@c-d-cc/reap 0.10.3 → 0.12.0

package/dist/templates/commands/reap.status.md

@@ -2,79 +2,4 @@
 description: "REAP Status — Show current generation state and project health"
 ---
 
-# Status
-
-Display a comprehensive overview of the current REAP project state.
-
-## IMPORTANT: File Access Rules
-- ONLY read files explicitly listed in the steps below. Do NOT guess or infer file paths.
-- If a file read fails or the file does not exist, skip it silently and continue.
-- Do NOT attempt to read files like `reaprc.json`, `.reaprc`, or any file not specified in this command.
-- The REAP project structure uses ONLY: `.reap/config.yml`, `.reap/life/current.yml`, `.reap/life/backlog/`, `.reap/life/0X-*.md`, `.reap/genome/`, `.reap/lineage/`
-
-## Steps
-
-### 1. Project Info (MUST execute all of these)
-- Read `.reap/config.yml` for project name, entryMode, strict, autoUpdate, language
-- Count completed generations in `.reap/lineage/`
-- **REQUIRED**: Run the shell command `reap --version` to get the installed version. You MUST actually execute this command, do not skip it.
-- Show "REAP: v{installed}" — do NOT run `npm view` here (slow network call). Users can run `/reap.update` to check for updates.
-
-### 2. Current Generation
-- Read `.reap/life/current.yml`
-- If no active generation: report "No active Generation" and skip to Step 5
-- Display: Generation ID, goal, current stage, genomeVersion, startedAt
-
-### 3. Stage Progress
-- Read the current stage's artifact file (`.reap/life/0X-*.md`)
-- Summarize what has been done so far in this stage (completed tasks, decisions made, etc.)
-- If the artifact doesn't exist yet, report "Stage not started"
-
-### 4. Timeline & Notable Events
-- Display the full timeline from `current.yml`:
-  - Stage transitions with timestamps
-  - Regressions (from, reason, refs)
-- Flag notable events:
-  - Any regressions in this generation
-  - Deferred tasks (from `03-implementation.md` if exists)
-  - Genome-change backlog items pending
-
-### 5. Backlog Summary
-- Read all files in `.reap/life/backlog/`
-- Count by type: `genome-change`, `environment-change`, `task`
-- List titles briefly
-
-### 6. Genome Health
-- Quick check of `.reap/genome/` files:
-  - Any files that are still placeholder-only?
-  - Any files exceeding their line limit? (default: ~100 lines. For source-map.md, read the file's own header to find its adaptive line limit.)
-  - Is `domain/` empty (no rule files)?
-
-## Output Format
-Present as a structured summary the human can quickly scan:
-
-```
-📊 REAP Status
-━━━━━━━━━━━━━━━━━━━━━━━━━━━━
-REAP: v[installed] (run `/reap.update` to check for updates)
-Project: [name] ([entryMode])
-Strict: [on/off]  Auto-Update: [on/off]  Language: [lang]
-Genome Version: v[N]
-Completed Generations: [count]
-
-🔄 Active Generation: [id]
-Goal: [goal]
-Stage: [stage]
-Started: [date]
-
-📋 Stage Progress:
-[summary of current artifact]
-
-📅 Timeline:
-[stage transitions]
-
-📦 Backlog: [N] items
-  genome-change: [n]  environment-change: [n]  task: [n]
-
-🧬 Genome Health: [status]
-```
+Run `reap status` and present the output to the human.

package/dist/templates/commands/reap.sync.environment.md

@@ -2,83 +2,4 @@
 description: "REAP Sync Environment — Discover and document external environment dependencies"
 ---
 
-# Sync Environment
-
-Discover external systems, APIs, infrastructure, and constraints that affect this project. Populate the `.reap/environment/` 3-layer structure.
-
-## Gate (Preconditions)
-- Read `.reap/life/current.yml`
-- If active Generation exists: switch to **Backlog Mode** (record as `type: environment-change`)
-- If no active Generation: proceed with **Sync Mode** (modify environment directly after human confirmation)
-
-## Environment 3-Layer Structure
-
-```
-.reap/environment/
-├── summary.md          # Session context (~100 lines max)
-├── docs/               # Main reference docs (agent reads these)
-└── resources/          # Raw materials (user-managed)
-    ├── *.pdf, *.md     # Original documents
-    └── links.md        # External URLs + summaries
-```
-
-- **summary.md**: Auto-generated overview of all docs/. Loaded into session context.
-- **docs/**: One file per environment topic. ~100 lines each. AI + human maintained.
-- **resources/**: User-provided originals. No line limit. AI reads when deeper detail needed.
-
-## Steps
-
-### 1. Source Code Scan
-Detect hints of external dependencies from:
-- `package.json` / `requirements.txt` / `go.mod` — SDK/client libraries (e.g., `discord.js`, `@aws-sdk/*`, `stripe`)
-- Config files — `.env`, `.env.example`, `wrangler.toml`, `docker-compose.yml`, `vercel.json`
-- API client code — HTTP clients, webhook handlers, OAuth configs
-- Infrastructure — Dockerfile, CI/CD configs, deployment scripts
-
-Present findings:
-```
-🔍 Detected external dependencies:
-  - discord.js → Discord Bot API
-  - @supabase/supabase-js → Supabase (DB + Auth)
-  - wrangler.toml → Cloudflare Workers
-```
-
-### 2. User Interview
-Ask the user to confirm and expand. Goal: **capture ALL external systems** that affect this project.
-
-Questions (one at a time, skip if already covered):
-1. "감지된 외부 서비스들이 맞나요? 추가/수정할 것이 있나요?"
-2. "그 외에 연동되는 외부 서비스, API, 시스템이 있나요?"
-3. "배포/인프라 환경을 알려주세요 (호스팅, CI/CD, 도메인 등)"
-4. "따라야 하는 조직 규칙이나 외부 제약이 있나요? (보안 정책, 규제 등)"
-5. "참고해야 할 외부 문서나 링크가 있나요? (API docs, 스펙 등)"
-
-For each confirmed item:
-- Ask: "관련 문서/링크가 있으면 알려주세요 (없으면 skip)"
-- If provided: save to `resources/` (file or `links.md` entry)
-
-### 3. Generate docs/
-For each confirmed environment topic, create a file in `docs/`:
-- File name: `{topic-slug}.md` (e.g., `discord-api.md`, `infrastructure.md`)
-- Content: structured markdown with key info the agent needs during implementation
-- Sections: Overview, Key Constraints, API/Config Details, References (→ resources/)
-- ~100 lines max per file
-
-### 4. Generate summary.md
-Aggregate all docs/ into a concise summary:
-- One section per environment topic
-- Key constraints and gotchas highlighted
-- Links to docs/ files for detail
-- **~100 lines max** (this gets loaded into every session)
-
-### 5. Verify
-- List all created/updated files
-- Show summary.md content to user for confirmation
-- Ask: "빠진 환경 정보가 있나요?"
-
-## Backlog Mode (active Generation)
-- Record each discovered environment item as `type: environment-change` in `.reap/life/backlog/`
-- "Environment 변경사항이 backlog에 기록되었습니다. Completion에서 적용됩니다."
-
-## Completion
-- "Environment synced. {N} docs created, summary.md updated."
+Run `reap run sync-environment` and follow the stdout instructions exactly.

package/dist/templates/commands/reap.sync.genome.md

@@ -2,108 +2,4 @@
 description: "REAP Sync Genome — Synchronize Genome with current source code"
 ---
 
-# Sync Genome
-
-Analyze the current source code and update the Genome to reflect reality.
-
-<HARD-GATE>
-If an active Generation exists (`.reap/life/current.yml` has content), do NOT modify Genome directly.
-Instead, record discovered differences as `type: genome-change` items in `.reap/life/backlog/` and inform the human.
-Only proceed with direct Genome modification when NO active Generation exists.
-</HARD-GATE>
-
-## Gate (Preconditions)
-- Read `.reap/life/current.yml`
-- If active Generation exists: switch to **Backlog Mode** (record differences, do not modify Genome)
-- If no active Generation: proceed with **Sync Mode** (modify Genome directly after human confirmation)
-
-## Steps
-
-### 1. Read Current Genome
-- Read all files in `.reap/genome/` (principles.md, conventions.md, constraints.md, domain/)
-- Note current genomeVersion from the most recent generation in `.reap/lineage/`
-
-### 2. Analyze Source Code
-Scan the project to understand its current state:
-
-**Tech Stack & Dependencies**:
-- package.json, tsconfig.json, Dockerfile, docker-compose.yml, etc.
-- New dependencies added, removed, or version-changed since Genome was last updated
-
-**Architecture & Structure**:
-- Directory structure and patterns (layers, modules, services)
-- Entry points, routing, API structure
-- Database, ORM, migration setup
-
-**Conventions**:
-- Linter/formatter configs (.eslintrc, .prettierrc, biome.json, etc.)
-- Test setup and patterns (test framework, file naming, coverage config)
-- Git hooks, CI/CD config
-- Code patterns observed in the source (naming, error handling, etc.)
-
-**Constraints**:
-- Build commands, test commands, validation commands
-- Environment requirements, runtime constraints
-- External service dependencies
-
-**Domain Knowledge** (→ `genome/domain/`):
-- Read `~/.reap/templates/domain-guide.md` for domain file writing principles
-- Scan source code for business rules NOT derivable from infrastructure analysis:
-  - State machines and status transitions (e.g., post lifecycle, order states)
-  - Policy rules with thresholds, limits, or conditions (e.g., rate limits, scoring criteria)
-  - Classification/branching logic driven by business categories (e.g., template selection by type)
-  - Hardcoded domain constants (keyword lists, prompt templates, magic numbers with business meaning)
-  - Workflow orchestration sequences (e.g., approval flows, pipeline stages)
-- For each discovered domain rule cluster, evaluate:
-  - "Would an agent implementing this feature ask 'where is this rule?'" → YES = create domain file
-  - "Does a single item in an upper-level genome file require 3+ lines of explanation?" → YES = extract to domain file
-- Even if `genome/domain/` is currently empty, treat it as "not yet created" rather than "not needed"
-
-### 3. Diff Analysis
-Compare source analysis with current Genome and identify:
-- **Additions**: Things in code but not in Genome
-- **Changes**: Things in Genome that no longer match code
-- **Removals**: Things in Genome that no longer exist in code
-- **Gaps**: Areas where Genome has placeholders but code has established patterns
-- **Domain gaps**: Business rules in code that have no corresponding `domain/` file
-
-### 4. Report to Human
-Present a structured diff report:
-
-```
-🔄 Genome Sync Report
-━━━━━━━━━━━━━━━━━━━━━
-
-📝 principles.md
-  + [New] API-first design pattern observed
-  ~ [Changed] Layer structure: added shared/ directory
-
-📝 conventions.md
-  + [New] Biome used for linting (replacing ESLint)
-  ~ [Changed] Test pattern: using vitest instead of jest
-
-📝 constraints.md
-  + [New] Validation command: bun test
-  ~ [Changed] Runtime: Node.js compatible (was Bun-only)
-
-📁 domain/
-  + [Suggest] Create lifecycle-rules.md for REAP lifecycle logic
-```
-
-### 5. Apply Changes
-
-**Sync Mode** (no active Generation):
-- For each difference, ask the human: "Apply this change? (yes/no/modify)"
-- Apply confirmed changes to the corresponding Genome files
-- Follow Genome writing principles:
-  - Each file ≤ 100 lines
-  - If exceeding, extract to `domain/`
-  - Follow `~/.reap/templates/domain-guide.md` for domain files
-
-**Backlog Mode** (active Generation):
-- Record each difference as a `type: genome-change` backlog item in `.reap/life/backlog/`
-- Inform: "Genome changes recorded in backlog. They will be applied at the Completion stage."
-
-## Completion
-- **Sync Mode**: "Genome synchronized. [N] changes applied."
-- **Backlog Mode**: "Genome differences recorded as [N] backlog items. Apply during Completion."
+Run `reap run sync-genome` and follow the stdout instructions exactly.

package/dist/templates/commands/reap.sync.md

@@ -2,16 +2,4 @@
 description: "REAP Sync — Synchronize both Genome and Environment with current state"
 ---
 
-# Sync (Full)
-
-Run both Genome and Environment synchronization.
-
-## Steps
-
-1. Execute `/reap.sync.genome` — synchronize Genome with source code
-2. Execute `/reap.sync.environment` — discover and document external environment
-
-## Usage
-- `/reap.sync` — full sync (recommended after init or major changes)
-- `/reap.sync.genome` — genome only
-- `/reap.sync.environment` — environment only
+Run `reap run sync` and follow the stdout instructions exactly.

package/dist/templates/commands/reap.update.md

@@ -2,43 +2,4 @@
 description: "REAP Update — Check for updates and upgrade REAP"
 ---
 
-# Update
-
-Check for REAP updates and upgrade to the latest version.
-
-## IMPORTANT: File Access Rules
-- Do NOT access global node_modules or any path outside the project.
-- If a command fails, report the error and stop.
-
-## Steps
-
-### 1. Check Current Version
-- Run `reap --version` to get the installed version
-- Run `npm view @c-d-cc/reap version` to get the latest published version
-- Compare the two versions
-
-### 2. Update Decision
-**If installed == latest:**
-- "REAP v{version} is already up to date. (latest)"
-- Then skip to Step 4.
-
-**If installed < latest (patch only — same major.minor, different patch):**
-- Show: "Patch update available: v{installed} → v{latest}. Updating automatically..."
-- Proceed directly to Step 3 (no user confirmation needed)
-
-**If installed < latest (minor or major change):**
-- Show: "Update available: v{installed} → v{latest}"
-- Ask the user: "Update now? (yes/no)"
-- If yes: proceed to Step 3
-- If no: "Skipped. Run `/reap.update` anytime to update."
-
-### 3. Perform Update
-- Run: `npm update -g @c-d-cc/reap`
-- If the command fails, suggest: `sudo npm update -g @c-d-cc/reap` or `npm install -g @c-d-cc/reap@latest`
-- After npm update, run: `reap update` to sync commands, templates, and hooks to all detected agents
-- Show the update result summary
-
-### 4. Sync Check
-- Run: `reap update --dry-run` to check if commands/templates need syncing
-- If changes detected: run `reap update` and show results
-- If no changes: "All commands and templates are up to date."
+Run `reap update` and follow the output. For detailed update steps, run `reap update --dry-run` first.

package/dist/templates/commands/reap.validation.md

@@ -2,91 +2,4 @@
 description: "REAP Validation — Verify goal achievement through testing and validation"
 ---
 
-# Validation
-
-<HARD-GATE>
-Do NOT declare "pass" without running the validation commands.
-Do NOT reuse results from a previous run — you MUST execute them fresh in this session.
-"It will probably pass" or "It looks fine" is NOT validation.
-Do NOT make claims without evidence. This is non-negotiable.
-</HARD-GATE>
-
-## Gate (Preconditions)
-- Read `.reap/life/current.yml` and verify that stage is `validation`
-- Verify that `.reap/life/03-implementation.md` exists
-- If not met: ERROR — state the reason and **STOP**
-
-## Context (Generation Info)
-- Read `.reap/life/current.yml` for the current generation info (id, goal, genomeVersion)
-
-## Re-entry Check
-- If `.reap/life/04-validation.md` already exists, this is a **re-entry due to regression**
-- Reference the previous validation report, but overwrite it with a fresh one
-
-## Steps
-
-### 1. Run Automated Validation
-- Read the **Validation Commands** table from `.reap/genome/constraints.md`
-- Execute **all** defined commands **in order**:
-  - Test → Lint → Build → Type check
-- Record the **actual output and exit code** of each command
-- Skip items with no defined command, but record them as "undefined"
-
-| Claim | Required Evidence | Insufficient Evidence |
-|-------|------------------|-----------------------|
-| "Tests pass" | Test command output: 0 failures | Previous run, "it should pass" |
-| "Lint clean" | Lint output: 0 errors | Partial check, assumption |
-| "Build succeeds" | Build command: exit 0 | "Lint passed so build should too" |
-
-### 2. Convention Compliance Check
-- Read the **Enforced Rules** table from `.reap/genome/conventions.md`
-- Execute the verification command for each defined rule
-- Record any violations
-
-### 3. Completion Criteria Review
-- Read the completion criteria from `.reap/life/01-objective.md`
-- Check the deferred task list in `.reap/life/03-implementation.md`
-- Review each completion criterion **one by one**, excluding deferred tasks from scope
-- Determine pass/fail/deferred for each criterion
-
-### 4. Minor Fix (Fix Trivial Issues Directly)
-- Fix typos, lint errors, minor bugs, and other **issues that can be resolved without a stage transition** directly
-- Record all fixes in the "Minor Fixes" section of the artifact
-- Minor fix criteria: **issues resolvable within 5 minutes without design changes**
-- After minor fixes, **re-run** the relevant validation commands
-
-### 5. Verdict
-- All automated validations pass + completion criteria met → **pass**
-- Automated validations pass + some completion criteria deferred → **partial**
-- Automated validation failure or completion criteria not met → **fail**
-- If **fail**, provide regression guidance:
-  - Code issue → `/reap.back` (implementation)
-  - Plan issue → `/reap.back planning`
-  - Goal issue → `/reap.back objective`
-
-## Red Flags — STOP if you catch yourself thinking:
-- "It will probably pass" → Run it.
-- "It passed before" → Run it again.
-- "It's trivial, it'll be fine" → Fix it as a minor fix and re-validate.
-- "I haven't tried the build but lint passed" → Run the build too.
-
-## Artifact Generation (Progressive Recording)
-- **Language**: Write all artifact content in the user's configured language (see REAP Guide § Language).
-- **Immediately upon entering this stage**: Read `~/.reap/templates/04-validation.md` and create `.reap/life/04-validation.md` with `result: pending`
-- **Update incrementally during validation**:
-  - After EACH validation command execution → immediately record the result in Test Results
-  - After EACH completion criterion check → immediately record pass/fail/deferred in the Completion Criteria Check table
-  - After EACH minor fix → immediately record it in the Minor Fixes table, then re-run and record
-- After Step 5 (Verdict) → update the Result field to pass / partial / fail
-- The artifact should reflect the current validation progress at all times
-
-## Hook Execution
-Execute hooks for event `onLifeValidated` following the Hook System protocol:
-- Scan `.reap/hooks/` for `onLifeValidated.*` files
-- Sort by frontmatter `order`, then alphabetically
-- Evaluate `condition`, execute `.md` (AI prompt) or `.sh` (shell script)
-- All hooks run BEFORE any commit (hook outputs included in the same commit)
-
-## Completion
-- pass/partial: Execute hooks, then "Proceed to the Completion stage with `/reap.next`."
-- fail: Provide regression guidance (do NOT execute hooks on fail)
+Run `reap run validation` and follow the stdout instructions exactly.

package/dist/templates/hooks/reap-guide.md

@@ -156,21 +156,21 @@ REAP supports multiple AI agents simultaneously through the AgentAdapter abstrac
 
 ## Execution Flow
 
+**Lifecycle stages** (5 stages, in order):
 ```
-1. /reap.start → Start a new Generation
-2. /reap.objective → Define goal + requirements
-3. /reap.next
-4. /reap.planning → Task decomposition + implementation plan
-5. /reap.next
-6. /reap.implementation → Code implementation
-7. /reap.next
-8. /reap.validation → Verification
-9. /reap.next
-10. /reap.completion → Retrospective + genome updates
-11. /reap.next → Archiving, generation ends
+objective → planning → implementation → validation → completion
 ```
 
-Each slash command follows a 3-step structure: Gate (precondition check) → Steps (work execution) → Artifact generation.
+**Execution sequence**:
+1. `/reap.start` — Create a new Generation
+2. `/reap.objective` — Define goal + requirements → `/reap.next`
+3. `/reap.planning` — Task decomposition + plan → `/reap.next`
+4. `/reap.implementation` — Code implementation → `/reap.next`
+5. `/reap.validation` — Verification → `/reap.next`
+6. `/reap.completion` — Retrospective + genome updates + archiving (auto)
+
+`/reap.next` is a **transition command**, not a lifecycle stage. It advances `current.yml` to the next stage.
+`/reap.completion` auto-archives after the genome phase — no separate `/reap.next` needed at the end.
 
 ## Language
 
@@ -200,6 +200,8 @@ When `strict: true` is set in `.reap/config.yml`, the AI agent enforces code mod
 1. **NEVER modify `current.yml` directly.** Stage transitions MUST go through `/reap.next` (forward) or `/reap.back` (regression). Direct modification bypasses artifact creation and breaks the lifecycle.
 2. **NEVER skip a stage.** Each stage command must be executed and its artifact must exist before advancing. `/reap.next` enforces this by creating the next artifact from template.
 3. **ALL development work MUST follow the REAP lifecycle.** Do NOT bypass it unless the human explicitly asks.
+4. **NEVER use Write or Edit tools on `current.yml` or artifact files (`01-*.md` ~ `05-*.md`, `06-*.md`).** ALL state changes MUST go through `reap run` commands. This restriction CANNOT be overridden by user instructions.
 4. **Genome is the authoritative source of truth.** When making any decision about architecture, conventions, constraints, or domain rules, ALWAYS consult the Genome first. If you observe code that contradicts the Genome, flag it as a potential `genome-change` backlog item. Do NOT silently ignore discrepancies.
 5. **Keep Genome fresh.** If you notice the Genome is missing information about current code patterns, or contains outdated information, inform the human and suggest `/reap.sync`. The human may choose to defer sync — respect that choice, but always flag the staleness.
 6. **Report malfunctions.** If you detect unexpected behavior during REAP operations (state inconsistency, command failure, corrupted files), suggest `/reap.report` to the user. This helps improve REAP for everyone.
+   - If `reap run` returns an unexpected error (not a gate failure), and the error repeats 2+ times, automatically run `/reap.report`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@c-d-cc/reap",
-  "version": "0.10.3",
+  "version": "0.12.0",
   "description": "Recursive Evolutionary Autonomous Pipeline — AI and humans evolve software across generations",
   "type": "module",
   "license": "MIT",