@garygentry/feature-forge 0.2.14 → 0.3.1

package/adapters/pi/skills/forge-2-tech/references/stage-exit-protocol.md

@@ -0,0 +1,268 @@
+# Stage Exit Protocol
+
+The single source of truth for how every forge **authoring** stage closes. It
+replaces the old ad-hoc "Next steps:" bullet lists with one fixed, correctly-ordered
+sequence: **verify (if missing or stale) → `/clear` → run the next command.**
+
+Two principles this protocol encodes (do not relitigate — they are locked product
+decisions):
+
+1. **Clearing is recommended on its own merits at every stage boundary** — a clean
+   start for the next stage — *not* as a proxy for a full context window. Window
+   fullness only changes *how emphatically* the clear is recommended, never *whether*
+   it is.
+2. **Verify happens before the clear, never after** — in the authoring session, whether
+   manual **or** auto. Verify's clean-room subagent is dispatched from the *current*
+   session, so the findings digest and any fix decision land where the context to act on
+   them still exists. This holds for auto-verify too: the stage skill dispatches the
+   clean-room verify (and any autoFix) at stage end, in-session, before the exit — it is
+   **not** deferred to the navigator, which runs *after* the `/clear` with none of the
+   authoring context. Clearing first throws that context away.
+
+## How this file is used
+
+The five authoring stages (`forge-0-epic` … `forge-4-backlog`) close with the
+**Scripted Stage Exit**: a short stamped block (below) that runs
+`forge-session.py stage-exit`, obeys the DIRECTIVES it prints per the **directive
+contract** in this file, and prints the script-emitted NEXT-STEPS block verbatim as the
+absolute last output. All the conditional logic the old prose blocks asked the model to
+compute (effective auto-verify, freshness collapse, gate selection, host wording) now
+lives in the script, deterministically; only genuinely interactive work (clean-room
+subagent dispatch, `AskUserQuestion` gates) remains prose — specified once here, not
+per stage.
+
+The loop (`forge-5-loop`) keeps its bespoke exits: it stamps the **standard block**
+(step-6 epic-member handoff) and the **warm variant** (all-done closing) below,
+verbatim. `forge-6-docs` is **terminal** — it stamps no exit block.
+
+A drift-guard test (`tests/test_stage_exit_protocol.py`) asserts each stamp site still
+contains its block, so an edit here must be mirrored into every stamp site (and
+vice-versa).
+
+## Stamp sites
+
+| Stamp site | Block |
+|---|---|
+| `forge-0-epic` … `forge-4-backlog` | scripted-stage-exit stamp |
+| `forge-5-loop` (step-6 epic-member handoff) | standard |
+| `forge-5-loop` (all-done closing → docs) | warm |
+
+The scripted stamp fills one build-time slot, `{stage-exit-args}` — the per-stage
+argument list (e.g. `--feature "{feature}" --stage forge-2-tech`; the epic stage passes
+`--feature "{epic}" --stage forge-0-epic --next-feature "{first-actionable-feature}"`).
+`{feature}` / `{epic}` / `{specsDir}` / `{first-actionable-feature}` remain runtime
+placeholders the skill resolves before running the command, exactly as elsewhere.
+
+<!-- BEGIN: scripted-stage-exit-stamp -->
+**Close this stage with the Scripted Stage Exit** (contract: `references/stage-exit-protocol.md`; do not improvise a "Next steps" list). Run:
+
+```bash
+R="$(bash -c 'for d in "${CLAUDE_PLUGIN_ROOT:-}" "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/cache/*/feature-forge/* "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done')"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" stage-exit {stage-exit-args} --specs-dir "{specsDir}" --host claude
+```
+
+Obey the DIRECTIVES it prints, in order, per the directive contract: `runInStageVerify: true` → dispatch the in-stage clean-room verify now (honoring `autoFixEligible`); `verifyGate: "standard"` → present the Standard Verify Gate; `verifyGate: "manual-print"` → print the `verifyCommand` for the user; non-empty `invalidAutoVerifyKeys` → print a one-line warning. Then **print the NEXT-STEPS block verbatim as your absolute last output — nothing after its sentinel line.**
+<!-- END: scripted-stage-exit-stamp -->
+
+## Directive contract
+
+`stage-exit` emits a DIRECTIVES object and a NEXT-STEPS block. The skill executes the
+directives **in this order**; the script has already computed every conditional, so a
+directive is an instruction, not a question to re-derive.
+
+### `invalidAutoVerifyKeys` (non-empty)
+
+Print a one-line warning first (e.g. "⚠️ forge.config.json `autoVerifyStages` has
+unknown keys: … — they are ignored; fix the typo").
+
+### `runInStageVerify: true` — in-stage auto-verify {stageNoun}
+
+Auto-verify is effective for this stage and verification is outstanding — verify **now,
+in this session** (principle #2 applied to auto-verify: the digest and any fix decision
+land here, where the authoring context still exists — not deferred to a post-`/clear`
+navigator):
+
+1. **Clean-room verify (require-clean).** Dispatch the clean-room `forge-verifier`
+   subagent from this session in require-clean mode — the same path the navigator uses
+   (`skills/forge-verify/SKILL.md`). Dispatch it **synchronously and await its digest
+   inline** — do **not** run it in the background or announce it as "still running";
+   the digest and any fix decision must land in this session. It inherits none of this
+   session's context, so no `/clear` is needed and only a compact digest returns.
+   **Clean-room unavailable** (no `Agent` tool, `forge-verifier` not dispatchable) **or
+   a non-answer returned** (the verifier returned a placeholder / "still running" /
+   delegation message instead of a findings block): do **not** run inline and do **not**
+   silently accept the non-answer as a pass — leave verify **pending** so the navigator
+   catch-up fires on a later Claude-host `/skill:forge`, print the
+   `verifyCommand` for the user to run, and continue to the NEXT-STEPS block.
+2. **Verify passed / no findings** → the fresh verify state is recorded by the
+   clean-room run; continue to the NEXT-STEPS block.
+3. **Verify found findings** →
+   - **`autoFixEligible: true` AND the findings document has zero unresolved decision
+     points** → chain `feature-forge:forge-fix` in-session (it owns its own commit +
+     step tracking), then run a **mandatory re-verify** in require-clean mode. Continue
+     to the NEXT-STEPS block only if the re-verify passes. On any precondition miss, a
+     forge-fix early stop, or a red re-verify, fall through to the digest gate below —
+     never a silent partial mutation. (`autoFixEligible` already folds in the config
+     `autoFix` flag and the clean-tree precondition; a dirty tree or
+     `gitCommitAfterStage: false` arrives here as `false`.)
+   - **`autoFixEligible: false`, or unresolved decision points** → surface a **compact
+     findings digest** as text, then present the gate via `AskUserQuestion`: **Run
+     `forge-fix` now** *(recommended — you are in-context and the digest is right
+     here)* / **Clear + advance anyway** (leave the findings for later) / **Stop
+     here**. Do **not** hard-stop and do **not** silently walk past. Act on the choice,
+     then continue to the NEXT-STEPS block.
+
+### `verifyGate: "standard"` — the Standard Verify Gate
+
+Auto-verify is off for this stage and verification is outstanding (`verifyState` is
+`never`, `stale`, or `failing`). Verify **now, before clearing**, using
+`AskUserQuestion` with exactly these three options — but only when the host has a
+question mechanism **and** the clean-room path is available (the `Agent` tool plus a
+dispatchable `forge-verifier` subagent); otherwise degrade exactly as `manual-print`
+below:
+
+- **Verify {stageNoun} now** *(recommended)* — dispatch the clean-room `forge-verifier`
+  subagent from this session in require-clean mode; the digest returns here so any fix
+  decision keeps its context. One-time — it does **not** change config.
+- **Verify now + enable auto-verify going forward** — verify now **and** patch
+  `"autoVerify": true` into `forge.config.json` in place (preserve formatting and every
+  other key) so future stages verify automatically, no prompt. This complements the
+  `forge-init` opt-in. **Do not auto-commit this config change** — treat it like
+  `notes`: a user-facing edit the user commits on their own cadence, never folded into
+  a stage's artifact commit.
+- **Skip for now** — go straight to the NEXT-STEPS block without verifying. Record this
+  stage's verify status as `"skipped"` in pipeline state (mirroring the existing skip
+  handling) **only** on an explicit skip — a skip does not go stale.
+
+If verify runs and finds findings, handle them exactly as in the in-stage flow above
+(digest + `AskUserQuestion` gate; `autoFixEligible` applies unchanged).
+
+### `verifyGate: "manual-print"`
+
+Verification is outstanding but the host cannot present the gate or dispatch
+clean-room. Do **not** run verify inline — print the `verifyCommand` for the user to
+run (mirroring `autoInvokeNextStage`), offer the auto-verify enable as plain text only
+if a config write is possible, and continue to the NEXT-STEPS block. Verify state stays
+outstanding, so the navigator catch-up can fire later.
+
+### `verifyGate: "none"`
+
+Verification is already resolved (fresh or explicitly skipped) or the in-stage run
+above covers it. Say so in one line and continue to the NEXT-STEPS block.
+
+### `epicReconcile` (epic backflow — present only when there are open requests)
+
+Emitted only when the exiting member carries `open` `epicChangeRequests` (recorded by
+`forge-1-prd`/`forge-2-tech` when the epic *decomposition* itself must change — see
+`references/pipeline-state-schema.json`). Absent on the common path and for standalone
+features. The script has already folded the routing into the NEXT-STEPS block, so this
+directive is informational — you do **not** re-derive the wording:
+
+- `required: true` (at least one `blocksCurrent: true` request) — the NEXT-STEPS block's
+  fenced **primary** command is the epic reconcile command
+  (`/skill:forge-0-epic {epic}`), and the normal next stage is demoted to a
+  follow-up line ("After reconciling, continue with …"). This is *reconcile-before-specs*:
+  proceeding would author artifacts against a decomposition that is about to change. It is
+  strongest when exiting `forge-2-tech` (next is `forge-3-specs`, the point of no cheap
+  return).
+- `reminder: true` (only `blocksCurrent: false` requests) — normal next-stage routing is
+  unchanged; the block appends a non-blocking reminder line ("You also flagged N epic
+  change(s) to reconcile when convenient …"). This is *finish-then-edit*.
+
+Either way the added lines are host-neutral (no literal `/clear`) and sit **above** the
+sentinel; just print the NEXT-STEPS block verbatim as always.
+
+### Deferred decisions — do not solicit next-stage decisions at this exit
+
+Each stage owns its own decisions. At a stage exit, do **not** pull a *later* stage's
+decision forward — do not ask the user (or decide unilaterally) something that properly
+belongs to the next stage's interview (e.g. at `forge-1-prd` exit, don't settle the
+concrete cache backend that `forge-2-tech` will design). Soliciting it here guesses ahead
+of the stage that owns the context, and the answer has nowhere durable to live.
+
+Instead, when you notice a decision that belongs downstream, **record it structurally** as
+a `deferredDecisions[]` entry on this feature's `.pipeline-state.json` by running
+`state-decision` (`--rationale` and `--target-stage` are optional; the verb stamps
+`raisedAt` and `status: "open"` for you). Add `--epic "{epic}"` when this feature is an
+epic member — required, per the Pipeline State Protocol in `references/shared-conventions.md`:
+
+```bash
+R="$(bash -c 'for d in "${CLAUDE_PLUGIN_ROOT:-}" "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/cache/*/feature-forge/* "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done')"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" state-decision \
+  --feature "{feature}" --question "<phrased for the target stage>" \
+  --rationale "<why it belongs downstream>" --target-stage "<owning stage>" \
+  --raised-by "{stage}" --specs-dir "{specsDir}"
+```
+
+This keeps the exit focused on *this* stage's next-step routing while carrying the open
+question forward for the owning stage to resolve (it flips `status` to `addressed` when it
+does). Prefer a `deferredDecisions[]` entry over stuffing the same thing into the free-text
+`notes` string. This is a recording affordance, not a gate: never block the exit on it.
+
+### The NEXT-STEPS block (always last)
+
+Print the script's NEXT-STEPS block **verbatim as your absolute last output**. Nothing
+follows its final sentinel line (`─ forge: end of stage ─`) — no caveats, no summary,
+no sign-off. The block already carries the `/clear` recommendation (host-aware wording
+via `--host`) and the exact next command, so trailing prose can only push the user's
+next action out of view.
+
+---
+
+## Standard block
+
+Stamped at the loop's step-6 epic-member handoff (finishing feature A → starting
+feature B's PRD). It self-adapts: step 1's verify gate only fires when verification is
+actually outstanding, so at a boundary where verify already ran (or was explicitly
+skipped, or auto-verify is on) it silently collapses to just the `/clear` →
+next-command steps.
+
+Slots: `{stage}` (a lowercase noun phrase), `{verify-command}`, `{next-command}`.
+
+<!-- BEGIN: standard-exit-block -->
+**This stage is done — walk the user through the Stage Exit Protocol** before moving on. The order is fixed, and step 2 is something only the user can do:
+
+1. **Verify {stage} first — if it isn't already verified.** If verify already ran in this session — via the in-stage auto-verify on the authoring stages, or the interactive impl-verify offered above on the loop — or is already fresh on record, or the stage was explicitly skipped, say so and go straight to step 2. Only when `autoVerify` is off for this stage **and** verify is **missing or stale** do you present the **Standard Verify Gate**: verify **now, before clearing**, using `AskUserQuestion` with exactly these three options — but only when the host has a question mechanism **and** the clean-room path is available (the `Agent` tool plus a dispatchable `forge-verifier` subagent):
+   - **Verify {stage} now** *(recommended)* — dispatch the clean-room `forge-verifier` subagent from this session in require-clean mode; the digest returns here so any fix decision keeps its context. One-time — it does **not** change config.
+   - **Verify now + enable auto-verify going forward** — verify now **and** patch `"autoVerify": true` into `forge.config.json` in place (preserve formatting and every other key) so future stages verify automatically, no prompt. This complements the `forge-init` opt-in. **Do not auto-commit this config change** — treat it like `notes`: a user-facing edit the user commits on their own cadence, never folded into a stage's artifact commit.
+   - **Skip for now** — go straight to `/clear` and the next command without verifying. Record this stage's verify status as `"skipped"` in pipeline state (mirroring the existing skip handling) **only** on an explicit skip — a skip does not go stale.
+
+   **Host / clean-room fallback (not a user-selectable option):** if the question mechanism, the `Agent` tool, or the `forge-verifier` subagent is unavailable, do **not** run clean-room — degrade to printing `{verify-command}` for the user to run inline/manually (mirroring `autoInvokeNextStage`), and offer the auto-verify enable as plain text only if a config write is possible.
+2. **Then `/clear`.** Recommended **unconditionally** at this boundary for a clean start — independent of how full the context window is. Every artifact is on disk, so the work survives the clear. **I can't `/clear` for you — you have to run it yourself.**
+3. **Then run the next command** in the fresh session — or re-run `/skill:forge` to let the navigator resume from disk:
+
+   ```
+   {next-command}
+   ```
+<!-- END: standard-exit-block -->
+
+---
+
+## Warm-acceptable variant
+
+Stamp this only at the `forge-5-loop → forge-6-docs` boundary (the all-done result
+report). Here clearing is **optional**: the docs stage benefits from the still-warm
+context of what the loop actually did, and impl-verify is already offered interactively
+by the loop itself, so this block defers rather than re-presenting a gate.
+
+> **Note — no literal `/clear` here.** The warm block lives in `result-reporting.md`, a
+> skill-*own* reference that the adapter build copies **verbatim** (unlike skill bodies,
+> it is not host-term translated), so a literal `/clear` would reach non-Claude adapters
+> undegraded. The warm variant says "clearing is optional" anyway, so it is phrased
+> host-neutrally without the token on purpose — do not reintroduce `/clear` here. (The
+> standard block *does* use `/clear`; that is fine because every standard stamp site is a
+> skill **body**, where `scripts/build-adapters.py` degrades it.)
+
+<!-- BEGIN: warm-exit-block -->
+**The loop is complete — this is the one boundary where clearing before the next stage is optional.**
+
+1. **Verify is already offered above.** Impl-verify is offered interactively right after this report (Step 5b for a standalone feature, Step 6.1 for an epic member) — run it there rather than as a second gate. It runs clean-room, so it needs no fresh session.
+2. **Clearing is optional here — warm is fine.** `forge-6-docs` benefits from the still-warm context of what the loop actually did, so continuing in this same session is the easy default. A cold start also works — every artifact is on disk — but there is no need to force it.
+3. **Then run the next command** — in this warm session, or a fresh one if you prefer:
+
+   ```
+   {next-command}
+   ```
+<!-- END: warm-exit-block -->

package/adapters/pi/skills/forge-3-specs/SKILL.md

@@ -0,0 +1,195 @@
+---
+# GENERATED — DO NOT EDIT. Source: skills/forge-3-specs/SKILL.md. Regenerate: python3 scripts/build-adapters.py
+name: forge-3-specs
+description: Generate numbered implementation spec documents from PRD and tech spec in the forge pipeline. Use when user runs /skill:forge-3-specs or asks to create detailed implementation specs for a forge feature after tech spec completion. Do NOT trigger for general specification writing, design docs, or implementation planning outside the forge pipeline.
+---
+
+# forge-3-specs — Implementation Spec Suite Generator
+
+Generate a comprehensive suite of numbered implementation specification documents that provide everything needed to implement a feature.
+
+## Prerequisites
+
+Read and follow `references/shared-conventions.md` for feature name validation, configuration reading, and force mode handling before proceeding.
+
+**Turn structure reminder:** Output analysis/context as text, then route ALL questions through `AskUserQuestion`. Never embed questions in text output — the user will not be prompted and the session will stall.
+
+## Step 1: Validate Prerequisites
+
+**Resolve the feature directory first** via the **Feature Directory Resolution** block in `references/shared-conventions.md`, setting `{resolvedFeatureDir}`.
+
+**Prerequisite check:** Read `{resolvedFeatureDir}/.pipeline-state.json`. If not in force mode, both `forge-1-prd` and `forge-2-tech` must be `complete`. If not, STOP and tell the user which prerequisites are missing.
+
+After the prerequisite check, invoke the **Stage-Entry Guard** block in `references/shared-conventions.md` with `{stage}` = `forge-3-specs`. Because this stage writes a suite incrementally, the guard's **interrupted** arm uses the `stages.forge-3-specs.artifacts` array (already updated after each spec file — Step 3) to resume from the first unwritten document rather than regenerating the whole suite.
+
+Read both `{resolvedFeatureDir}/PRD.md` and `{resolvedFeatureDir}/tech-spec.md` into context.
+
+After reading the PRD and tech spec, invoke the **Epic Context Injection** block in `references/shared-conventions.md`. It self-gates on the resolved feature's `epic` back-pointer: for a standalone feature it is a no-op; for an epic member it loads EPIC.md, this feature's charter, and the completed direct dependencies' specs into context before the spec suite is planned.
+
+## Step 2: Examine Existing Context
+
+1. **Read the PRD and tech spec thoroughly**: These are your source of truth
+2. **Examine the existing codebase**: Look at how other packages are structured, what patterns they follow, what types they export
+3. **Check other features' implementation specs**: Look at `{specsDir}/*/[0-9][0-9]-*.md` AND `{specsDir}/*/*/[0-9][0-9]-*.md` (depth-2, for epic-nested features) for consistency in format and depth. Subject to the **feature-shaped-dir bound**: only treat a matched directory as a feature if it directly contains a `.pipeline-state.json` (per the Feature Directory Resolution block) — ignore `EPIC.md` directories and other non-feature subtrees. Flat-only trees gain no new matches from the depth-2 glob, so standalone behavior is unchanged (REQ-COMPAT-01).
+4. **Read integration target code**: For every package listed as an integration point in the tech spec, read its actual source — types, exports, patterns. For every integration point, include the EXACT function signature and import path you read from the source code. Include the file path where you found it. If you cannot locate an expected export, say so explicitly: 'WARNING: Could not locate X export in {module} — verify this exists before implementing.'
+5. **Read spec examples**: Read `references/spec-examples.md` for the expected depth and quality of spec sections. These examples are your quality bar.
+
+## Step 3: Plan the Document Suite
+
+Read `references/spec-archetypes.md` for the menu of document types.
+
+Based on the feature's complexity, propose a document plan to the user before writing. Output the document list as text, then use `AskUserQuestion` for the question — do NOT include the question in your text output.
+
+**Example text output (no question here):**
+```
+I'll create the following spec documents for {feature}:
+
+Required:
+  00-core-definitions.md     — Type definitions, error hierarchy, shared contracts
+  01-architecture-layout.md   — Directory structure, exports map, dependency graph
+  NN-testing-strategy.md      — Test approach, coverage targets, fixture patterns
+
+Feature-specific:
+  02-{subsystem-a}.md         — {Brief description}
+  03-{subsystem-b}.md         — {Brief description}
+  04-integration-points.md    — Integration with existing project modules
+```
+
+**Then call `AskUserQuestion`** following the **Decision Support** protocol in `references/shared-conventions.md`: recommend this plan as the default (it's your evidence-backed read of the feature's complexity) and name the trade-off so the user can push back knowingly — more documents means finer separation of concerns but more to keep in sync; fewer means tighter docs but risks one document carrying multiple concerns. Lead with: "I recommend this plan. Add or remove any documents?" Note the guidance below — resist splitting a concern into a sub-50-line document.
+
+**Incremental artifact tracking:** After each spec document is written (by you or a writer subagent), immediately run `state-artifact` with the new file path — once per file, not once at the end. This enables crash recovery if the session is interrupted mid-suite (see shared-conventions.md "Stage-Entry Guard"). Add `--epic "{epic}"` when this feature is an epic member — required, per the Pipeline State Protocol.
+
+```bash
+R="$(bash -c 'for d in "${FEATURE_FORGE_ROOT:-}" "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/cache/*/feature-forge/* "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done')"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" state-artifact \
+  --feature "{feature}" --stage forge-3-specs --path "<file>" --specs-dir "{specsDir}"
+```
+
+## Step 4: Write the Spec Suite
+
+The suite has a hard internal dependency: every domain/integration doc references the
+shared types and layout from `00-core-definitions.md` and `01-architecture-layout.md`.
+So author in two phases — a sequential foundation, then a parallel fan-out.
+
+### 4a. Foundation pass (sequential, you author)
+
+Write `00-core-definitions.md` and `01-architecture-layout.md` yourself, in the main
+session, **before** anything else. Every later document depends on these shared types
+and the directory/exports map, so they must exist and be stable first.
+
+### 4b. Domain fan-out (parallel `forge-spec-writer` subagents)
+
+Once the foundation is written, dispatch the remaining numbered docs in parallel — **one
+`forge-spec-writer` subagent per document, in a single message with multiple subagent
+calls** (the `superpowers:dispatching-parallel-agents` pattern). Each writer is given:
+- the PRD and tech-spec,
+- the just-written `00-core-definitions.md` and `01-architecture-layout.md` (so it builds
+  on the shared types, not its own),
+- the stack profile path `references/stacks/{stack}.md` (if `stack` is set in config),
+- the quality bar in `references/spec-examples.md`,
+- the **exact single filename it must write** and the archetype slice (from
+  `references/spec-archetypes.md`) it covers.
+- **(epic members only — additive context):** the relevant `EPIC.md` Contracts section(s)
+  for this feature, and the `tech-spec.md` of each completed direct dependency at {paths} — so
+  the doc is written against real upstream contracts, not guesses.
+
+Each writer authors **only its one assigned file** and returns a short **manifest** of
+the `REQ-XXX-NN` IDs it covered (feeds Step 5 traceability). Author `NN-testing-strategy.md`
+last (it can be its own writer, or you author it once the others' shapes are known).
+
+**Fallback (no subagents available):** author the documents yourself in batches of 3–5,
+foundation first; after each batch, optionally commit
+(`git add {specsDir}/{feature}/ && git commit -m "{commitPrefix}({feature}): specs batch {n}"`)
+and re-read only `00-core-definitions.md` plus the upstream docs the next batch needs —
+do not reload everything. This keeps quality up under context pressure.
+
+### Quality requirements (every document, whoever writes it)
+
+1. Number sequentially: `00-`, `01-`, `02-`, etc.
+2. Every implementation detail MUST trace to either a PRD requirement (REQ-XXX-NN) or a tech-spec decision
+3. Before the body, include a `## Requirement Coverage` table mapping every REQ-XXX-NN this document covers to the section that implements it
+4. Include complete type definitions, data structures, and function signatures in the project's language — not pseudocode. If a stack profile exists at `references/stacks/{stack}.md` (where `{stack}` comes from `forge.config.json`), follow its conventions for type definitions, error hierarchies, and documentation comments.
+5. Include error handling for every operation
+6. Include example usage where it aids clarity
+7. Cross-reference other spec documents by filename when one document depends on definitions from another
+
+### Document Conventions
+
+- Filename format: `{specsDir}/{feature}/##-<descriptive-name>.md`
+- Each document should be self-contained enough that an engineer could implement it without reading other spec docs (though cross-references help for context)
+- Include a "Dependencies" section listing which other spec docs must be implemented first
+- Include a "Verification" section describing how to confirm the implementation matches the spec
+
+## Step 5: Cross-Reference Validation
+
+Before writing `TRACEABILITY.md` or running the stage exit, invoke the **Stage-Completion Re-check** block in `references/shared-conventions.md` with `{stage}` = `forge-3-specs` — a resumed mid-stage continuation must not overwrite a committed `TRACEABILITY.md` or re-fire a finished exit.
+
+After writing all documents, verify:
+
+1. Every PRD requirement has coverage in at least one spec document
+2. Every tech-spec decision is reflected in the implementation specs
+3. Cross-references between spec documents are consistent (no broken references)
+4. Type definitions used across documents are consistent
+5. No orphaned implementation details that don't trace to requirements
+6. Produce a traceability matrix: a markdown table mapping every REQ-XXX-NN from the PRD to the spec document and section that implements it. Write this to `{resolvedFeatureDir}/TRACEABILITY.md`
+
+List any gaps or inconsistencies found and resolve them.
+
+## Step 6: Review with User
+
+Present a summary of all documents created as text, with key decisions highlighted. Then use `AskUserQuestion` to collect feedback — do NOT include these questions in your text output:
+
+"1. Does the level of detail match what you need? 2. Any areas that need more depth? 3. Any missing subsystems or concerns?"
+
+## Step 7: Update Pipeline State and Commit
+
+Pipeline state is written by the `state-*` verbs — see the Pipeline State Protocol in `references/shared-conventions.md`.
+
+1. Record completion by running `state-complete` (below) with `--version`, one `--artifact` per created file including `TRACEABILITY.md`, and `--based-on forge-1-prd=<current version> --based-on forge-2-tech=<current version>`. It sets `status: "complete"`, `completedAt`, the version and `basedOnVersions`, and applies the downstream staleness cascade deterministically, so no downstream status is set by hand.
+2. **Offer a note — don't force one.** As a statement (not a blocking question), let the user know they can jot anything worth preserving across sessions and you'll store it in the `notes` field. If they volunteer something, store it; otherwise proceed.
+3. If `gitCommitAfterStage` is true, follow the Git Commit Protocol in `references/shared-conventions.md`: stage files, attempt commit with message `"{commitPrefix}({feature}): complete implementation specs v{n}"` (marking `stages.forge-3-specs.status` `complete` with `commitHash: null` in that commit), then record the artifact-commit hash via the protocol's two-commit follow-up (never `--amend`) only on success. If commit fails, leave status as `in-progress`.
+4. **Close with the Stage Exit Protocol** (single-sourced in `references/stage-exit-protocol.md`; do not improvise a "Next steps" list). Specs feed every downstream stage, so the verify gate matters here:
+
+The `state-complete` call for item 1 — and the `state-note` call only when the user volunteered a note in item 2 — with the portable plugin-root prelude. Add `--epic "{epic}"` to each call when this feature is an epic member — required, per the Pipeline State Protocol in `references/shared-conventions.md`:
+
+```bash
+R="$(bash -c 'for d in "${FEATURE_FORGE_ROOT:-}" "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/cache/*/feature-forge/* "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done')"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" state-complete \
+  --feature "{feature}" --stage forge-3-specs --version {n} \
+  --based-on "forge-1-prd=<n>" --based-on "forge-2-tech=<n>" \
+  --artifact "<file>" --artifact TRACEABILITY.md --specs-dir "{specsDir}"
+# ONLY run the next call if the user volunteered a note in item 2 — otherwise stop here.
+python3 "$R/scripts/forge-session.py" state-note \
+  --feature "{feature}" --note "<what the user volunteered>" --specs-dir "{specsDir}"
+```
+
+**Close this stage with the Scripted Stage Exit** (contract: `references/stage-exit-protocol.md`; do not improvise a "Next steps" list). Run:
+
+```bash
+R="$(bash -c 'for d in "${FEATURE_FORGE_ROOT:-}" "$HOME"/.claude/skills/feature-forge "$HOME"/.claude/plugins/cache/*/feature-forge/* "$HOME"/.claude/plugins/*/feature-forge "$HOME"/.agents/skills/feature-forge ./.agents/skills/feature-forge; do [ -x "$d/scripts/forge-root.sh" ] && exec "$d/scripts/forge-root.sh"; done')"
+[ -n "$R" ] || { echo "feature-forge: cannot locate plugin root" >&2; exit 1; }
+python3 "$R/scripts/forge-session.py" stage-exit --feature "{feature}" --stage forge-3-specs --specs-dir "{specsDir}" --host pi
+```
+
+Obey the DIRECTIVES it prints, in order, per the directive contract: `runInStageVerify: true` → dispatch the in-stage clean-room verify now (honoring `autoFixEligible`); `verifyGate: "standard"` → present the Standard Verify Gate; `verifyGate: "manual-print"` → print the `verifyCommand` for the user; non-empty `invalidAutoVerifyKeys` → print a one-line warning. Then **print the NEXT-STEPS block verbatim as your absolute last output — nothing after its sentinel line.**
+
+## Gotchas
+
+- Don't create specs for things that are already fully specified in the tech spec. If the tech spec has complete type definitions, the implementation spec should reference them, not duplicate them.
+- Every spec document should include complete type definitions and function signatures in the project's language with documentation comments. The backlog generator and implementing engineer depend on these being exact, not approximate.
+- Resist the urge to create too many documents. Each document should represent a major concern. If a "document" would be under 50 lines, it probably belongs as a section in another document.
+- Watch for implicit dependencies between subsystems. If subsystem A's types are used by subsystem B, the spec should explicitly state this and ensure the types are defined in the shared types document.
+- If the feature is large, the spec suite might be 8-12 documents. If it's simple, 3-4 is fine. Match complexity to the feature, not a fixed template.
+
+---
+
+## Host execution notes (Pi)
+
+This Pi bundle preserves Claude's `AskUserQuestion` references because it ships a Pi compatibility extension registering an `AskUserQuestion` tool. On Pi:
+
+- **User input:** use `AskUserQuestion` for genuine user decisions. It supports multiple questions, option descriptions, recommended ordering, multi-select, previews, and free-form Other/custom answers.
+- **Skill dispatch:** Pi uses `/skill:<name>` commands. If you cannot invoke a skill directly, print the exact `/skill:<name> ...` command for the user to run.
+- **Subagents:** this bundle declares its custom agents (`forge-researcher`, `forge-spec-writer`, `forge-verifier`) as package agents. If a `subagent` tool is registered, dispatch one with `{ agent: "forge-verifier", task: "..." }`, or fan several out concurrently with `{ tasks: [{ agent: "forge-spec-writer", task: "..." }, ...] }`. If no `subagent` tool is available, run that step inline yourself.
+- **Background / monitoring:** run long-lived commands in the foreground and report progress as it arrives.