@esoteric-logic/praxis-harness 1.2.1 → 2.0.1

package/base/skills/status-update/SKILL.md

@@ -0,0 +1,50 @@
+---
+name: status-update
+disable-model-invocation: true
+description: >
+  Atomic update to vault status.md. Ensures consistent format, enforces
+  the 100-line limit, and archives resolved items. Called at milestone
+  boundaries, session end, and phase transitions.
+---
+
+# status-update Skill
+
+## Required Fields (top of status.md, always present)
+
+```yaml
+current_plan: {path or "none"}
+last_updated: {YYYY-MM-DD}
+last_session: {ISO timestamp}
+loop_position: DISCUSS | PLAN | EXECUTE | VERIFY | IDLE
+```
+
+## Steps
+
+1. Read vault_path from `~/.claude/praxis.config.json`
+2. Read current `{vault_path}/status.md`
+3. Update the required fields at the top
+4. Add or update the What / So What / Now What section:
+   - **What**: Facts only — what was done, what exists now
+   - **So What**: Why it matters — blockers, risks, progress
+   - **Now What**: Next actions, ordered by priority
+5. Check line count — if >100 lines, archive resolved sections:
+   - Move completed What/So What/Now What blocks to `{vault_path}/notes/{date}_status-archive.md`
+   - Keep only active/unresolved items in status.md
+6. Write the updated file
+
+## When to Call
+
+| Trigger | What to Update |
+|---------|---------------|
+| Milestone complete | Add accomplishment to What, advance Now What |
+| Phase transition | Update `loop_position` |
+| Session end | Update `last_session`, write current state |
+| Blocker hit | Add blocker to So What, propose resolution in Now What |
+| Plan created/changed | Update `current_plan` |
+
+## Constraints
+
+- status.md must stay under 100 lines — archive aggressively
+- Never delete content — always archive to notes/
+- A status.md older than 14 days is stale — vault-gc flags these
+- Use `[[wikilinks]]` for all internal vault references

package/base/skills/vault-gc/SKILL.md

@@ -4,7 +4,6 @@ disable-model-invocation: true
 description: Audit vault health and detect entropy. Invoke manually with /vault-gc
   only. Two modes — full audit (manual) and lightweight staleness check (called
   inline by session-retro). Never auto-deletes. Side-effect skill — never auto-triggers.
-allowed-tools: Bash, Read, Write
 ---
 
 # vault-gc Skill

package/base/{commands/gsd-verify.md → skills/verify/SKILL.md}

@@ -1,8 +1,10 @@
 ---
+name: verify
+disable-model-invocation: true
 description: Validation phase — runs test/lint/typecheck/build and reports PASS or FAIL. Use after each milestone completion.
 ---
 
-You are running the GSD verification phase for the current milestone.
+You are running the verification phase for the current milestone.
 
 **Step 1 — Run validation sequence**
 Execute in order, showing actual output (never assertions):
@@ -21,13 +23,14 @@ If no commands are defined: warn and ask user for the correct commands.
 
 **Step 3 — On PASS**
 1. Update the active plan file: mark milestone status as complete
-2. Prompt: "Milestone verified. Ready to commit — proceed?"
-3. After commit: check if more milestones remain
-   - Yes → "Run `/gsd:execute` for the next milestone."
-   - No → "All milestones complete. Running self-review."
+2. Commit immediately — verification passed, no permission needed.
+   Use conventional commit format. See git-workflow.md.
+3. Check if more milestones remain:
+   - Yes → "Milestone committed. Run `/execute` for the next milestone."
+   - No → "All milestones committed. Running self-review."
 4. After ALL milestones: trigger Self-Review Protocol
    - Launch a subagent to review the full diff as a critical code reviewer
-   - Subagent receives ONLY: the diff, the SPEC, relevant rules files
+   - Subagent receives ONLY: the diff, the SPEC (from plan file `## SPEC` section), relevant rules files
    - Address all Critical and Major findings before reporting done
 
 **Step 3b — UNIFY (mandatory after all milestones verified)**

package/base/skills/verify-app/SKILL.md

@@ -5,7 +5,6 @@ description: End-to-end application verification. Launches a subagent to run the
   test suite, check build, verify runtime behavior, and confirm acceptance criteria.
   Use after implementation to catch integration issues that unit tests miss.
   Side-effect skill — never auto-triggers.
-allowed-tools: Bash, Read
 ---
 
 # verify-app Skill
@@ -14,16 +13,17 @@ allowed-tools: Bash, Read
 Read vault_path from `~/.claude/praxis.config.json`.
 Detect current project by matching CWD to `local_path` in vault `_index.md`.
 
-## DONE-WHEN
+## Acceptance
 - [ ] Full test suite passes (not just changed tests)
 - [ ] Build succeeds with zero warnings
 - [ ] Lint passes with zero warnings
 - [ ] Typecheck passes (if applicable)
-- [ ] Acceptance criteria verified (from active plan done-when)
+- [ ] Acceptance criteria verified (from active plan)
 - [ ] No regressions detected in related functionality
 - [ ] Verification report written
 
-## NON-GOALS
+## Boundaries
+Out of scope:
 - Does not fix issues — reports them for the user to address
 - Does not modify code
 - Does not deploy or publish
@@ -148,8 +148,7 @@ Format each concern as:
 | Caller | When |
 |--------|------|
 | Manual `/verify-app` | After any implementation |
-| `/gsd:verify` | Can replace or complement Step 1 |
-| Ralph iteration | After story completion |
+| `/verify` | Can replace or complement Step 1 |
 
 ## Removal Condition
 Remove when CI/CD pipeline covers all verification steps and results are

package/kits/infrastructure/KIT.md

@@ -43,23 +43,10 @@ environments.
 
 ## Workflow Integration
 
-This kit operates WITHIN the universal base workflow:
-- **GSD** structures the work (discuss → plan → execute → verify)
-- **Superpowers** enforces TDD and code review during execution
+This kit operates WITHIN the Praxis workflow:
+- **Praxis** structures the work (discuss → plan → execute → verify → simplify → ship)
 - **This kit** adds infrastructure-specific rules and commands
 
-## Ralph Integration
-
-To persist this kit across Ralph iterations, add to project `CLAUDE.md`:
-
-```markdown
-## Active kit
-On session start, activate: /kit:infrastructure
-```
-
-Each Ralph iteration reads project CLAUDE.md and activates the kit automatically.
-The `/kit` command is idempotent — double-activation is a no-op.
-
 ## Prerequisites
 
 Run `install.sh` in this directory to check for required CLI tools.

package/kits/web-designer/KIT.md

@@ -41,27 +41,14 @@ accessibility audit and final lint.
 
 ## Workflow Integration
 
-This kit operates WITHIN the universal base workflow:
-- **GSD** structures the work (discuss → plan → execute → verify)
-- **Superpowers** enforces TDD and code review during execution
+This kit operates WITHIN the Praxis workflow:
+- **Praxis** structures the work (discuss → plan → execute → verify → simplify → ship)
 - **This kit** adds domain-specific design rules and skill chain
 
-The skills chain is a SEQUENCE, not a replacement for GSD phases.
-Use GSD to plan which phase to work on, then execute within that phase
+The skills chain is a SEQUENCE, not a replacement for Praxis phases.
+Use `/plan` to plan which phase to work on, then execute within that phase
 using the kit's skills.
 
-## Ralph Integration
-
-To persist this kit across Ralph iterations, add to project `CLAUDE.md`:
-
-```markdown
-## Active kit
-On session start, activate: /kit:web-designer
-```
-
-Each Ralph iteration reads project CLAUDE.md and activates the kit automatically.
-The `/kit` command is idempotent — double-activation is a no-op.
-
 ## Prerequisites
 
 Run `install.sh` in this directory to install all required npm skills and MCP servers.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@esoteric-logic/praxis-harness",
-  "version": "1.2.1",
+  "version": "2.0.1",
   "description": "Layered Claude Code harness — workflow discipline, AI-Kits, persistent vault integration",
   "bin": {
     "praxis-harness": "./bin/praxis.js"
@@ -24,8 +24,7 @@
     "ai-harness",
     "vault",
     "obsidian",
-    "workflow",
-    "gsd"
+    "workflow"
   ],
   "author": "arcanesme",
   "license": "MIT",

package/scripts/lint-harness.sh

@@ -46,7 +46,7 @@ fi
 
 # ─── 2. Skill frontmatter ───
 echo ""
-echo "Skills (name:, disable-model-invocation:, description:):"
+echo "Skills (name:, description:):"
 if [[ -d "$REPO_PATH/base/skills" ]]; then
   for skill_dir in "$REPO_PATH"/base/skills/*/; do
     [[ -d "$skill_dir" ]] || continue
@@ -60,10 +60,14 @@ if [[ -d "$REPO_PATH/base/skills" ]]; then
     header=$(head -10 "$skill_file")
     missing=""
     echo "$header" | grep -q "^name:" || missing="$missing name:"
-    echo "$header" | grep -q "^disable-model-invocation:" || missing="$missing disable-model-invocation:"
     echo "$header" | grep -q "^description:" || missing="$missing description:"
     if [[ -z "$missing" ]]; then
-      ok "skills/$skill_name"
+      # Note auto-invocable skills (no disable-model-invocation)
+      if echo "$header" | grep -q "^disable-model-invocation:"; then
+        ok "skills/$skill_name"
+      else
+        ok "skills/$skill_name (auto-invocable)"
+      fi
     else
       error "skills/$skill_name SKILL.md missing:$missing"
     fi

package/templates/claude-progress.json

@@ -9,16 +9,6 @@
   "stack": ["item-1", "item-2"],
   "milestones": [],
   "features": [],
-  "ralph_state": {
-    "mode": "idle",
-    "prd_path": null,
-    "current_story": null,
-    "completed_stories": [],
-    "blocked_stories": [],
-    "learnings": [],
-    "last_iteration": null,
-    "session_count": 0
-  },
   "last_session": null,
   "sessions": []
 }

package/base/commands/gsd-discuss.md

@@ -1,53 +0,0 @@
----
-description: Entry point for all feature work. Frames the problem, gathers SPEC questions, and recommends next phase. Use before /gsd:plan-phase.
----
-
-You are starting the GSD discuss phase — framing the problem before planning.
-
-**Step 1 — Load minimal context**
-- Read vault_path from `~/.claude/praxis.config.json`
-- Detect project from CWD matching `local_path` in vault `_index.md`
-- If no project detected: ask which project before continuing
-
-**Step 2 — Read ONLY these files (nothing else)**
-1. `{vault_path}/status.md` — current state and blockers
-2. Active plan (if `current_plan:` is set in status.md) — skim objectives only
-3. `~/.claude/rules/profile.md` — user context
-
-Do NOT load rules, kit context, or session history at this phase.
-
-**Step 3 — Search for related work**
-Run: `obsidian search query="{topic}" limit=5`
-Check if specs, prior plans, or research already exist for this topic.
-
-**Step 4 — SPEC questions**
-Ask the user to answer all four:
-- **WHAT**: Concrete deliverable (not vague goals)
-- **DONE-WHEN**: Specific checks that prove completion
-- **CONSTRAINTS**: Performance, compatibility, style requirements
-- **NON-GOALS**: What this task explicitly does NOT include
-
-If answers are ambiguous: ask 2–3 follow-up questions. Do not proceed with vague scope.
-
-**Step 5 — Problem framing**
-Output a 1-paragraph problem framing that includes:
-- What exists today (from status.md / vault search)
-- What gap or need the user described
-- Recommendation: proceed to `/gsd:plan-phase` or write a `/spec` first
-
-**Step 5b — Scope guard**
-- Problem framing (Step 5 output) must not exceed 200 words. If the problem
-  requires more to frame: it is too large. Split into sub-problems and run
-  `/gsd:discuss` on each separately.
-- After framing: explicitly list what is NOT being decided in this discuss phase.
-- Never output implementation code, pseudocode, or file-level changes during discuss.
-  This phase produces a problem statement, not a solution.
-- If the framing implies >5 milestones or >3 file groups: flag as scope explosion
-  risk and recommend splitting before `/gsd:plan-phase`.
-
-**Step 6 — Handoff**
-End with: "Run `/gsd:plan-phase` to continue, or `/spec` if this needs a design spec first."
-
-**Rules:**
-- Problem framing is a paragraph, not a design doc.
-- If scope exceeds 5 milestones: recommend splitting into multiple GSD passes.

package/base/commands/ralph.md

@@ -1,110 +0,0 @@
----
-description: Ralph autonomous execution command. Runs multi-story iterations from a PRD with fresh context per story. Use for >5 independent stories or overnight execution.
----
-
-You are running Ralph — autonomous multi-story execution.
-
-**Step 1 — Read state**
-- Read vault_path from `~/.claude/praxis.config.json`
-- Read `{vault_path}/claude-progress.json` → check `ralph_state`
-- If `ralph_state.mode` is `"active"` and `current_story` is set: resume that story
-- If `ralph_state.mode` is `"idle"`: begin new iteration (Step 2)
-
-**Step 2 — PRD validation**
-- Read the PRD file at `ralph_state.prd_path`
-- Validate each story against size constraints:
-  - Must be completable in ~10k output tokens
-  - Must touch ≤3 file groups
-  - Must require ≤1 architectural decision
-- Reject stories that exceed constraints. Report which stories need splitting.
-- Stories requiring cross-story reasoning belong in GSD, not Ralph.
-
-**Step 2b — PRD format (canonical)**
-Ralph PRDs must follow this structure:
-  ```markdown
-  ---
-  title: {PRD title}
-  date: YYYY-MM-DD
-  status: active
-  stories_total: {n}
-  ---
-  # PRD: {title}
-
-  ## Context
-  Why this work exists. 1-3 sentences.
-
-  ## Stories
-
-  ### Story: {story-id}
-  **As a**: {role}
-  **I want**: {capability}
-  **So that**: {outcome}
-  **Done when**:
-  - [ ] {verifiable check}
-  **File group**: {list of files, max 3 groups}
-  **Dependencies**: {story-ids that must complete first, or "none"}
-  **Estimate**: S / M / L
-  ```
-- Size validation: before starting any Ralph run, scan every story.
-  Any story marked L or missing a File group: STOP. Fix the PRD first.
-- S = <3 files. M = 3-5 files. L = 5+ files (must split before Ralph).
-
-**Step 3 — State bridge**
-- `ralph_state` in `claude-progress.json` is the ONLY state between iterations
-- Never reference conversation history as source of truth
-- Read `ralph_state` at iteration start, write at iteration end
-- Fields:
-  - `mode`: "idle" | "active"
-  - `prd_path`: path to PRD file
-  - `current_story`: story identifier currently being executed
-  - `completed_stories`: array of finished story identifiers
-  - `blocked_stories`: array of stories that could not complete
-  - `learnings`: array of [LEARN:tag] entries discovered during iterations
-  - `last_iteration`: ISO timestamp of last completed iteration
-  - `session_count`: number of iterations completed
-
-**Step 4 — Iteration bootstrap**
-For each story, in a fresh context:
-1. Read project CLAUDE.md (always first)
-2. Read `claude-progress.json` → `ralph_state` (authoritative)
-3. Read PRD → current story ONLY (not full PRD)
-4. Activate kit if specified in project CLAUDE.md (`## Active kit`)
-5. Execute the story using GSD execute + verify phases
-
-**Step 4b — Blocked story protocol**
-When a story cannot complete (test fails after 3 attempts, dependency missing, etc.):
-1. Do NOT retry the story. Ralph stories get one attempt.
-2. Record in `ralph_state.blocked_stories`:
-   ```json
-   { "story": "{story-id}", "reason": "{specific error}", "blocked_at": "{ISO timestamp}" }
-   ```
-3. Write the blocker to the active plan file under the story entry.
-4. Move to the next unblocked story. Never halt the entire Ralph run.
-5. At run end: report all blocked stories as a group for human resolution.
-
-**Step 5 — Iteration end**
-After each story completes:
-1. Run session-retro in Ralph-auto mode (summary + learnings, skip user-facing phases)
-2. Update `ralph_state`:
-   - Push `current_story` to `completed_stories`
-   - Set `current_story` to next story (or null if done)
-   - Update `last_iteration` timestamp
-   - Increment `session_count`
-3. Git commit the story's changes
-4. Advance to next story or report completion
-
-**Step 6 — Decision table**
-
-| Condition | Use Ralph | Use GSD |
-|-----------|-----------|---------|
-| >5 independent stories | Yes | - |
-| Overnight/unattended execution | Yes | - |
-| Mechanical transformations (migrations, renames) | Yes | - |
-| Cross-story reasoning required | - | Yes |
-| Architectural decisions span stories | - | Yes |
-| Human checkpoints needed | - | Yes |
-
-**Rules:**
-- Kit activation is idempotent via `/kit:<name>` — safe to activate every iteration.
-- Ralph never asks for user input mid-story. If blocked: add to `blocked_stories`, skip, continue.
-- Default to GSD. Use Ralph only when stories are clearly independent and well-scoped.

package/base/commands/simplify.md

@@ -1,15 +0,0 @@
----
-description: Post-implementation code cleanup. Launches a subagent to find and
-  simplify over-abstraction, dead paths, verbosity, and missed idioms in the
-  recent diff. Run after implementation, before /verify-app or /ship.
----
-
-Invoke the code-simplifier skill on the current project's recent changes.
-
-Accept an optional scope argument:
-- No argument → `git diff HEAD~1` (default)
-- `staged` → staged changes only
-- `HEAD~N` or SHA → specific range
-
-The code-simplifier skill handles all phases: scope detection, subagent launch,
-finding presentation, user-approved edits, and optional [LEARN:simplify] capture.

package/base/rules/code-quality.md

@@ -1,65 +0,0 @@
-# Code Quality — Rules
-# Scope: All projects, all sessions
-# Complements `coding.md` with structural quality thresholds.
-
-## Invariants — BLOCK on violation
-
-### No deep nesting
-- Conditionals nested >3 levels deep must be refactored (extract function, early return, guard clause).
-- Applies to if/else, try/catch, loops, and match/switch statements.
-
-### Cyclomatic complexity
-- Functions with cyclomatic complexity >15: BLOCK. Refactor before commit.
-- Measure by counting decision points (if, else if, for, while, case, &&, ||, catch).
-
-### Public function documentation
-- All public functions and methods must have doc comments.
-- Doc comments describe intent and constraints, not implementation.
-- Internal/private helpers: doc comments optional, but name must be self-describing.
-
-### No commented-out code
-- No commented-out code blocks in committed files.
-- Dead code belongs in git history, not in source files.
-- `// TODO:` and `// FIXME:` are annotations, not commented-out code — these are allowed.
-
----
-
-## Conventions — WARN on violation
-
-### Complexity awareness
-- Cyclomatic complexity >10: WARN. Consider splitting the function.
-- Functions longer than 50 lines: review for single-responsibility violation.
-
-### No magic numbers
-- No magic numbers without a named constant and a comment explaining the value.
-- Exception: 0, 1, -1, and values obvious from immediate context (e.g., `array.length - 1`).
-
-### Single responsibility
-- Each function does one thing. If the description requires "and", split it.
-- Each file has one primary concern. Utility grab-bags indicate missing abstractions.
-
-### No hardcoded environment values
-- No hardcoded URLs, ports, hostnames, or credentials specific to an environment.
-- Use environment variables, config files, or parameter injection.
-- Cross-ref: `coding.md` — No hardcoded values invariant.
-
----
-
-## Verification Commands
-
-```bash
-# Find deeply nested blocks (rough heuristic — look for 4+ indent levels)
-rg '^\s{16,}(if|for|while|try)' --type-add 'code:*.{ts,js,py,go,rs}' -t code
-
-# Find commented-out code blocks (multi-line)
-rg '^\s*//\s*(const|let|var|function|class|import|return|if|for)' --type-add 'code:*.{ts,js}' -t code
-rg '^\s*#\s*(def |class |import |return |if |for )' -t py
-
-# Find magic numbers in staged files
-git diff --staged | grep -E '[^0-9][2-9][0-9]{2,}[^0-9]' | grep -v 'const\|#\|//'
-```
-
----
-
-## Removal Condition
-Permanent. Structural quality thresholds apply regardless of project or language.

package/base/rules/security.md

@@ -1,40 +0,0 @@
-# Security — Rules
-# Scope: All projects, all sessions
-
-## Invariants (BLOCK on violation)
-
-### Secrets
-- NEVER hardcode secrets — no API keys, tokens, passwords, connection strings in code.
-  Use environment variables or a secrets manager.
-- If a secret is found in code: flag immediately, do not proceed until remediated.
-- Pre-commit scan (always): `rg "(sk-|ghp_|pplx-|AKIA|Bearer [A-Za-z0-9+/]{20,})" $(git diff --staged --name-only)`
-- Secrets in logs: never log request bodies, headers, or responses that may contain credentials. Redact before logging.
-
-### Input Validation
-- Validate all inputs at boundaries — APIs, user input, file uploads, environment variables.
-- Never trust external data without validation.
-- Validate response shape, not just status code — 200 with error body is a silent failure.
-
-### Permissions
-- Least privilege — request only permissions and scopes needed.
-- No wildcard IAM policies. No `chmod 777`.
-- GitHub Actions: pin action versions to commit SHA, not tags.
-
-## Conventions (WARN on violation)
-
-### Dependencies
-- Audit new dependencies before adding: `npm audit`, `pip audit`, or equivalent.
-- Check for known CVEs before adding any package.
-- Pin to exact versions. No floating ranges in production.
-
-## Verification Commands
-```bash
-# Secret scan staged files
-rg "(sk-|ghp_|pplx-|AKIA|Bearer [A-Za-z0-9+/]{20,})" $(git diff --staged --name-only)
-
-# Secret scan entire repo (audit mode)
-rg "(sk-|ghp_|pplx-|AKIA|Bearer [A-Za-z0-9+/]{20,})" --glob "!*.lock" .
-
-# Check for .env files accidentally staged
-git diff --staged --name-only | grep -E "\.env$|\.env\."
-```

package/base/skills/prd-writer/SKILL.md

@@ -1,108 +0,0 @@
----
-name: prd-writer
-disable-model-invocation: true
-description: Structured PRD authoring for Ralph. Gathers context, builds stories,
-  validates against Ralph constraints, writes PRD to vault. Invoke manually with
-  /prd-writer only. Side-effect skill — never auto-triggers.
-allowed-tools: Bash, Read, Write, Edit
----
-
-# prd-writer Skill
-
-## Vault Path Resolution
-Read vault_path from `~/.claude/praxis.config.json`. If missing: tell user to run `install.sh`.
-
-## DONE-WHEN
-- [ ] PRD written to vault with all stories populated
-- [ ] Every story has: role, capability, outcome, done-when, file group, dependencies, estimate
-- [ ] No story marked L (must be split before writing)
-- [ ] Total stories ≤15
-- [ ] ralph_state.prd_path set in claude-progress.json
-- [ ] status.md updated with PRD reference
-- [ ] Vault indexed (automatic)
-
-## NON-GOALS
-- Does not execute stories — that is Ralph's job
-- Does not create plans — use `/plan` for that
-- Does not write specs or ADRs — use `/spec` for that
-
----
-
-## Phase 1 — Gather Context
-
-1. Read `{vault_path}/status.md` — current state and active work
-2. Read `{vault_path}/_index.md` — project goals and metadata
-3. Ask the user:
-   - What is the PRD objective? (one sentence)
-   - What area of the codebase does this cover?
-   - Any known constraints or dependencies?
-
-## Phase 2 — Build Stories
-
-For each story, collect:
-- **Title**: short identifier (e.g., `add-auth-middleware`)
-- **As a**: role
-- **I want**: capability
-- **So that**: outcome
-- **Done when**: list of verifiable checks
-- **File group**: list of files (max 3 groups per story)
-- **Dependencies**: story-ids that must complete first, or "none"
-- **Estimate**: S / M / L
-
-Present stories in a table for user review before proceeding.
-
-## Phase 3 — Validate Against Ralph Constraints
-
-For each story, check:
-- Completable in ~10k output tokens
-- Touches ≤3 file groups
-- Requires ≤1 architectural decision
-- No cross-story reasoning required
-- Estimate is S or M (never L)
-
-Violations:
-- L estimate → STOP. Story must be split before PRD is written.
-- >3 file groups → STOP. Reduce scope or split.
-- Cross-story dependency chains → WARN. Ralph executes stories independently.
-- >15 stories total → suggest splitting into multiple PRDs.
-
-## Phase 4 — Write PRD
-
-Use `references/prd-template.md` as the canonical format.
-
-1. Fill all fields. No placeholders may remain.
-2. Scan the output for unreplaced `{placeholder}` patterns. Zero must survive.
-3. Write to: `{vault_path}/plans/{YYYY-MM-DD}_{kebab-title}-prd.md`
-
-## Phase 5 — Wire State
-
-1. Update `{vault_path}/status.md`:
-   - Set `current_plan:` to the PRD path
-   - Update `## Now What` with "PRD ready for Ralph execution"
-2. Update `{vault_path}/claude-progress.json`:
-   - Set `ralph_state.prd_path` to the PRD file path
-   - Set `ralph_state.mode` to "idle"
-   - Set `ralph_state.completed_stories` to `[]`
-   - Set `ralph_state.blocked_stories` to `[]`
-3. Report:
-   ```
-   ✓ PRD written:      {path}
-   ✓ Stories:           {n} (S: {n}, M: {n})
-   ✓ ralph_state:       prd_path set, mode idle
-   ✓ status.md:         updated
-
-   Next: run /ralph to begin autonomous execution.
-   ```
-
-## Error Handling
-
-| Condition | Action |
-|-----------|--------|
-| All stories marked L | Warn: "No stories are Ralph-suitable. Split or use GSD." |
-| >15 stories | Suggest splitting into 2+ PRDs |
-| Missing file groups | STOP. Every story needs a file group for Ralph |
-| User declines story edits | Write PRD as-is with warnings noted |
-| vault_path missing | Tell user to run install.sh |
-
-## Removal Condition
-Remove when PRD authoring is fully automated from issue trackers or when Ralph accepts unstructured input.

package/base/skills/prd-writer/references/prd-template.md

@@ -1,22 +0,0 @@
----
-title: {PRD title}
-date: YYYY-MM-DD
-status: active
-stories_total: {n}
----
-# PRD: {title}
-
-## Context
-Why this work exists. 1-3 sentences.
-
-## Stories
-
-### Story: {story-id}
-**As a**: {role}
-**I want**: {capability}
-**So that**: {outcome}
-**Done when**:
-- [ ] {verifiable check}
-**File group**: {list of files, max 3 groups}
-**Dependencies**: {story-ids that must complete first, or "none"}
-**Estimate**: S / M / L