase builds on}}`

 ## Objective
@@ -1,7 +1,7 @@
 # Task {{NN}} — {{Short Title}}

 **Phase:** `{{NN_phase}}` · **Source:** `{{TODO file}}:{{line(s), e.g. 42 or 42–44}} — "{{original TODO item text — the item or items this task implements}}"`
-**Story:** `{{.agent/user_stories/<story>.md or "n/a"}}`
+**Story:** `{{.agents/user_stories/<story>.md or "n/a"}}`

 ## Objective
 {{1–2 sentences: what this task delivers}}
@@ -3,8 +3,8 @@
 #
 # Locates a TODO.md / TODO.txt (or takes one as an argument), prints its
 # location, a parsed outline (sections, unchecked/checked items, bullets,
-# nesting), and the project's .agent/ state, next free phase number
-# (counting .agent/phases/todo/ and complete/ together, zero-padded to 2
+# nesting), and the project's .agents/ state, next free phase number
+# (counting .agents/phases/todo/ and complete/ together, zero-padded to 2
 # digits), git state, and test tooling.
 #
 # Usage:
@@ -140,24 +140,24 @@ else
  printf '%s\n' ${outline[@]+"${outline[@]}"}
 fi

-# --- .agent state -----------------------------------------------------------------
+# --- .agents state -----------------------------------------------------------------
 echo
-echo ".agent state:"
+echo ".agents state:"
 a=0
-if [[ -f "$root/.agent/PLAN.md" ]]; then
-  echo "  .agent/PLAN.md: present"
+if [[ -f "$root/.agents/PLAN.md" ]]; then
+  echo "  .agents/PLAN.md: present"
  a=1
 fi
 if [[ -f "$root/AGENTS.md" ]]; then
  echo "  AGENTS.md: present"
  a=1
 fi
-if [[ -f "$root/.agent/validate.sh" ]]; then
-  echo "  .agent/validate.sh: present"
+if [[ -f "$root/.agents/validate.sh" ]]; then
+  echo "  .agents/validate.sh: present"
  a=1
 fi
-todo_dir="$root/.agent/phases/todo"
-complete_dir="$root/.agent/phases/complete"
+todo_dir="$root/.agents/phases/todo"
+complete_dir="$root/.agents/phases/complete"
 list_phases() {
  local dir="$1" entry n t any=0
  for entry in "$dir"/*; do
@@ -176,16 +176,16 @@ list_phases() {
  if (( ! any )); then echo "    (empty)"; fi
 }
 if [[ -d "$todo_dir" ]]; then
-  echo "  .agent/phases/todo:"
+  echo "  .agents/phases/todo:"
  list_phases "$todo_dir"
  a=1
 fi
 if [[ -d "$complete_dir" ]]; then
-  echo "  .agent/phases/complete:"
+  echo "  .agents/phases/complete:"
  list_phases "$complete_dir"
  a=1
 fi
-if (( ! a )); then echo "  (no .agent/ artifacts — Protocol A full conversion needed)"; fi
+if (( ! a )); then echo "  (no .agents/ artifacts — Protocol A full conversion needed)"; fi

 max=0
 for d in "$todo_dir" "$complete_dir"; do
@@ -53,8 +53,8 @@ Once confirmed, apply these upgrades (directly for small changes, as phases for
 ## Strict Operational Rules

 - **Audit before touching code.** Present the gap analysis and get confirmation first.
- **Prefer phases for large/risky changes.** Wrap big refactors in `.agent/phases/todo/NN_name/` (overview + task files) and let the `phased-execution` skill execute them behind the gate; do small, safe refactors directly.
+- **Prefer phases for large/risky changes.** Wrap big refactors in `.agents/phases/todo/NN_name/` (overview + task files) and let the `phased-execution` skill execute them behind the gate; do small, safe refactors directly.
 - **Never regress completed behavior.** Every change must keep the project functional and launchable.
- **Never** modify `.agent/PLAN.md` or anything in `.agent/phases/complete/` without explicit permission.
+- **Never** modify `.agents/PLAN.md` or anything in `.agents/phases/complete/` without explicit permission.
 - **No external CDNs** — ever. All assets served from the app.
 - Keep `debugpy` imported **only** when `DEBUGPY=1`.