@arvorco/relentless 0.1.23 → 0.1.26

package/.claude/skills/constitution/SKILL.md

@@ -90,7 +90,11 @@ Read and analyze project documentation:
 
 ## Step 4: Generate Personalized Prompt
 
-Using the generic template from relentless, create a personalized `prompt.md` with:
+Load the base template from `templates/prompt.md` and personalize it:
+
+**Base Template Location:** `templates/prompt.md`
+
+Create a personalized `prompt.md` with:
 
 **Section 1: Quality Gates**
 ```markdown

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

@@ -7,6 +7,11 @@ description: "Execute implementation workflow phase by phase. Use after analysis
 
 Guide systematic implementation of features using TDD and quality-first approach.
 
+> **Note:** This skill uses generic placeholders. Adapt commands and paths to your project:
+> - Quality commands: Check your `package.json`, `Makefile`, or build config
+> - File paths: Adjust based on your project structure
+> - Examples show common conventions - your project may differ
+
 ---
 
 ## The Job
@@ -17,27 +22,32 @@ Implement user stories one at a time, following strict TDD and updating all trac
 
 ## Before You Start
 
-1. **Read the Constitution** - Review `relentless/constitution.md` for project principles
-2. **Read prompt.md** - Review `relentless/prompt.md` for workflow guidelines
+1. **Read the Constitution** - Review your project's constitution (if exists) for governance principles
+2. **Read prompt.md** - Review workflow guidelines (if exists)
 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
+5. **Identify Quality Commands** - Find your project's typecheck, lint, and test commands
 
 ---
 
 ## CRITICAL: Quality Gates (Non-Negotiable)
 
-Before marking ANY story as complete, ALL checks must pass:
+Before marking ANY story as complete, ALL quality checks must pass.
+
+**Find your project's commands** (examples for different ecosystems):
 
 ```bash
-# TypeScript strict mode check
-bun run typecheck
+# JavaScript/TypeScript (npm/yarn/bun/pnpm):
+npm run typecheck && npm run lint && npm test
 
-# ESLint with zero warnings policy
-bun run lint
+# Python:
+mypy . && ruff check . && pytest
 
-# All tests must pass
-bun test
+# Go:
+go build ./... && golangci-lint run && go test ./...
+
+# Rust:
+cargo check && cargo clippy && cargo test
 ```
 
 **If ANY check fails, DO NOT mark the story as complete. Fix the issues first.**
@@ -52,19 +62,19 @@ For EVERY story, follow strict Test-Driven Development:
 ```bash
 # Create test file if needed
 # Write tests that define expected behavior
-bun test  # Tests MUST fail initially
+# Run your test command - tests MUST fail initially
 ```
 
 ### Step 2: Implement Minimum Code (GREEN)
 ```bash
 # Write only enough code to pass tests
-bun test  # Tests MUST pass
+# Run tests - they MUST pass now
 ```
 
 ### Step 3: Refactor
 ```bash
 # Clean up while keeping tests green
-bun test  # Tests MUST still pass
+# Run tests - they MUST still pass
 ```
 
 **Do NOT skip TDD. Tests are contracts that validate your implementation.**
@@ -83,7 +93,7 @@ For each story (in dependency order):
 ### 2. Find Relevant Checklist Items
 - Open `checklist.md`
 - Find items tagged with `[US-XXX]` for this story
-- Note constitution compliance items `[Constitution]`
+- Note any governance/compliance items
 
 ### 3. Implement with TDD
 Follow the TDD workflow above for each acceptance criterion.
@@ -110,9 +120,8 @@ For each verified checklist item:
 
 ### 6. Run Quality Checks
 ```bash
-bun run typecheck  # 0 errors required
-bun run lint       # 0 warnings required
-bun test           # All tests must pass
+# Run your project's quality commands
+# All must pass with 0 errors/warnings
 ```
 
 ### 7. Commit Changes
@@ -142,18 +151,15 @@ Append progress entry:
 - Key decisions made
 
 **Files Changed:**
-- path/to/file.ts (new/modified)
+- path/to/file (new/modified)
 
 **Tests Added:**
-- path/to/file.test.ts
+- path/to/test.file
 
 **Learnings:**
 - Patterns discovered
 - Gotchas encountered
 
-**Constitution Compliance:**
-- Principle N: How it was followed
-
 ---
 ```
 
@@ -165,23 +171,23 @@ Append progress entry:
 **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
+- [ ] Test command runs successfully
+- [ ] Test files are auto-discovered
+- [ ] Coverage report available
+- [ ] Type checking passes
+- [ ] Linting 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
+- [ ] CHK-001 [US-001] Test command executes successfully
+- [ ] CHK-002 [US-001] Test files are auto-discovered
+- [ ] CHK-007 Tests written BEFORE implementation
 
 **Implementation Steps:**
 1. Write a simple failing test first
-2. Configure bun test runner
+2. Configure test runner for your project
 3. Verify test discovery works
-4. Run `bun run typecheck` - must pass
-5. Run `bun run lint` - must pass with 0 warnings
+4. Run type checking - must pass
+5. Run linting - 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"
@@ -238,5 +244,4 @@ After completing each story, these files MUST be updated:
 
 ---
 
-*Reference: See `relentless/prompt.md` for additional guidelines*
-*Reference: See `relentless/constitution.md` for project principles*
+*Adapt all commands and paths to your project's specific setup*

package/.claude/skills/relentless/SKILL.md

@@ -237,18 +237,21 @@ After creating relentless/prd.json, run the orchestrator:
 
 ```bash
 # With Claude Code (default)
-./relentless/bin/relentless.sh
+relentless run --feature <feature-name>
 
 # With a specific agent
-./relentless/bin/relentless.sh --agent amp
-./relentless/bin/relentless.sh --agent codex
-./relentless/bin/relentless.sh --agent gemini
+relentless run --feature <feature-name> --agent amp
+relentless run --feature <feature-name> --agent codex
+relentless run --feature <feature-name> --agent gemini
 
 # Smart routing (auto-select best agent per story)
-./relentless/bin/relentless.sh --agent auto
+relentless run --feature <feature-name> --agent auto
 
 # Custom max iterations
-./relentless/bin/relentless.sh --max-iterations 30
+relentless run --feature <feature-name> --max-iterations 30
+
+# With TUI interface
+relentless run --feature <feature-name> --tui
 ```
 
 ---

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@arvorco/relentless",
-  "version": "0.1.23",
+  "version": "0.1.26",
   "description": "Universal AI agent orchestrator - works with Claude Code, Amp, OpenCode, Codex, Droid, and Gemini",
   "type": "module",
   "publishConfig": {

package/src/init/scaffolder.ts

@@ -49,9 +49,17 @@ const relentlessRoot = getRelentlessRoot();
 
 /**
  * Files to create in the relentless/ directory
+ * These can be force-updated with -f flag
  */
 const RELENTLESS_FILES: Record<string, () => string> = {
   "config.json": () => JSON.stringify(DEFAULT_CONFIG, null, 2),
+};
+
+/**
+ * Files that should NEVER be overwritten, even with -f flag
+ * These are personalized files that users customize for their project
+ */
+const PROTECTED_FILES: Record<string, () => string> = {
   "prompt.md": () => PROMPT_TEMPLATE,
 };
 
@@ -171,7 +179,7 @@ export async function initProject(projectDir: string = process.cwd(), force: boo
     }
   }
 
-  // Create relentless files
+  // Create relentless files (can be force-updated)
   console.log(chalk.dim("\nCreating relentless files..."));
 
   for (const [filename, contentFn] of Object.entries(RELENTLESS_FILES)) {
@@ -187,6 +195,19 @@ export async function initProject(projectDir: string = process.cwd(), force: boo
     console.log(`  ${chalk.green("✓")} relentless/${filename} ${force ? `(${action})` : ""}`);
   }
 
+  // Create protected files (NEVER overwritten, even with -f)
+  for (const [filename, contentFn] of Object.entries(PROTECTED_FILES)) {
+    const path = join(relentlessDir, filename);
+
+    if (existsSync(path)) {
+      console.log(`  ${chalk.yellow("⚠")} relentless/${filename} already exists (protected, not overwriting)`);
+      continue;
+    }
+
+    await Bun.write(path, contentFn());
+    console.log(`  ${chalk.green("✓")} relentless/${filename} (created)`);
+  }
+
   // Note: constitution.md is NOT copied - it should be created by /relentless.constitution command
   // This ensures each project gets a personalized constitution
 

package/templates/prompt.md

@@ -0,0 +1,72 @@
+# Relentless Agent Instructions
+
+You are an autonomous coding agent. Follow these instructions exactly.
+
+**This is a generic template. Personalize it for your project using:**
+```bash
+/relentless.constitution
+```
+
+---
+
+## Your Task (Per Iteration)
+
+1. Read `relentless/features/<feature>/prd.json`
+2. Read `relentless/features/<feature>/progress.txt`
+3. Check you're on the correct branch from PRD `branchName`
+4. Pick the **highest priority** story where `passes: false`
+5. Review existing code to understand patterns
+6. Implement the story
+7. Run quality checks (typecheck, lint, test)
+8. If ALL checks pass, commit: `feat: [Story ID] - [Story Title]`
+9. Update PRD: set `passes: true`
+10. Append progress to `progress.txt`
+
+---
+
+## Quality Requirements
+
+Before marking a story complete:
+- [ ] All quality checks pass (typecheck, lint, test)
+- [ ] Zero errors and zero warnings
+- [ ] No debug code (console.log, debugger)
+- [ ] No unused imports or variables
+- [ ] Follows existing patterns
+
+---
+
+## Progress Report Format
+
+APPEND to progress.txt:
+```
+## [Date/Time] - [Story ID]
+- What was implemented
+- Files changed
+- Learnings for future iterations
+---
+```
+
+---
+
+## Stop Condition
+
+After completing a story, check if ALL stories have `passes: true`.
+
+If ALL complete:
+```
+<promise>COMPLETE</promise>
+```
+
+Otherwise, end normally (next iteration continues).
+
+---
+
+## Notes
+
+This is the default template. You should personalize `relentless/prompt.md` with:
+- Your project's specific quality commands
+- Your testing framework and patterns
+- Your coding conventions
+- Project-specific gotchas
+
+Run `/relentless.constitution` to generate a personalized prompt.