@sandrinio/vbounce 1.3.2 → 1.5.0

package/brains/claude-agents/devops.md

@@ -28,30 +28,30 @@ When the Team Lead delegates a story merge (after Architect PASS):
 ### Pre-Merge Checks
 ```bash
 # Verify the story worktree exists and has no uncommitted changes
-cd .worktrees/STORY-{ID}
+cd .worktrees/STORY-{ID}-{StoryName}
 git status
 git log --oneline sprint/S-{XX}..HEAD  # review story commits
 
 # Verify QA and Architect reports exist and show PASS
-ls .bounce/reports/STORY-{ID}-qa*.md
-ls .bounce/reports/STORY-{ID}-arch.md
+ls .bounce/reports/STORY-{ID}-{StoryName}-qa*.md
+ls .bounce/reports/STORY-{ID}-{StoryName}-arch.md
 ```
 
 ### Merge Execution
 ```bash
 # Archive reports BEFORE removing worktree
-mkdir -p .bounce/archive/S-{XX}/STORY-{ID}
-cp .worktrees/STORY-{ID}/.bounce/reports/* .bounce/archive/S-{XX}/STORY-{ID}/
+mkdir -p .bounce/archive/S-{XX}/STORY-{ID}-{StoryName}
+cp .worktrees/STORY-{ID}-{StoryName}/.bounce/reports/* .bounce/archive/S-{XX}/STORY-{ID}-{StoryName}/
 
 # Switch to sprint branch and merge
 git checkout sprint/S-{XX}
-git merge story/STORY-{ID} --no-ff -m "Merge STORY-{ID}: {Story Name}"
+git merge story/STORY-{ID}-{StoryName} --no-ff -m "Merge STORY-{ID}: {Story Name}"
 ```
 
 ### Conflict Resolution
 If merge conflicts occur:
 - **Simple conflicts** (import ordering, adjacent edits, whitespace): Resolve directly.
-- **Complex conflicts** (logic changes, competing implementations): Write a **Merge Conflict Report** to `.bounce/reports/STORY-{ID}-merge-conflict.md` and notify the Lead. Do NOT guess at resolution.
+- **Complex conflicts** (logic changes, competing implementations): Write a **Merge Conflict Report** to `.bounce/reports/STORY-{ID}-{StoryName}-merge-conflict.md` and notify the Lead. Do NOT guess at resolution.
 
 When resolving conflicts:
 - Preserve the intent of BOTH story branches
@@ -73,8 +73,8 @@ git merge --abort  # or git reset --hard HEAD~1
 ### Worktree Cleanup
 ```bash
 # Remove worktree and story branch
-git worktree remove .worktrees/STORY-{ID}
-git branch -d story/STORY-{ID}
+git worktree remove .worktrees/STORY-{ID}-{StoryName}
+git branch -d story/STORY-{ID}-{StoryName}
 
 # Verify cleanup
 git worktree list
@@ -123,7 +123,7 @@ git push origin --delete sprint/S-{XX}  # if pushed to remote
 For stories or sprints that need preview environments:
 ```bash
 # Push story branch for preview deploy (if CI supports it)
-git push origin story/STORY-{ID}
+git push origin story/STORY-{ID}-{StoryName}
 
 # Verify preview URL is live and functional
 # Check deployment logs for errors
@@ -146,18 +146,21 @@ Before approving a deployment:
 
 ## Your Output
 
-Write a **DevOps Report** to `.bounce/reports/STORY-{ID}-devops.md` (for story merges) or `.bounce/reports/sprint-S-{XX}-devops.md` (for sprint releases).
+Write a **DevOps Report** to `.bounce/reports/STORY-{ID}-{StoryName}-devops.md` (for story merges) or `.bounce/reports/sprint-S-{XX}-devops.md` (for sprint releases).
 You MUST include the YAML frontmatter block exactly as shown below:
 
+**Token Tracking**: Before generating this report, retrieve your session's token usage (if you are Claude, ask your CLI; if Gemini, read your context estimate; if Codex, read your log output) and populate `tokens_used`.
+
 ### Story Merge Report
 ```markdown
 ---
 type: "story-merge"
 status: "{Clean / Conflicts Resolved / Failed}"
+tokens_used: {number}
 conflicts_detected: {true/false}
 ---
 
-# DevOps Report: STORY-{ID} Merge
+# DevOps Report: STORY-{ID}-{StoryName} Merge
 
 ## Pre-Merge Checks
 - [ ] Worktree clean (no uncommitted changes)
@@ -181,6 +184,12 @@ conflicts_detected: {true/false}
 
 ## Environment Changes
 - {New env vars, config changes, or "None"}
+
+## Process Feedback
+> Optional. Note friction with the V-Bounce framework itself — templates, handoffs, tooling, scripts.
+
+- {e.g., "hotfix_manager.sh sync failed silently when no worktrees existed"}
+- {e.g., "None"}
 ```
 
 ### Sprint Release Report
@@ -188,6 +197,7 @@ conflicts_detected: {true/false}
 ---
 type: "sprint-release"
 status: "{Deployed / Pending / Manual}"
+tokens_used: {number}
 version: "{VERSION}"
 ---
 
@@ -219,6 +229,12 @@ version: "{VERSION}"
 - [ ] Sprint branch deleted
 - [ ] Sprint report archived
 - [ ] Delivery Plan updated
+
+## Process Feedback
+> Optional. Note friction with the V-Bounce framework itself — templates, handoffs, tooling, scripts.
+
+- {e.g., "Sprint merge workflow assumes remote push but project has no remote configured"}
+- {e.g., "None"}
 ```
 
 ## Critical Rules

package/brains/claude-agents/qa.md

@@ -13,7 +13,7 @@ Validate that the Developer's implementation meets the Story's acceptance criter
 ## Before Testing
 
 1. **Query Project Lessons**: Run `./scripts/vbounce_ask.mjs "<summarize the story spec here>"` to retrieve known failure patterns relevant to this story from `LESSONS.md` and past reports.
-2. **Read the Developer Implementation Report** (`.bounce/reports/STORY-{ID}-dev.md`) to understand what was built.
+2. **Read the Developer Implementation Report** (`.bounce/reports/STORY-{ID}-{StoryName}-dev.md`) to understand what was built.
 3. **Read Story §2 The Truth** — these are your pass/fail criteria. If the Gherkin scenarios don't pass, the bounce failed.
 
 ## Your Testing Process
@@ -60,19 +60,22 @@ Check for unnecessary complexity the Developer added beyond the Story spec:
 
 ## Your Output
 
-Write a **QA Validation Report** to `.bounce/reports/STORY-{ID}-qa.md`.
+Write a **QA Validation Report** to `.bounce/reports/STORY-{ID}-{StoryName}-qa.md`.
 You MUST include the YAML frontmatter block exactly as shown below:
 
+**Token Tracking**: Before generating this report, retrieve your session's token usage (if you are Claude, ask your CLI; if Gemini, read your context estimate; if Codex, read your log output) and populate `tokens_used`.
+
 ### If Tests PASS:
 ```markdown
 ---
 status: "PASS"
 bounce_count: {N}
+tokens_used: {number}
 bugs_found: 0
 gold_plating_detected: false
 ---
 
-# QA Validation Report: STORY-{ID} — PASS
+# QA Validation Report: STORY-{ID}-{StoryName} — PASS
 
 ## Quick Scan Results
 - {Summary of structural health}
@@ -102,6 +105,12 @@ gold_plating_detected: false
 - Fixture data matches spec examples: {Yes/No}
 - API contracts match §3: {Yes/No}
 
+## Process Feedback
+> Optional. Note friction with the V-Bounce framework itself — templates, handoffs, RAG quality, tooling.
+
+- {e.g., "Dev report didn't specify which test runner was used — had to discover it myself"}
+- {e.g., "None"}
+
 ## Recommendation
 PASS — Ready for Architect review.
 ```
@@ -111,13 +120,14 @@ PASS — Ready for Architect review.
 ---
 status: "FAIL"
 bounce_count: {N}
+tokens_used: {number}
 bugs_found: {number of bugs}
 gold_plating_detected: {true/false}
 failed_scenarios:
   - "{scenario name}"
 ---
 
-# QA Validation Report: STORY-{ID} — FAIL (Bounce {N})
+# QA Validation Report: STORY-{ID}-{StoryName} — FAIL (Bounce {N})
 
 ## Failures
 ### Bug 1: {Short description}
@@ -130,6 +140,12 @@ failed_scenarios:
 ## Gold-Plating Findings
 - {Any unnecessary additions}
 
+## Process Feedback
+> Optional. Note friction with the V-Bounce framework itself — templates, handoffs, RAG quality, tooling.
+
+- {e.g., "Story §2 Gherkin scenarios were ambiguous — 'valid input' not defined"}
+- {e.g., "None"}
+
 ## Recommendation
 FAIL — Returning to Developer for fixes. Bounce count: {N}/3.
 ```
@@ -142,10 +158,10 @@ Every finding must include a non-coder analogy. Examples:
 
 ## Checkpointing
 
-After completing each major phase of your testing (e.g., Quick Scan done, PR Review done, scenarios validated), write a progress checkpoint to `.bounce/reports/STORY-{ID}-qa-checkpoint.md`:
+After completing each major phase of your testing (e.g., Quick Scan done, PR Review done, scenarios validated), write a progress checkpoint to `.bounce/reports/STORY-{ID}-{StoryName}-qa-checkpoint.md`:
 
 ```markdown
-# QA Checkpoint: STORY-{ID}
+# QA Checkpoint: STORY-{ID}-{StoryName}
 ## Completed
 - {Which testing phases are done}
 ## Remaining

package/brains/claude-agents/scribe.md

@@ -17,13 +17,13 @@ You follow the **vdoc workflow**: explore the codebase → plan documentation st
 
 1. **Read LESSONS.md** at the project root. Check for known documentation gotchas and naming conventions.
 2. **Read the task file** from the Team Lead — it tells you what was built this sprint and what needs documenting.
-3. **If `product_documentation/_manifest.json` exists**, read it first. Understand what's already documented to avoid duplicates and identify stale docs.
+3. **If `vdocs/_manifest.json` exists**, read it first. Understand what's already documented to avoid duplicates and identify stale docs.
 4. **Read the Sprint Report and Dev Reports** referenced in your task — they summarize what was built, key decisions, and any product docs flagged as affected.
 
 ## Documentation Workflow
 
 ### Mode: Init (No existing docs)
-When `product_documentation/` doesn't exist yet:
+When `vdocs/` doesn't exist yet:
 
 1. **Explore** — Scan the codebase to understand the project structure, features, and boundaries.
    - Read key entry points, config files, and route definitions
@@ -33,17 +33,17 @@ When `product_documentation/` doesn't exist yet:
    - Group by feature, not by file
    - Each doc should cover a cohesive capability
    - Identify cross-cutting concerns (auth, error handling, etc.)
-3. **Generate** — Write feature-centric markdown docs to `product_documentation/`.
+3. **Generate** — Write feature-centric markdown docs to `vdocs/`.
    - One doc per feature or cohesive capability
    - Include: what it does, how it works, key components, data flow, configuration
    - Use code references (file paths, function names) but don't paste large code blocks
-4. **Manifest** — Create/update `product_documentation/_manifest.json`.
+4. **Manifest** — Create/update `vdocs/_manifest.json`.
    - Project fingerprint (name, tech stack, key dirs)
    - Doc inventory with rich descriptions and tags for semantic matching
 5. **Self-Review** — Read each generated doc and verify accuracy against the codebase.
 
 ### Mode: Audit (Existing docs)
-When `product_documentation/` already exists:
+When `vdocs/` already exists:
 
 1. **Read `_manifest.json`** — understand current doc inventory.
 2. **Compare against codebase** — look for:
@@ -85,7 +85,7 @@ The manifest is a semantic routing table — it helps agents quickly find releva
   },
   "docs": [
     {
-      "path": "product_documentation/auth-system.md",
+      "path": "vdocs/auth-system.md",
       "title": "Authentication System",
       "description": "JWT-based auth with refresh tokens, OAuth providers, and role-based access control",
       "tags": ["auth", "jwt", "oauth", "rbac", "login", "session"],
@@ -98,8 +98,19 @@ The manifest is a semantic routing table — it helps agents quickly find releva
 ## Your Output
 
 Write a **Scribe Report** to `.bounce/reports/sprint-S-{XX}-scribe.md`:
+You MUST include the YAML frontmatter block exactly as shown below:
+
+**Token Tracking**: Before generating this report, retrieve your session's token usage (if you are Claude, ask your CLI; if Gemini, read your context estimate; if Codex, read your log output) and populate `tokens_used`.
 
 ```markdown
+---
+mode: "{init / audit / create}"
+tokens_used: {number}
+docs_created: {count}
+docs_updated: {count}
+docs_removed: {count}
+---
+
 # Scribe Report: Sprint S-{XX}
 
 ## Mode
@@ -127,6 +138,12 @@ Write a **Scribe Report** to `.bounce/reports/sprint-S-{XX}-scribe.md`:
 
 ## Lessons Flagged
 - {Any documentation gotchas worth recording}
+
+## Process Feedback
+> Optional. Note friction with the V-Bounce framework itself — templates, handoffs, RAG quality.
+
+- {e.g., "Dev reports rarely fill the 'Product Docs Affected' section — had to discover stale docs manually"}
+- {e.g., "None"}
 ```
 
 ## Critical Rules
@@ -137,5 +154,5 @@ Write a **Scribe Report** to `.bounce/reports/sprint-S-{XX}-scribe.md`:
 - **Feature-centric, not file-centric.** Organize by user-visible capabilities, not by file paths.
 - **You NEVER communicate with other agents directly.** Your report is your only output.
 - **You NEVER modify LESSONS.md.** Flag documentation lessons for the Lead to record.
-- **You NEVER modify application code.** You only create/edit files in `product_documentation/`.
+- **You NEVER modify application code.** You only create/edit files in `vdocs/`.
 - **Self-review is not optional.** Read every doc you write and verify it against the codebase.

package/brains/cursor-rules/vbounce-docs.mdc

@@ -8,17 +8,20 @@ alwaysApply: false
 
 ## Document Locations
 
-All in `product_plans/`. Deliveries get folders. Epics are subfolders. Stories live with Epic.
+All in `product_plans/`. Uses a state-based architecture (`strategy/`, `backlog/`, `sprints/`, `archive/`).
 
 | Document | Output |
 |----------|--------|
-| Charter | `product_plans/{project}_charter.md` |
-| Roadmap | `product_plans/{project}_roadmap.md` |
-| Risk Registry | `product_plans/RISK_REGISTRY.md` |
-| Delivery Plan | `product_plans/{delivery}/DELIVERY_PLAN.md` |
-| Epic | `product_plans/{delivery}/EPIC-{NNN}_{name}/EPIC-{NNN}.md` |
-| Story | `product_plans/{delivery}/EPIC-{NNN}_{name}/STORY-{EpicID}-{StoryID}.md` |
-| Product Docs | `product_documentation/*.md` + `_manifest.json` |
+| Charter | `product_plans/strategy/{project}_charter.md` |
+| Roadmap | `product_plans/strategy/{project}_roadmap.md` |
+| Risk Registry | `product_plans/strategy/RISK_REGISTRY.md` |
+| Delivery Plan | `product_plans/strategy/{delivery}_delivery_plan.md` |
+| Sprint Plan | `product_plans/sprints/sprint-{XX}/sprint-{XX}.md` |
+| Epic | `product_plans/backlog/EPIC-{NNN}_{name}/EPIC-{NNN}.md` |
+| Story | `product_plans/backlog/EPIC-{NNN}_{name}/STORY-{EpicID}-{StoryID}-{StoryName}.md` |
+| Hotfix | `product_plans/hotfixes/HOTFIX-{Date}-{Name}.md` |
+| Sprint Report | `product_plans/sprints/sprint-{XX}/sprint-report.md` |
+| Product Docs | `vdocs/*.md` + `_manifest.json` |
 
 ## Skills Reference
 
@@ -30,6 +33,7 @@ All in `product_plans/`. Deliveries get folders. Epics are subfolders. Stories l
 | react-best-practices | `skills/react-best-practices/` | Developer |
 | vibe-code-review | `skills/vibe-code-review/` | QA, Architect |
 | write-skill | `skills/write-skill/` | Team Lead |
+| improve | `skills/improve/` | Team Lead |
 
 ## Report Formats
 

package/brains/cursor-rules/vbounce-process.mdc

@@ -15,13 +15,14 @@ Documents are created in strict hierarchy — no level can be skipped:
 Charter (why) → Roadmap (strategic what/when) → Epic (detailed what) → Story (how) → Delivery Plan (execution) → Risk Registry (risks)
 
 ### Pre-Bounce Checks
-Before sprints: Lead triages request (L1 Trivial → Hotfix Path. L2-L4 → Epic Path). Lead reads RISK_REGISTRY.md (flag blocking risks), DELIVERY_PLAN.md §5 Open Questions (resolve before bouncing), and product_documentation/_manifest.json (know what's documented).
+Before sprints: Lead triages request (L1 Trivial → Hotfix Path. L2-L4 → Epic Path). Determines Execution Mode (Full Bounce vs Fast Track). Enforces sequential dependency order for stories with `Depends On:`. Reads RISK_REGISTRY.md (flag blocking risks), `sprint-{XX}.md` §2 Sprint Open Questions (resolve before bouncing), and vdocs/_manifest.json (know what's documented). Charter/Roadmap are frozen during sprints — use Impact Analysis Protocol for emergency changes.
 
 ### Phase 2: The Bounce (Implementation)
 **Standard Path (L2-L4):**
+0. Team Lead runs `./scripts/pre_bounce_sync.sh` to ensure LanceDB RAG context is fresh.
 1. Team Lead sends Story context pack to Developer.
-2. Developer reads LESSONS.md, implements code, writes Implementation Report.
-3. QA validates against Story §2 The Truth. If fail → Bug Report to Dev.
+2. Developer reads LESSONS.md, implements code, writes Implementation Report. CLI Orchestrator must run `./scripts/validate_report.mjs` on the report to enforce YAML strictness.
+3. QA validates against Story §2 The Truth. If fail → Bug Report to Dev. CLI Orchestrator must run `./scripts/validate_report.mjs` on the QA report before passing to Architect/Dev.
 4. Dev fixes and resubmits. 3+ failures → Escalated.
 5. Architect validates Safe Zone compliance and ADR adherence.
 6. DevOps merges story into sprint branch, validates, handles releases.
@@ -36,7 +37,7 @@ Before sprints: Lead triages request (L1 Trivial → Hotfix Path. L2-L4 → Epic
 6. DevOps (or Team Lead) runs `./scripts/hotfix_manager.sh sync` to update active worktrees.
 
 ### Phase 3: Review
-Sprint Report → Human review → Delivery Plan updated → Lessons recorded. If new features delivered → spawn Scribe agent to generate/update product_documentation/.
+Sprint Report → Human review → Delivery Plan updated → Lessons recorded. If new features delivered → spawn Scribe agent to generate/update vdocs/.
 
 ### Story States
 Draft → Refinement → Ready to Bounce → Bouncing → QA Passed → Architect Passed → Sprint Review → Done

package/brains/cursor-rules/vbounce-rules.mdc

@@ -14,13 +14,16 @@ alwaysApply: true
 ## During Implementation
 4. **Follow the Safe Zone**. No new patterns or libraries without Architect approval.
 5. **No Gold-Plating**. Implement exactly what the Story specifies. Extra features are defects.
-6. **Self-assess Correction Tax**. Track % human intervention needed.
+6. **Write Self-Documenting Code**. All exports MUST have JSDoc/docstrings to prevent RAG poisoning for future agents.
+7. **Self-assess Correction Tax**. Track % human intervention needed.
 
 ## After Implementation
-7. **Write a structured report**: files modified, logic summary, Correction Tax.
-8. **Flag lessons**. Gotchas and multi-attempt fixes get flagged for recording.
+8. **Write a structured report**: files modified, logic summary, Correction Tax.
+9. **Flag lessons**. Gotchas and multi-attempt fixes get flagged for recording.
 
 ## Always
-9. **Reports are the only handoff**. No direct agent-to-agent communication.
-10. **One source of truth**. Reference upstream documents, don't duplicate.
-11. **Change Logs are mandatory** on every document modification.
+10. **Reports are the only handoff**. No direct agent-to-agent communication.
+11. **One source of truth**. Reference upstream documents, don't duplicate.
+12. **Change Logs are mandatory** on every document modification.
+13. **Agent Reports MUST use YAML Frontmatter**. Every `.bounce/report/` generated must start with a strict `---` YAML block containing core status and metrics before the Markdown body.
+14. **Framework Integrity**. Any modification to a `brains/` or `skills/` file MUST be recorded in `brains/CHANGELOG.md` and trigger `./scripts/pre_bounce_sync.sh`.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sandrinio/vbounce",
-  "version": "1.3.2",
+  "version": "1.5.0",
   "description": "V-Bounce OS: Turn your AI coding assistant into a full engineering team through structured SDLC skills.",
   "type": "module",
   "bin": {
@@ -46,4 +46,4 @@
     "js-yaml": "^4.1.1",
     "marked": "^17.0.3"
   }
-}
+}

package/scripts/validate_report.mjs

@@ -14,19 +14,20 @@ import yaml from 'js-yaml';
 
 // Defined schemas for each report type
 const SCHEMAS = {
-    dev: ['status', 'correction_tax', 'tests_written', 'files_modified', 'lessons_flagged'],
+    dev: ['status', 'correction_tax', 'tokens_used', 'tests_written', 'files_modified', 'lessons_flagged'],
     qa: {
-        base: ['status', 'bounce_count', 'bugs_found', 'gold_plating_detected'],
+        base: ['status', 'bounce_count', 'tokens_used', 'bugs_found', 'gold_plating_detected'],
         conditional: { 'FAIL': ['failed_scenarios'] }
     },
     arch: {
-        base: ['status'],
+        base: ['status', 'tokens_used'],
         conditional: { 'PASS': ['safe_zone_score', 'ai_isms_detected', 'regression_risk'], 'FAIL': ['bounce_count', 'critical_failures'] }
     },
     devops: {
-        base: ['type', 'status'],
+        base: ['type', 'status', 'tokens_used'],
         conditional: { 'story-merge': ['conflicts_detected'], 'sprint-release': ['version'] }
-    }
+    },
+    scribe: ['mode', 'tokens_used', 'docs_created', 'docs_updated', 'docs_removed']
 };
 
 function extractFrontmatter(content) {
@@ -89,6 +90,7 @@ function main() {
     else if (filename.endsWith('-qa.md')) agentType = 'qa';
     else if (filename.endsWith('-arch.md')) agentType = 'arch';
     else if (filename.endsWith('-devops.md')) agentType = 'devops';
+    else if (filename.endsWith('-scribe.md')) agentType = 'scribe';
 
     if (agentType === 'unknown') {
         console.error(`WARNING: Unrecognized report type for ${filename}. Ensure filename ends in -dev.md, -qa.md, -arch.md, or -devops.md.`);
@@ -108,6 +110,10 @@ function main() {
         if (agentType === 'qa') validateQA(data);
         if (agentType === 'arch') validateArch(data);
         if (agentType === 'devops') validateDevops(data);
+        if (agentType === 'scribe') {
+            const missing = SCHEMAS.scribe.filter(k => !(k in data));
+            if (missing.length > 0) throw new Error(`SCRIBE_SCHEMA_ERROR: Missing required keys: ${missing.join(', ')}`);
+        }
 
         console.log(`VALID: ${filename} matches the ${agentType.toUpperCase()} schema.`);
         process.exit(0);

package/scripts/vbounce_index.mjs

@@ -82,7 +82,7 @@ async function indexFile(filePath, embedder) {
     else if (filePath.includes('ROADMAP.md')) type = 'adr';
     else if (filePath.includes('.bounce/reports')) type = 'report';
     else if (filePath.includes('product_plans')) type = 'plan';
-    else if (filePath.includes('product_documentation')) type = 'documentation';
+    else if (filePath.includes('vdocs')) type = 'documentation';
 
     const metadata = { file: basename, type };
     const chunks = chunkMarkdown(content, metadata);
@@ -147,7 +147,7 @@ async function main() {
         if (fs.existsSync('LESSONS.md')) filesToIndex.push('LESSONS.md');
         if (fs.existsSync('ROADMAP.md')) filesToIndex.push('ROADMAP.md');
         walkDir('product_plans');
-        walkDir('product_documentation');
+        walkDir('vdocs');
         walkDir('.bounce/reports');
     } else if (targetPath) {
         const stat = fs.statSync(targetPath);

package/scripts/verify_framework.mjs

@@ -20,27 +20,44 @@ const EXPECTED_PROMPT_SIGNATURES = {
     'developer.md': [
         'status:',
         'correction_tax:',
+        'tokens_used:',
+        'tests_written:',
         'files_modified:',
         'lessons_flagged:'
     ],
     'qa.md': [
         'status: "PASS"',
+        'bounce_count:',
         'bugs_found: 0',
+        'gold_plating_detected:',
         'status: "FAIL"',
+        'tokens_used:',
         'failed_scenarios:'
     ],
     'architect.md': [
         'status: "PASS"',
         'safe_zone_score:',
+        'ai_isms_detected:',
         'regression_risk:',
         'status: "FAIL"',
+        'bounce_count:',
+        'tokens_used:',
         'critical_failures:'
     ],
     'devops.md': [
         'type: "story-merge"',
+        'status:',
         'conflicts_detected:',
         'type: "sprint-release"',
+        'tokens_used:',
         'version:'
+    ],
+    'scribe.md': [
+        'mode:',
+        'tokens_used:',
+        'docs_created:',
+        'docs_updated:',
+        'docs_removed:'
     ]
 };