@sienklogic/plan-build-run 2.1.0 → 2.1.1

package/plugins/copilot-pbr/references/integration-patterns.md

@@ -0,0 +1,117 @@
+# Integration Patterns Reference
+
+Technology-specific grep/search patterns and E2E flow templates for integration-checker.
+
+## E2E Flow Templates
+
+### Authentication Flow
+
+| Step | Check |
+|------|-------|
+| 1. Login form exists | Component with email/password fields or OAuth button |
+| 2. Form submits to auth endpoint | onSubmit calls auth API or redirects to OAuth |
+| 3. Backend validates credentials | Route handler with validation logic |
+| 4. Token/session created | JWT generation or session creation |
+| 5. Token stored client-side | Cookie set or localStorage/state |
+| 6. Requests include auth | Auth header or cookie sent with API calls |
+| 7. Protected routes accessible | Auth middleware passes with valid token |
+| 8. Invalid auth redirects | 401 or redirect when no/invalid token |
+
+### Data Display Flow
+
+| Step | Check |
+|------|-------|
+| 1. Page/component renders | Component file with JSX/HTML |
+| 2. Component requests data | useEffect/useSWR/useQuery with API call |
+| 3. API route handles request | Route handler exists for endpoint |
+| 4. Handler queries data source | Database query or service call |
+| 5. Data returned | res.json() or return with data |
+| 6. Component renders data | Data mapped to JSX elements |
+| 7. Loading state handled | Loading indicator while fetching |
+| 8. Error state handled | Error message on failure |
+
+### Form Submission Flow
+
+| Step | Check |
+|------|-------|
+| 1. Form component exists | Form element with inputs |
+| 2. Client-side validation | Schema or manual checks |
+| 3. Submit calls API | fetch/axios with form data |
+| 4. Server validates input | Input validation in handler |
+| 5. Server processes request | Business logic (CRUD) |
+| 6. Database mutation | Write operation |
+| 7. Success response | Response with success status |
+| 8. UI reflects success | Toast/redirect/state update |
+| 9. Error handling | Server errors shown in form |
+
+### CRUD Flow (per entity)
+
+| Step | Check |
+|------|-------|
+| 1. List view | Component renders list |
+| 2. Create form | Component with creation UI |
+| 3. Create API | POST route with handler |
+| 4. Read/detail API | GET route with handler |
+| 5. Update form | Component with edit UI |
+| 6. Update API | PUT/PATCH route with handler |
+| 7. Delete action | Delete button/handler |
+| 8. Delete API | DELETE route with handler |
+| 9. Frontend calls all CRUD | All operations invoked from UI |
+| 10. Auth on all ops | All operations require auth (if applicable) |
+
+## Technology-Specific Search Patterns
+
+### React / Next.js
+
+```bash
+# Component imports and usage
+grep -rn "import.*{Component}" src/ --include="*.tsx"
+grep -rn "<{Component}" src/ --include="*.tsx"
+
+# Context providers (must wrap the app)
+grep -rn "Provider" src/app/layout.tsx src/pages/_app.tsx 2>/dev/null
+
+# Client vs Server components (Next.js)
+grep -rn "'use client'\|\"use client\"" src/ --include="*.tsx"
+
+# Next.js API routes (App Router)
+find src/app/api -name "route.ts" 2>/dev/null
+
+# Next.js middleware
+find src -name "middleware.ts" -maxdepth 2 2>/dev/null
+
+# Data fetching hooks
+grep -rn "useSWR\|useQuery\|useMutation\|getServerSideProps\|getStaticProps" src/ --include="*.tsx" --include="*.ts"
+```
+
+### Express / Node.js API
+
+```bash
+# Route registration on main app
+grep -rn "app\.use\|router\.use" src/ --include="*.ts" --include="*.js"
+
+# Middleware chain order (important for auth)
+grep -rn "\.use(" src/app.ts src/server.ts src/index.ts 2>/dev/null
+
+# Error handling middleware (must be last)
+grep -rn "err.*req.*res.*next\|ErrorHandler\|errorMiddleware" src/ --include="*.ts" --include="*.js"
+
+# Database connection used in routes
+grep -rn "db\.\|prisma\.\|knex\.\|mongoose\.\|sequelize\." src/ --include="*.ts" --include="*.js" | grep -v "node_modules"
+```
+
+### Python (Django / Flask / FastAPI)
+
+```bash
+# URL patterns
+grep -rn "urlpatterns\|path(\|route(" */urls.py **/urls.py 2>/dev/null
+
+# View imports
+grep -rn "from.*views.*import\|from.*api.*import" */urls.py **/urls.py 2>/dev/null
+
+# Middleware registration
+grep -rn "MIDDLEWARE" */settings.py 2>/dev/null
+
+# Model imports in views
+grep -rn "from.*models.*import" */views.py **/views.py 2>/dev/null
+```

package/plugins/copilot-pbr/references/model-profiles.md

@@ -0,0 +1,143 @@
+# Model Profiles Reference
+
+How Plan-Build-Run maps agents to models and how to configure model selection.
+
+---
+
+## Session Model (Orchestrator)
+
+The orchestrator is your main Claude Code session -- it reads skills, manages state, and routes work to agents. Its model is whatever you selected in Claude Code (not controlled by PBR's `config.json`).
+
+**Cost impact:** The orchestrator accounts for roughly 40% of total session cost. Agents set to `inherit` (planner, executor, debugger, general in the `balanced` profile) also use this model. Switching your session from Opus to Sonnet reduces cost for both the orchestrator and all `inherit` agents.
+
+**Recommendations:**
+
+| Goal | Session Model | Config Adjustment |
+|------|---------------|-------------------|
+| Maximum quality | Opus | None needed -- `inherit` agents get Opus |
+| Balanced cost/quality | Sonnet | None needed -- `inherit` agents get Sonnet, which handles most tasks well |
+| Cheap orchestration, Opus agents | Sonnet | Set `planner: "opus"`, `executor: "opus"`, `debugger: "opus"` to override inherit |
+
+Sonnet 4.6 handles orchestration tasks (state reading, routing decisions, context assembly) effectively. Reserve Opus for agents doing complex reasoning, architecture, or novel code generation.
+
+---
+
+## Agent-to-Model Mapping
+
+Each Plan-Build-Run agent's model is controlled by `config.json models.*`. When no config entry exists for an agent, the agent inherits the session model.
+
+The `model:` frontmatter field has been removed from PBR agent definitions — `config.json` is now the sole source of truth for agent model assignment.
+
+### Default Agent Models
+
+| Agent | Default Model | Rationale |
+|-------|---------------|-----------|
+| `researcher` | `sonnet` | Research requires strong reasoning for source evaluation and synthesis |
+| `planner` | `inherit` | Planning is complex; inherits the session's primary model |
+| `executor` | `inherit` | Execution needs the full capability of the session model |
+| `verifier` | `sonnet` | Verification needs solid reasoning but not the heaviest model |
+| `integration-checker` | `sonnet` | Cross-phase analysis requires strong pattern matching |
+| `plan-checker` | `sonnet` | Plan quality analysis needs good analytical capability |
+| `debugger` | `inherit` | Debugging is complex; inherits session model |
+| `codebase-mapper` | `sonnet` | Codebase analysis requires thorough reasoning |
+| `synthesizer` | `haiku` | Synthesis is mechanical combination; speed over depth |
+| `general` | `inherit` | Lightweight utility; inherits session model |
+| `audit` | `inherit` | Session log analysis inherits session model |
+| `dev-sync` | `inherit` | Cross-plugin sync is mechanical; inherits session model |
+
+The `inherit` value means the agent uses whatever model the parent session is running (typically the user's configured Claude model). Defaults listed above are the effective values from the `balanced` profile in `config.json`.
+
+---
+
+## Model Profile Presets
+
+The `/pbr:settings model-profile {preset}` command sets all agent models at once using a preset:
+
+| Profile | Researcher | Planner | Executor | Verifier | Int-Checker | Debugger | Mapper | Synthesizer |
+|---------|-----------|---------|----------|----------|-------------|----------|--------|-------------|
+| `quality` | opus | opus | opus | opus | sonnet | opus | sonnet | sonnet |
+| `balanced` | sonnet | inherit | inherit | sonnet | sonnet | inherit | sonnet | haiku |
+| `budget` | haiku | haiku | haiku | haiku | haiku | haiku | haiku | haiku |
+| `adaptive` | sonnet | sonnet | inherit | sonnet | haiku | inherit | haiku | haiku |
+
+### Preset Descriptions
+
+- **quality**: Maximum capability across all agents. Best results but highest token cost. Use for critical projects or complex architectures.
+- **balanced**: The default preset. Front-loads intelligence in research and verification, inherits session model for planning and execution. Good general-purpose choice.
+- **budget**: All agents use haiku. Fastest and cheapest, but reduced quality for complex reasoning tasks. Suitable for well-defined, mechanical work.
+- **adaptive**: Front-loads intelligence in research and planning (where decisions matter most), uses lighter models for mechanical execution and verification. Good cost-quality tradeoff.
+
+---
+
+## Configuring Models
+
+### Per-Agent Configuration
+
+Set an individual agent's model via `/pbr:settings`:
+
+```
+/pbr:settings model executor sonnet
+/pbr:settings model verifier opus
+```
+
+Or edit `config.json` directly:
+
+```json
+{
+  "models": {
+    "researcher": "sonnet",
+    "planner": "inherit",
+    "executor": "inherit",
+    "verifier": "sonnet",
+    "integration_checker": "sonnet",
+    "debugger": "inherit",
+    "mapper": "sonnet",
+    "synthesizer": "haiku"
+  }
+}
+```
+
+### Valid Model Values
+
+| Value | Meaning |
+|-------|---------|
+| `sonnet` | Claude Sonnet (4.5/4.6) -- balanced speed and capability |
+| `opus` | Claude Opus (4.6) -- highest capability, slower |
+| `haiku` | Claude Haiku (4.5) -- fastest, lower capability |
+| `inherit` | Use the session's primary model (whatever the user is running) |
+
+Note: Claude Code 2.1.45+ supports Sonnet 4.6. Model values are abstract names — Claude Code resolves them to the latest available version.
+
+---
+
+## Custom Profiles
+
+The `model_profiles` key in `config.json` lets you define named profiles beyond the four built-in presets. Each profile is a partial map of agent names to model strings — omitted agents fall back to the active profile defaults.
+
+```json
+{
+  "model_profiles": {
+    "my-profile": {
+      "executor": "opus",
+      "planner": "opus",
+      "synthesizer": "sonnet"
+    }
+  }
+}
+```
+
+Activate a custom profile with `/pbr:settings model-profile my-profile`. The profile merges with the `balanced` preset: any agent not listed in your custom profile uses its `balanced` default.
+
+Partial profiles are allowed — you can override just the agents you care about. This is useful for temporarily upgrading a single agent without specifying the rest.
+
+---
+
+## Model Selection in Skill Orchestration
+
+Skills that spawn subagents use the `model` parameter in `Task()` calls. Some skills hardcode a lighter model for specific tasks:
+
+- **Build skill**: Spawns inline verifiers with `model: "haiku"` for quick spot-checks
+- **Build skill**: Spawns codebase mapper updates with `model: "haiku"` for incremental map refreshes
+- **Plan skill**: Uses the configured `planner` model for main planning work
+
+The `subagent_type` parameter automatically loads the agent definition, and the model from `config.json` takes precedence over any agent-level model setting.

package/plugins/copilot-pbr/references/model-selection.md

@@ -0,0 +1,31 @@
+# Model Selection Reference
+
+Plan-Build-Run uses adaptive model selection to balance cost and capability.
+
+## How It Works
+
+1. The planner annotates each task with `complexity="simple|medium|complex"`
+2. The build skill maps complexity to a model via `config.models.complexity_map`
+3. The executor agent is spawned with the selected model
+
+## Default Mapping
+
+| Complexity | Model | Rationale |
+|-----------|-------|-----------|
+| simple | haiku | Fast, cheap — sufficient for mechanical changes |
+| medium | sonnet | Good balance for standard feature work |
+| complex | inherit | Uses session model — see `model-profiles.md` Session Model section for cost implications |
+
+## Override Mechanisms
+
+1. **Per-task override**: Add `model="sonnet"` attribute to task XML in PLAN.md
+2. **Config override**: Set `models.complexity_map` in config.json to change defaults
+3. **Agent-level override**: Set `models.executor` in config.json to force a single model for all executor spawns (disables adaptive selection)
+
+## Heuristics
+
+The planner uses these signals to determine complexity:
+- File count and types
+- Task name keywords
+- Dependency count
+- Whether the task introduces new patterns vs. follows established ones

package/plugins/copilot-pbr/references/pbr-tools-cli.md

@@ -0,0 +1,400 @@
+# pbr-tools.js CLI Reference
+
+Command-line interface for structured JSON operations on `.planning/` state.
+Skills and agents call this via Bash to avoid token-expensive text parsing.
+
+```
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js <command> [args]
+```
+
+All commands output JSON to stdout. Errors output JSON with an `error` field to stderr (exit code 1).
+
+---
+
+## State Commands
+
+### `state load`
+
+Returns full project state as a single JSON object.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state load
+```
+
+**Output:**
+```json
+{
+  "exists": true,
+  "config": { ... },        // config.json contents
+  "state": {                 // STATE.md frontmatter + parsed body
+    "version": 2,
+    "current_phase": "1",
+    "status": "building",
+    "progress_percent": 45,
+    "last_activity": "2025-01-15",
+    "last_command": "/pbr:execute-phase",
+    "blockers": []
+  },
+  "roadmap": {               // Parsed ROADMAP.md
+    "phases": [{ "number": "01", "name": "...", "status": "planned", ... }]
+  },
+  "phase_count": 3,
+  "current_phase": "1",
+  "progress": { "phases": [...], "total_plans": 5, "completed_plans": 2, "percentage": 40 }
+}
+```
+
+### `state check-progress`
+
+Recalculates progress from filesystem (plan files, summaries, verification).
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state check-progress
+```
+
+**Output:**
+```json
+{
+  "phases": [
+    { "directory": "01-setup", "plans": 2, "summaries": 2, "completed": 2, "has_verification": true, "status": "verified" }
+  ],
+  "total_plans": 5,
+  "completed_plans": 3,
+  "percentage": 60
+}
+```
+
+### `state update <field> <value>`
+
+Atomically updates a single field in STATE.md. Uses file locking.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state update current_phase 2
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state update status building
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state update last_activity now   # auto-timestamps
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state update plans_complete 3
+```
+
+**Valid fields:** `current_phase`, `status`, `plans_complete`, `last_activity`
+
+**Output:** `{ "success": true, "field": "status", "value": "building" }`
+
+---
+
+## Config Commands
+
+### `config validate`
+
+Validates `config.json` against the JSON schema. Detects both schema violations and semantic conflicts.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js config validate
+```
+
+**Output:**
+```json
+{
+  "valid": true,
+  "errors": [],
+  "warnings": ["features.auto_continue=true with mode=interactive: auto_continue only fires in autonomous mode"]
+}
+```
+
+### `config resolve-depth [dir]`
+
+Resolves the effective depth profile by merging base profile with user overrides.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js config resolve-depth
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js config resolve-depth /path/to/.planning
+```
+
+**Output:** Full depth profile object with all resolved values (research rounds, plan detail level, verification depth, etc.)
+
+---
+
+## Plan & Phase Commands
+
+### `plan-index <phase>`
+
+Returns plan inventory for a phase, grouped by wave.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js plan-index 1
+```
+
+**Output:**
+```json
+{
+  "phase": "01-setup",
+  "total_plans": 3,
+  "plans": [
+    {
+      "file": "PLAN-01.md",
+      "plan_id": "01",
+      "wave": 1,
+      "type": "feature",
+      "autonomous": true,
+      "depends_on": [],
+      "gap_closure": false,
+      "has_summary": true,
+      "must_haves_count": 4
+    }
+  ],
+  "waves": { "wave_1": ["01", "02"], "wave_2": ["03"] }
+}
+```
+
+### `phase-info <phase>`
+
+Comprehensive single-phase status combining roadmap, filesystem, and plan data.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js phase-info 1
+```
+
+**Output:**
+```json
+{
+  "phase": "01-setup",
+  "name": "setup",
+  "goal": "Initialize project infrastructure",
+  "roadmap_status": "building",
+  "filesystem_status": "partial",
+  "plans": [...],
+  "plan_count": 3,
+  "summaries": [{ "file": "SUMMARY-01.md", "plan": "01", "status": "complete" }],
+  "completed": 1,
+  "verification": null,
+  "has_context": false
+}
+```
+
+### `must-haves <phase>`
+
+Collects all must-haves from phase plans — truths, artifacts, and key links.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js must-haves 1
+```
+
+**Output:**
+```json
+{
+  "phase": "01-setup",
+  "plans": {
+    "01": { "truths": ["..."], "artifacts": ["..."], "key_links": ["..."] }
+  },
+  "all": { "truths": [...], "artifacts": [...], "key_links": [...] },
+  "total": 12
+}
+```
+
+---
+
+## Frontmatter Command
+
+### `frontmatter <filepath>`
+
+Parses a markdown file's YAML frontmatter and returns as JSON.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js frontmatter .planning/phases/01-setup/PLAN-01.md
+```
+
+**Output:** The frontmatter fields as a JSON object. Returns `{ "error": "File not found: ..." }` if the file doesn't exist.
+
+---
+
+## Roadmap Commands
+
+### `roadmap update-status <phase> <status>`
+
+Updates the Status column for a phase in ROADMAP.md's Phase Overview table. Uses file locking. Warns on invalid status transitions but does not block them.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js roadmap update-status 1 building
+```
+
+**Valid statuses:** `pending`, `planned`, `building`, `built`, `partial`, `needs_fixes`, `verified`, `skipped`
+
+**Output:** `{ "success": true, "old_status": "planned", "new_status": "building" }`
+
+### `roadmap update-plans <phase> <complete> <total>`
+
+Updates the Plans column (e.g., "2/5") for a phase in ROADMAP.md.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js roadmap update-plans 1 2 5
+```
+
+**Output:** `{ "success": true, "old_plans": "1/5", "new_plans": "2/5" }`
+
+---
+
+## History Commands
+
+### `history append <type> <title> [body]`
+
+Appends a record to HISTORY.md. Creates the file if it doesn't exist.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js history append milestone "v1.0 Release" "Initial release with core features"
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js history append phase "01-setup Complete" "3 plans executed, all verified"
+```
+
+**Types:** `milestone`, `phase`
+
+**Output:** `{ "success": true }`
+
+### `history load`
+
+Loads all HISTORY.md records as structured JSON.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js history load
+```
+
+**Output:**
+```json
+{
+  "records": [
+    { "type": "milestone", "title": "v1.0 Release", "date": "2025-01-15", "body": "..." }
+  ],
+  "line_count": 42
+}
+```
+
+Returns `null` if HISTORY.md doesn't exist.
+
+---
+
+## Event Command
+
+### `event <category> <event> [JSON-details]`
+
+Logs a structured event to `.planning/logs/events.jsonl`.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js event build plan-complete '{"plan":"01","phase":"01-setup"}'
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js event error hook-failure '{"script":"validate-task.js"}'
+```
+
+**Output:** `{ "logged": true, "category": "build", "event": "plan-complete" }`
+
+If the JSON-details argument is not valid JSON, it's stored as `{ "raw": "<the string>" }`.
+
+---
+
+## Compound Init Commands
+
+Compound commands that compose multiple data sources into a single JSON response.
+Replace multi-step context loading in skills with a single CLI call.
+
+### `init execute-phase <phase>`
+
+Everything an executor needs to start building a phase.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init execute-phase 3
+```
+
+**Output:**
+```json
+{
+  "executor_model": "sonnet",
+  "verifier_model": "sonnet",
+  "config": { "depth": "standard", "mode": "interactive", "parallelization": {}, "planning": {}, "gates": {}, "features": {} },
+  "phase": { "num": "3", "dir": "03-auth", "name": "auth", "goal": "...", "has_context": false, "status": "planned", "plan_count": 2, "completed": 0 },
+  "plans": [{ "file": "PLAN-01.md", "plan_id": "01", "wave": 1, "autonomous": true, "has_summary": false, "must_haves_count": 4, "depends_on": [] }],
+  "waves": { "wave_1": ["01", "02"] },
+  "branch_name": "main",
+  "git_clean": true
+}
+```
+
+### `init plan-phase <phase>`
+
+Everything a planner needs to start phase planning.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init plan-phase 3
+```
+
+**Output:** `researcher_model`, `planner_model`, `checker_model`, `config` (depth profile, features, planning settings), `phase` (num, dir, goal, depends_on), `existing_artifacts`, `workflow` flags.
+
+### `init quick <description>`
+
+Everything the quick skill needs: next task number, slug, directory path.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init quick "add search feature"
+```
+
+**Output:** `next_task_number`, `slug`, `dir`, `dir_name`, `timestamp`, `config` subset.
+
+### `init verify-work <phase>`
+
+Everything a verifier needs to start verification.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init verify-work 3
+```
+
+**Output:** `verifier_model`, `phase` info, `has_verification`, `prior_attempts`, `prior_status`, `summaries`.
+
+### `init resume`
+
+Detect interrupted state and suggest continuation.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init resume
+```
+
+**Output:** `state`, `auto_next`, `continue_here`, `active_skill`, `current_phase`, `progress`.
+
+### `init progress`
+
+All phases with status and completion data.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js init progress
+```
+
+**Output:** `current_phase`, `phase_count`, `status`, `phases` array, `total_plans`, `completed_plans`, `percentage`.
+
+---
+
+## State Mutation Extensions
+
+### `state patch <JSON>`
+
+Multi-field atomic STATE.md update. Updates all fields in a single pass.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state patch '{"status":"executing","last_activity":"now"}'
+```
+
+**Valid fields:** `current_phase`, `status`, `plans_complete`, `last_activity`, `progress_percent`, `phase_slug`, `last_command`, `blockers`
+
+**Output:** `{ "success": true, "updated": ["status", "last_activity"] }`
+
+### `state advance-plan`
+
+Increment current plan number in STATE.md and update progress percentage.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state advance-plan
+```
+
+**Output:** `{ "success": true, "previous_plan": 1, "current_plan": 2, "total_plans": 5, "progress_percent": 40 }`
+
+### `state record-metric [--duration Nm] [--plans-completed N]`
+
+Record session/execution metrics. Appends to HISTORY.md and updates last_activity.
+
+```bash
+node ${CLAUDE_PLUGIN_ROOT}/scripts/pbr-tools.js state record-metric --duration 15m --plans-completed 3
+```
+
+**Output:** `{ "success": true, "duration_minutes": 15, "plans_completed": 3 }`