@arvorco/relentless 0.1.20 → 0.1.22

package/.claude/commands/relentless.implement.md

@@ -1,15 +1,42 @@
 ---
-description: Execute implementation workflow phase by phase.
+description: Execute implementation workflow for a feature manually, story by story.
 ---
 
 Load the implement skill and begin systematic implementation.
 
+**Usage:** `/relentless.implement [story-id]`
+
 **Context:** $ARGUMENTS
 
-The implement skill will:
-1. Guide you through implementing tasks in dependency order
-2. Track progress per user story
-3. Ensure quality gates are met
-4. Update progress.txt with learnings
+The implement skill will guide you through:
+
+1. **TDD Workflow** - Tests first, then implementation
+2. **Quality Gates** - typecheck, lint, test must all pass
+3. **File Updates** - tasks.md, checklist.md, prd.json, progress.txt
+4. **Dependency Order** - Stories implemented in correct sequence
+
+## Quick Start
+
+1. Ensure you have all artifacts: spec.md, plan.md, tasks.md, checklist.md, prd.json
+2. Run `/relentless.analyze` first (must pass with no CRITICAL issues)
+3. Run `/relentless.implement` to start with the next available story
+4. Or run `/relentless.implement US-003` to implement a specific story
+
+## What Gets Updated
+
+After each story:
+- `tasks.md` - Acceptance criteria checked off
+- `checklist.md` - Verified items checked off
+- `prd.json` - Story marked as `passes: true`
+- `progress.txt` - Progress entry with learnings
+
+## Prerequisites
+
+- `/relentless.analyze` must pass
+- All feature artifacts must exist
+- Constitution and prompt.md reviewed
+
+## See Also
 
-Prerequisites: /relentless.analyze must pass (no CRITICAL issues)
+- `relentless run` - Automated orchestration (runs agents automatically)
+- `/relentless.analyze` - Check artifact consistency before implementing

package/.claude/skills/implement/SKILL.md

@@ -5,137 +5,238 @@ description: "Execute implementation workflow phase by phase. Use after analysis
 
 # Implementation Workflow Executor
 
-Guide systematic implementation of features using the task breakdown.
+Guide systematic implementation of features using TDD and quality-first approach.
 
 ---
 
 ## The Job
 
-Guide user through implementing tasks in correct order following dependencies.
+Implement user stories one at a time, following strict TDD and updating all tracking files.
 
 ---
 
-## Prerequisites
+## Before You Start
 
-Before starting:
-- `/relentless.analyze` must pass (no CRITICAL issues)
-- All artifacts exist (spec, plan, tasks, checklist)
-- Constitution reviewed
+1. **Read the Constitution** - Review `relentless/constitution.md` for project principles
+2. **Read prompt.md** - Review `relentless/prompt.md` for workflow guidelines
+3. **Read progress.txt** - Check learnings from previous iterations
+4. **Review artifacts** - Ensure spec.md, plan.md, tasks.md, checklist.md exist
+5. **Run `/relentless.analyze`** - Must pass with no CRITICAL issues
 
 ---
 
-## Implementation Flow
+## CRITICAL: Quality Gates (Non-Negotiable)
 
-### Phase 0: Setup
-1. Review `tasks.md` for setup tasks
-2. Install dependencies
-3. Create directory structure
-4. Initialize configuration
+Before marking ANY story as complete, ALL checks must pass:
 
-### Phase 1: Foundation
-1. Implement data models
-2. Create base utilities
-3. Set up infrastructure
-4. Tests for foundation
+```bash
+# TypeScript strict mode check
+bun run typecheck
 
-### Phase 2: User Stories
-For each story in dependency order:
-1. Read story acceptance criteria
-2. Implement functionality
-3. Write tests
-4. Run quality checks (typecheck, lint)
-5. Verify against checklist
-6. Commit changes
-7. Mark story complete in prd.json
+# ESLint with zero warnings policy
+bun run lint
 
-### Phase 3: Polish
-1. Performance optimization
-2. Error handling improvements
-3. Documentation
-4. Final quality checks
+# All tests must pass
+bun test
+```
+
+**If ANY check fails, DO NOT mark the story as complete. Fix the issues first.**
 
 ---
 
-## Per-Story Workflow
+## TDD Workflow (MANDATORY)
 
-```markdown
-**Current:** US-001: Create User Registration Endpoint
+For EVERY story, follow strict Test-Driven Development:
 
-**Acceptance Criteria:**
-- [ ] POST /api/auth/register endpoint exists
-- [ ] Email validation works
-- [ ] Password requirements enforced
-- [ ] Password hashed before storage
-- [ ] Confirmation email sent
-- [ ] Returns 201 with user ID
-- [ ] Returns 400 for invalid input
-- [ ] Typecheck passes
-- [ ] Tests pass
-
-**Checklist Items:**
-- CHK-001: User table created
-- CHK-006: Password hashing uses bcrypt
-- CHK-011: Returns correct status codes
-
-**Steps:**
-1. Create endpoint handler
-2. Implement validation
-3. Add password hashing
-4. Integrate email service
-5. Write unit tests
-6. Write integration tests
-7. Run typecheck
-8. Run tests
-9. Verify checklist items
-10. Commit with message: "feat: US-001 - Create User Registration Endpoint"
+### Step 1: Write Failing Tests First (RED)
+```bash
+# Create test file if needed
+# Write tests that define expected behavior
+bun test  # Tests MUST fail initially
 ```
 
----
+### Step 2: Implement Minimum Code (GREEN)
+```bash
+# Write only enough code to pass tests
+bun test  # Tests MUST pass
+```
 
-## Quality Gates
+### Step 3: Refactor
+```bash
+# Clean up while keeping tests green
+bun test  # Tests MUST still pass
+```
 
-Before marking story complete:
-- [ ] All acceptance criteria checked
-- [ ] Typecheck passes
-- [ ] Linter passes
-- [ ] Tests pass
-- [ ] Relevant checklist items verified
-- [ ] Code committed
+**Do NOT skip TDD. Tests are contracts that validate your implementation.**
 
 ---
 
-## Progress Tracking
+## Per-Story Implementation Flow
+
+For each story (in dependency order):
+
+### 1. Identify the Story
+- Read `prd.json` to find the next story where `passes: false`
+- Check dependencies are met (dependent stories have `passes: true`)
+- Read the story's acceptance criteria
+
+### 2. Find Relevant Checklist Items
+- Open `checklist.md`
+- Find items tagged with `[US-XXX]` for this story
+- Note constitution compliance items `[Constitution]`
 
-Update `progress.txt` after each story:
+### 3. Implement with TDD
+Follow the TDD workflow above for each acceptance criterion.
 
+### 4. Update tasks.md
+As you complete each criterion:
 ```markdown
-## 2026-01-11 - US-001
-- Implemented user registration endpoint
-- Added email validation and password hashing
-- Email service integration working
-- All tests passing
+# Change from:
+- [ ] Criterion text
 
-**Learnings:**
-- Bcrypt cost factor 12 provides good balance
-- Email validation regex from validator.js works well
-- Nodemailer setup straightforward
+# To:
+- [x] Criterion text
+```
+
+### 5. Update checklist.md
+For each verified checklist item:
+```markdown
+# Change from:
+- [ ] CHK-XXX [US-001] Description
+
+# To:
+- [x] CHK-XXX [US-001] Description
+```
+
+### 6. Run Quality Checks
+```bash
+bun run typecheck  # 0 errors required
+bun run lint       # 0 warnings required
+bun test           # All tests must pass
+```
+
+### 7. Commit Changes
+```bash
+git add -A
+git commit -m "feat: US-XXX - Story Title"
+```
+
+### 8. Update prd.json
+Set the story's `passes` field to `true`:
+```json
+{
+  "id": "US-001",
+  "title": "...",
+  "passes": true,  // <- Change from false to true
+  ...
+}
+```
+
+### 9. Update progress.txt
+Append progress entry:
+```markdown
+## [Date] - US-XXX: Story Title
+
+**Implemented:**
+- What was built
+- Key decisions made
 
 **Files Changed:**
-- src/api/auth/register.ts (new)
-- src/services/user.service.ts (new)
-- src/utils/password.ts (new)
-- tests/auth/register.test.ts (new)
+- path/to/file.ts (new/modified)
+
+**Tests Added:**
+- path/to/file.test.ts
+
+**Learnings:**
+- Patterns discovered
+- Gotchas encountered
+
+**Constitution Compliance:**
+- Principle N: How it was followed
+
+---
+```
 
 ---
+
+## Example Per-Story Workflow
+
+```markdown
+**Current:** US-001: Test Infrastructure Setup
+
+**Acceptance Criteria:**
+- [ ] `bun test` command runs successfully
+- [ ] Test files with pattern `*.test.ts` are auto-discovered
+- [ ] `bun test --coverage` shows coverage report
+- [ ] Typecheck passes
+- [ ] Lint passes
+
+**Relevant Checklist Items:**
+- [ ] CHK-001 [US-001] `bun test` command executes successfully
+- [ ] CHK-002 [US-001] Test files with `*.test.ts` pattern are auto-discovered
+- [ ] CHK-007 [Constitution] Tests written BEFORE implementation
+
+**Implementation Steps:**
+1. Write a simple failing test first
+2. Configure bun test runner
+3. Verify test discovery works
+4. Run `bun run typecheck` - must pass
+5. Run `bun run lint` - must pass with 0 warnings
+6. Update tasks.md - check off completed criteria
+7. Update checklist.md - mark verified items
+8. Commit: "feat: US-001 - Test Infrastructure Setup"
+9. Update prd.json: set passes: true
+10. Update progress.txt with learnings
 ```
 
 ---
 
+## File Update Summary
+
+After completing each story, these files MUST be updated:
+
+| File | Update |
+|------|--------|
+| `tasks.md` | Check off `- [x]` completed acceptance criteria |
+| `checklist.md` | Check off `- [x]` verified checklist items |
+| `prd.json` | Set `"passes": true` for the story |
+| `progress.txt` | Append progress entry with learnings |
+
+---
+
+## Implementation Phases
+
+### Phase 0: Setup
+- Infrastructure, tooling, configuration
+- Usually US-001 type stories
+
+### Phase 1: Foundation
+- Data models, types, schemas
+- Base utilities and helpers
+- Core infrastructure
+
+### Phase 2: User Stories
+- Feature implementation
+- Follow dependency order strictly
+
+### Phase 3: Polish
+- E2E tests
+- Documentation
+- Performance optimization
+
+---
+
 ## Notes
 
 - Work on ONE story at a time
-- Follow dependency order
-- Don't skip quality checks
-- Commit frequently
-- Update progress after each story
-- This is a guided workflow, not automated
+- Follow dependency order strictly
+- Never skip TDD - tests come FIRST
+- Never skip quality checks
+- Commit after each story
+- Update ALL tracking files
+- This is a guided workflow for manual implementation
+
+---
+
+*Reference: See `relentless/prompt.md` for additional guidelines*
+*Reference: See `relentless/constitution.md` for project principles*

package/CHANGELOG.md

@@ -0,0 +1,269 @@
+# Changelog
+
+All notable changes to Relentless will be documented in this file.
+
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
+and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [Unreleased]
+
+## [0.1.20] - 2026-01-13
+
+### Added
+- Constitution skill now creates **both** `constitution.md` AND `prompt.md` in one command
+- Personalized `prompt.md` generation based on project structure analysis
+- Automatic detection of quality commands from `package.json`
+- Project-specific patterns extraction from README, AGENTS.md, and other docs
+- TDD workflow guidance when tests are detected
+
+### Changed
+- **BREAKING WORKFLOW**: `/relentless.constitution` now generates both constitution and prompt files
+- Simplified generic `prompt.md` template from ~3.5KB to ~1KB
+- Updated README with new simplified workflow (init → constitution → specify)
+- Removed separate `/relentless.prompt` skill (now integrated into constitution)
+
+### Fixed
+- Generic prompt template now properly encourages personalization
+- Documentation now correctly reflects the simplified workflow
+
+## [0.1.19] - 2026-01-12
+
+### Added
+- Dynamic story grid sizing based on terminal height
+- Automatic calculation of available space for story display
+- All stories now visible on large terminals (63+ rows)
+
+### Changed
+- Story grid adapts to terminal size automatically
+- Removed static 8-row limitation
+- Improved space utilization (shows 40+ story rows on large terminals)
+
+### Fixed
+- Hidden stories issue (only 16 of 23 stories were visible)
+- Story grid now scales properly with terminal size
+
+## [0.1.18] - 2026-01-12
+
+### Added
+- Rich story information display in TUI
+- Priority badges with color coding (P1-P2 red, P3-P5 yellow, P6+ gray)
+- Acceptance criteria count indicator `(Nc)` per story
+- Research indicator emoji (🔍) for stories requiring investigation
+- Phase badges showing story phase (Setup, Foundation, Stories, Polish)
+
+### Changed
+- Story titles now show 40 characters (increased from 25, 60% more context)
+- Enhanced Story type with priority, criteriaCount, research, and phase fields
+- Improved visual hierarchy with better use of available terminal width
+
+### Fixed
+- **CRITICAL**: TUI rendering artifacts completely resolved
+- Removed all bordered components causing Ink reconciliation issues
+- Simplified layout with text separators instead of borders (`── Title ──`)
+- No more repeated empty borders or overlapping text
+
+## [0.1.17] - 2026-01-12
+
+### Fixed
+- TUI scroll artifacts by constraining UI height to terminal dimensions
+- Added terminal height awareness via `stdout.rows`
+- Prevented UI from exceeding available terminal space
+
+## [0.1.16] - 2026-01-12
+
+### Fixed
+- Terminal clearing before TUI start to prevent rendering artifacts
+- Added ANSI escape codes to clear screen before Ink rendering
+
+## [0.1.15] - 2026-01-12
+
+### Fixed
+- Newline rendering issues in TUI output
+- Enhanced `addOutput()` to split and clean embedded newlines
+- Removed `\n` prefixes from iteration messages
+
+## [0.1.14] - 2026-01-12
+
+### Fixed
+- Empty line padding in TUI AgentOutput component
+- Removed blank line padding that created visual artifacts
+
+## [0.1.13] - 2026-01-12
+
+### Added
+- Checklist support in orchestration loop
+- `checklist.md` now loaded and included in agent prompts
+- Quality gates automatically presented to agents during execution
+
+### Changed
+- Agent prompts now include quality checklist after plan.md
+- Improved guidance for agents with project-specific quality requirements
+
+## [0.1.12] - 2026-01-12
+
+### Fixed
+- **CRITICAL**: Bash scripts now included in npm package
+- Changed `.npmignore` from `scripts/` to `/scripts/` to only exclude root directory
+- `/relentless.specify` command now works correctly (was failing with "script not found")
+- Package now includes 5 essential bash scripts (47KB total)
+
+## [0.1.11] - 2026-01-12
+
+### Changed
+- Repository cleanup: Removed ~170KB of obsolete files
+- Removed obsolete `.specify/` directory (92KB)
+- Removed duplicate `skills/` directory at root (64KB)
+- Removed obsolete scripts: `ralph.sh`, `prompt.md`, `prd.json.example`
+- Cleaned up `.npmignore` references to removed files
+
+### Fixed
+- Professional, lean codebase with clear structure
+
+## [0.1.10] - 2026-01-11
+
+### Fixed
+- Version display now reads from `package.json` dynamically
+- `relentless --version` now syncs automatically with releases
+- Removed hardcoded version string
+
+## [0.1.9] - 2026-01-11
+
+### Fixed
+- **CRITICAL**: `.claude/skills/` directory now included in npm package
+- Added negation patterns to `.npmignore`: `!.claude/`, `!.claude/skills/`, `!.claude/commands/`
+- `/relentless.constitution` and other skills now work after npm install
+- Package grew from 54KB to 76KB with skills included
+
+## [0.1.8] - 2026-01-11
+
+### Added
+- `--force` flag to `init` command for reinstalling/updating files
+- Ability to overwrite existing relentless files with latest versions
+
+### Fixed
+- Improved path resolution for global installations
+- Better error handling and diagnostics in init command
+
+## [0.1.7] - 2026-01-11
+
+### Changed
+- Renamed "Legacy" to "Ralph Wiggum Method" in documentation
+
+### Fixed
+- Updated constitution command to use `.claude/skills/` paths
+- Updated specify command to use new paths
+- Removed obsolete `plan.old.md` command file
+
+## [0.1.6] - 2026-01-11
+
+### Fixed
+- GitHub Actions: Added contents write permission for GitHub releases
+- Updated to modern GitHub release action syntax
+
+## [0.1.5] - 2026-01-11
+
+### Changed
+- Stopped tracking `package-lock.json` (npm package best practice)
+
+## [0.1.4] - 2026-01-11
+
+### Fixed
+- Package-lock.json updates for consistency
+
+## [0.1.2] - 2026-01-11
+
+### Fixed
+- Corrected bin path in `package.json`
+- Fixed GitHub Actions workflow syntax
+
+## [0.1.1] - 2026-01-11
+
+### Fixed
+- Initial bug fixes for npm publishing
+
+## [0.1.0] - 2026-01-10
+
+### Added - Initial Release
+
+**Core Features:**
+- Universal AI agent orchestrator supporting Claude Code, Amp, OpenCode, Codex, Droid, and Gemini
+- Single binary installation with PATH setup
+- Beautiful TUI interface with real-time progress tracking
+- Intelligent agent fallback and rate limit detection
+- Auto-recovery when rate limits reset
+
+**Specification & Planning (Relentless Commands):**
+- `/relentless.constitution` - Create project principles and governance
+- `/relentless.specify` - Interactive feature specification from natural language
+- `/relentless.plan` - Generate technical implementation plans
+- `/relentless.tasks` - Create hierarchical task breakdown (4-phase structure)
+- `/relentless.checklist` - Generate quality validation checklists
+- `/relentless.clarify` - Interactive ambiguity resolution
+
+**Task Management:**
+- Dependency-ordered execution with circular dependency detection
+- Parallel task markers for concurrent execution
+- Phase-based planning (Setup → Foundation → Stories → Polish)
+- Research phase support for investigation tasks
+
+**CLI Commands:**
+- `relentless init` - Initialize project structure
+- `relentless run` - Execute orchestration loop
+- `relentless convert` - Convert markdown PRDs to JSON
+- `relentless features` - Manage feature directories
+- `relentless analyze` - Cross-artifact consistency checking
+- `relentless issues create` - Generate GitHub issues from stories
+
+**Skills System:**
+- Multi-tier agent support (Full/Extensions/Manual)
+- Skills auto-installation for Claude Code, Amp, OpenCode
+- Manual workflow support for Droid, Codex, Gemini
+
+**Documentation:**
+- Comprehensive README with quick start guides
+- Agent-specific workflow documentation
+- Architecture documentation
+- MIT License
+
+---
+
+## Evolution from Ralph Wiggum
+
+Relentless evolved from the [Ralph Wiggum Pattern](https://ghuntley.com/ralph/) created by Geoffrey Huntley. Key innovations:
+
+- **Multi-agent support** - Works with any AI coding agent, not just Claude
+- **Skills system** - Native commands instead of manual prompt engineering  
+- **Beautiful TUI** - Real-time visualization vs text-only output
+- **Intelligent fallback** - Automatic agent switching on rate limits
+- **Structured workflow** - Constitution → Specify → Plan → Tasks → Run
+
+---
+
+## Links
+
+- **GitHub**: https://github.com/ArvorCo/Relentless
+- **npm Package**: https://www.npmjs.com/package/@arvorco/relentless
+- **License**: MIT
+- **Inspiration**: [Ralph Wiggum Pattern](https://ghuntley.com/ralph/) by Geoffrey Huntley
+
+[Unreleased]: https://github.com/ArvorCo/Relentless/compare/v0.1.20...HEAD
+[0.1.20]: https://github.com/ArvorCo/Relentless/compare/v0.1.19...v0.1.20
+[0.1.19]: https://github.com/ArvorCo/Relentless/compare/v0.1.18...v0.1.19
+[0.1.18]: https://github.com/ArvorCo/Relentless/compare/v0.1.17...v0.1.18
+[0.1.17]: https://github.com/ArvorCo/Relentless/compare/v0.1.16...v0.1.17
+[0.1.16]: https://github.com/ArvorCo/Relentless/compare/v0.1.15...v0.1.16
+[0.1.15]: https://github.com/ArvorCo/Relentless/compare/v0.1.14...v0.1.15
+[0.1.14]: https://github.com/ArvorCo/Relentless/compare/v0.1.13...v0.1.14
+[0.1.13]: https://github.com/ArvorCo/Relentless/compare/v0.1.12...v0.1.13
+[0.1.12]: https://github.com/ArvorCo/Relentless/compare/v0.1.11...v0.1.12
+[0.1.11]: https://github.com/ArvorCo/Relentless/compare/v0.1.10...v0.1.11
+[0.1.10]: https://github.com/ArvorCo/Relentless/compare/v0.1.9...v0.1.10
+[0.1.9]: https://github.com/ArvorCo/Relentless/compare/v0.1.8...v0.1.9
+[0.1.8]: https://github.com/ArvorCo/Relentless/compare/v0.1.7...v0.1.8
+[0.1.7]: https://github.com/ArvorCo/Relentless/compare/v0.1.6...v0.1.7
+[0.1.6]: https://github.com/ArvorCo/Relentless/compare/v0.1.5...v0.1.6
+[0.1.5]: https://github.com/ArvorCo/Relentless/compare/v0.1.4...v0.1.5
+[0.1.4]: https://github.com/ArvorCo/Relentless/compare/v0.1.2...v0.1.4
+[0.1.2]: https://github.com/ArvorCo/Relentless/compare/v0.1.1...v0.1.2
+[0.1.1]: https://github.com/ArvorCo/Relentless/compare/v0.1.0...v0.1.1
+[0.1.0]: https://github.com/ArvorCo/Relentless/releases/tag/v0.1.0

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@arvorco/relentless",
-  "version": "0.1.20",
+  "version": "0.1.22",
   "description": "Universal AI agent orchestrator - works with Claude Code, Amp, OpenCode, Codex, Droid, and Gemini",
   "type": "module",
   "publishConfig": {