start-vibing 1.1.2 → 1.1.4

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "start-vibing",
-  "version": "1.1.2",
+  "version": "1.1.4",
   "description": "Setup Claude Code agents, skills, and hooks in your project. Smart copy that preserves your custom domains and configurations.",
   "type": "module",
   "bin": {

package/template/.claude/CLAUDE.md

@@ -1,168 +1,129 @@
-# Claude Development System - Agent Context
-
-This file provides context for all agents. For user-facing rules, see `/CLAUDE.md`.
-
----
-
-## System Architecture
-
-```
-.claude/
-├── agents/          # 11 specialized agents (READ before acting)
-├── skills/          # 8 skill systems with cache
-├── config/          # Project-specific configuration
-├── commands/        # Slash commands
-└── hooks/           # Security hooks
-```
-
----
-
-## Configuration Files
-
-Project-specific settings are in `.claude/config/`:
-
-| File                   | Purpose                              |
-| ---------------------- | ------------------------------------ |
-| `project-config.json`  | Stack, structure, commands           |
-| `domain-mapping.json`  | File patterns to domains             |
-| `quality-gates.json`   | Quality check commands               |
-| `testing-config.json`  | Test framework and conventions       |
-| `security-rules.json`  | Security audit rules                 |
-
-**RULE:** Agents MUST read config files before acting. Do NOT hardcode project specifics.
-
----
-
-## Agent → Skill Mapping
-
-| Agent            | Primary Skill      | Secondary                        |
-| ---------------- | ------------------ | -------------------------------- |
-| analyzer         | codebase-knowledge | -                                |
-| research         | research-cache     | codebase-knowledge               |
-| documenter       | docs-tracker       | codebase-knowledge               |
-| tester           | test-coverage      | -                                |
-| ui-ux-reviewer   | ui-ux-audit        | -                                |
-| security-auditor | security-scan      | -                                |
-| quality-checker  | quality-gate       | -                                |
-| final-validator  | final-check        | ALL                              |
-| commit-manager   | workflow-state     | docs-tracker, codebase-knowledge |
-| domain-updater   | codebase-knowledge | docs-tracker                     |
-
----
-
-## Execution Protocol
-
-### Before ANY implementation:
-
-1. **Start task** via `workflow-manager.py start-task --type [feature|fix|refactor] --description "..."`
-2. **Read config** from `.claude/config/` for project specifics
-3. Read relevant skill SKILL.md file
-4. Check skill cache for existing data
-5. Research if needed (web search)
-6. **Approve files** via `workflow-manager.py approve-files --files "path/to/file.ts"`
-
-### After implementation:
-
-1. Update skill cache with changes
-2. Run quality gates + record results
-3. Security audit (if auth/data involved)
-4. Final validation
-5. **Mark workflow ready** via `workflow-manager.py final-validation --result approved --ready-to-commit true`
-6. **Update domains** via domain-updater agent (BEFORE commit, keeps git clean)
-7. **Commit + complete task** via commit-manager agent (FINAL step, runs complete-task)
-
----
-
-## Workflow State Tracking
-
-Location: `.claude/workflow-state.json`
-
-### CLI Commands (MANDATORY)
-
-```bash
-# 1. Start task (MUST be first)
-python .claude/hooks/workflow-manager.py start-task --type feature --description "..."
-
-# 2. After analyzer approves, register files
-python .claude/hooks/workflow-manager.py approve-files --files "src/*.ts"
-
-# 3. After each agent
-python .claude/hooks/workflow-manager.py agent-executed --agent [name] --result approved
-
-# 4. After quality gates
-python .claude/hooks/workflow-manager.py quality-gate --gate [typecheck|lint|build] --passed true
-
-# 5. Final validation
-python .claude/hooks/workflow-manager.py final-validation --result approved --ready-to-commit true
-
-# 6. After commit
-python .claude/hooks/workflow-manager.py complete-task --commit-hash [hash]
-```
-
-### Hooks Enforcement
-
-- **PreToolUse**: Blocks file edits if task not started or file not approved
-- **PostToolUse**: Auto-tracks all file modifications
-- **Stop**: Blocks session end if workflow incomplete
-- **Husky**: Blocks commit if validation failed
-
----
-
-## VETO Power Agents
-
-These agents CAN and MUST stop the flow if rules are violated:
-
-| Agent                | Blocks When                                        |
-| -------------------- | -------------------------------------------------- |
-| **security-auditor** | User ID from request, sensitive data, no validation |
-| **final-validator**  | Any rule violated, tests failing, docs missing      |
-
----
-
-## Quality Requirements
-
-All implementations MUST:
-
-- [ ] Pass typecheck (command from config)
-- [ ] Pass lint (command from config)
-- [ ] Pass unit tests (command from config)
-- [ ] Pass E2E tests (command from config)
-- [ ] Pass build (command from config)
-- [ ] Have E2E tests with real auth
-- [ ] Have documentation in `docs/`
-- [ ] Be security audited
-- [ ] Be committed with conventional commits
-- [ ] Have domains updated with session learnings
-
----
-
-## Domain Updater Agent
-
-The **domain-updater** runs BEFORE commit-manager to ensure git stays clean.
-
-### Purpose
-
-- Document **problems encountered** during the session
-- Record **solutions** applied to fix issues
-- Add **prevention tips** for future sessions
-- Update **attention points** with new learnings
-- Keep domain knowledge **current and accurate**
-
-### Trigger
-
-Runs automatically:
-1. After final-validator approves in any workflow
-2. BEFORE commit-manager (so changes are included in commit)
-3. Stop hook blocks session end until domain-updater executes (if files were modified)
-
-### Workflow Order
-
-```
-final-validator → domain-updater → commit-manager → complete-task
-                       ↑                    ↑
-              (updates domains)    (commits all + archives)
-```
-
-### Configuration
-
-Reads domain patterns from `.claude/config/domain-mapping.json`
+# Claude Development System - Agent Context
+
+This file provides context for all agents. For user-facing rules, see `/CLAUDE.md`.
+
+---
+
+## System Architecture
+
+```
+.claude/
+├── agents/          # 11 specialized agents (READ before acting)
+├── skills/          # 8 skill systems with cache
+├── config/          # Project-specific configuration
+├── commands/        # Slash commands
+└── hooks/           # Security hooks
+```
+
+---
+
+## Configuration Files
+
+Project-specific settings are in `.claude/config/`:
+
+| File                   | Purpose                              |
+| ---------------------- | ------------------------------------ |
+| `project-config.json`  | Stack, structure, commands           |
+| `domain-mapping.json`  | File patterns to domains             |
+| `quality-gates.json`   | Quality check commands               |
+| `testing-config.json`  | Test framework and conventions       |
+| `security-rules.json`  | Security audit rules                 |
+
+**RULE:** Agents MUST read config files before acting. Do NOT hardcode project specifics.
+
+---
+
+## Agent → Skill Mapping
+
+| Agent            | Primary Skill      | Secondary                        |
+| ---------------- | ------------------ | -------------------------------- |
+| analyzer         | codebase-knowledge | -                                |
+| research         | research-cache     | codebase-knowledge               |
+| documenter       | docs-tracker       | codebase-knowledge               |
+| tester           | test-coverage      | -                                |
+| ui-ux-reviewer   | ui-ux-audit        | -                                |
+| security-auditor | security-scan      | -                                |
+| quality-checker  | quality-gate       | -                                |
+| final-validator  | final-check        | ALL                              |
+| commit-manager   | workflow-state     | docs-tracker, codebase-knowledge |
+| domain-updater   | codebase-knowledge | docs-tracker                     |
+
+---
+
+## Execution Protocol
+
+### Before ANY implementation:
+1. **Read config** from `.claude/config/` for project specifics
+2. Read relevant skill SKILL.md file
+3. Check skill cache for existing data
+4. Research if needed (web search)
+
+### After implementation:
+
+1. Update skill cache with changes
+2. Run quality gates + record results
+3. Security audit (if auth/data involved)
+4. Final validation
+5. **Update domains** via domain-updater agent (BEFORE commit, keeps git clean)
+6. **Commit** via commit-manager agent (FINAL step)
+
+---
+
+## VETO Power Agents
+
+These agents CAN and MUST stop the flow if rules are violated:
+
+| Agent                | Blocks When                                        |
+| -------------------- | -------------------------------------------------- |
+| **security-auditor** | User ID from request, sensitive data, no validation |
+| **final-validator**  | Any rule violated, tests failing, docs missing      |
+
+---
+
+## Quality Requirements
+
+All implementations MUST:
+
+- [ ] Pass typecheck (command from config)
+- [ ] Pass lint (command from config)
+- [ ] Pass unit tests (command from config)
+- [ ] Pass E2E tests (command from config)
+- [ ] Pass build (command from config)
+- [ ] Have E2E tests with real auth
+- [ ] Have documentation in `docs/`
+- [ ] Be security audited
+- [ ] Be committed with conventional commits
+- [ ] Have domains updated with session learnings
+
+---
+
+## Domain Updater Agent
+
+The **domain-updater** runs BEFORE commit-manager to ensure git stays clean.
+
+### Purpose
+
+- Document **problems encountered** during the session
+- Record **solutions** applied to fix issues
+- Add **prevention tips** for future sessions
+- Update **attention points** with new learnings
+- Keep domain knowledge **current and accurate**
+
+### Trigger
+
+Runs automatically:
+1. After final-validator approves in any workflow
+2. BEFORE commit-manager (so changes are included in commit)
+3. Stop hook blocks session end until domain-updater executes (if files were modified)
+
+### Workflow Order
+
+```
+final-validator → domain-updater → commit-manager → complete-task
+                       ↑                    ↑
+              (updates domains)    (commits all + archives)
+```
+
+### Configuration
+
+Reads domain patterns from `.claude/config/domain-mapping.json`

package/template/.claude/agents/analyzer.md

@@ -27,20 +27,6 @@ You analyze the impact of any change before implementation begins.
     - Attention points (already identified!)
 4. **APPROVE FILES** for modification (see below)
 
-## WORKFLOW STATE TRACKING
-
-Run these commands automatically after analysis:
-
-```bash
-# 1. Mark analyzer as executed
-python .claude/hooks/workflow-manager.py agent-executed --agent analyzer --result approved
-
-# 2. Approve files that can be modified
-python .claude/hooks/workflow-manager.py approve-files --files "path/to/file1.ts" "path/to/file2.tsx" "src/feature/*"
-```
-
-**CRITICAL:** Without running `approve-files`, the hooks will BLOCK all Edit/Write operations!
-
 ## Research Requirement
 
 For changes affecting architecture:

package/template/.claude/agents/commit-manager.md

@@ -34,25 +34,6 @@ If any item is NO, **DO NOT COMMIT**.
 
 Run these commands automatically during commit process:
 
-### Before Commit - Verify State
-
-```bash
-python .claude/hooks/workflow-manager.py status
-```
-
-### After Commit Success
-
-```bash
-# Get the commit hash
-COMMIT_HASH=$(git log -1 --format="%h")
-
-# Mark commit-manager as executed
-python .claude/hooks/workflow-manager.py agent-executed --agent commit-manager --result approved --notes "Commit: $COMMIT_HASH"
-
-# Complete the workflow (FINAL STEP)
-python .claude/hooks/workflow-manager.py complete-task --commit-hash $COMMIT_HASH
-```
-
 **IMPORTANT:** commit-manager is the FINAL agent. The correct flow is:
 
 ```

package/template/.claude/agents/documenter.md

@@ -16,16 +16,6 @@ You create and maintain all documentation.
 > - `.claude/skills/docs-tracker/SKILL.md` - Detection and update rules
 > - `.claude/config/domain-mapping.json` - File-to-domain mapping
 
-## WORKFLOW STATE TRACKING
-
-Run this command automatically after documenting:
-
-```bash
-python .claude/hooks/workflow-manager.py agent-executed --agent documenter --result approved --notes "Updated domain X, changelog, flow docs"
-```
-
-Note: Documentation files are auto-tracked by PostToolUse hook when created/modified.
-
 ## Responsibilities
 
 1. **Detect** changed files via git diff