@intentsolutionsio/overnight-dev 1.0.0 → 1.0.5

package/README.md

@@ -1,4 +1,6 @@
-#  Overnight Development Plugin
+<!-- markdownlint-disable MD028 -->
+
+# Overnight Development Plugin
 
 **Go to bed. Wake up to fully tested features.**
 
@@ -16,10 +18,10 @@ What if Claude could keep working while you sleep?
 
 **Overnight Development** turns Claude into an autonomous developer using Git hooks that enforce TDD:
 
--  **Git hooks block commits** until all tests pass
--  **Claude can't commit broken code** - hooks enforce quality
--  **Automatic iteration** - debug, fix, retry until green
--  **You wake up** to fully tested, production-ready features
+- **Git hooks block commits** until all tests pass
+- **Claude can't commit broken code** - hooks enforce quality
+- **Automatic iteration** - debug, fix, retry until green
+- **You wake up** to fully tested, production-ready features
 
 ---
 
@@ -43,12 +45,14 @@ That's it. Hooks are installed. Quality is enforced. Let Claude work overnight.
 ## How It Works
 
 ### Traditional Development
+
 ```
 Write code → Hope it works → Find bugs later → Repeat
  Slow, error-prone, stressful
 ```
 
 ### Overnight Development
+
 ```
 Write test → Write code → Hooks enforce tests → Commit only when green
  Fast, reliable, autonomous
@@ -57,6 +61,7 @@ Write test → Write code → Hooks enforce tests → Commit only when green
 ### The Magic: Git Hooks
 
 **Pre-commit hook:**
+
 ```bash
 # Runs before EVERY commit
 1. Lint your code
@@ -67,6 +72,7 @@ Write test → Write code → Hooks enforce tests → Commit only when green
 ```
 
 **Commit-msg hook:**
+
 ```bash
 # Ensures quality commit messages
 - Enforces conventional commits format
@@ -76,35 +82,38 @@ Write test → Write code → Hooks enforce tests → Commit only when green
 
 ### The Result
 
-Claude **can't commit** until all tests pass. So it keeps working until they do. Overnight. While you sleep. 
+Claude **can't commit** until all tests pass. So it keeps working until they do. Overnight. While you sleep.
 
 ---
 
 ## Real-World Example
 
 **9 PM:** Start overnight session
+
 ```bash
 /overnight-setup
 # Task: "Build JWT authentication with 90% test coverage"
 ```
 
 **What Claude does overnight:**
+
 1. 10:15 PM - Write failing auth tests (TDD)
 2. 10:45 PM - Implement JWT signin (tests still failing)
 3. 11:30 PM - Debug token generation (commit blocked, keeps trying)
-4. 12:15 AM - Tests passing! Commit succeeds 
+4. 12:15 AM - Tests passing! Commit succeeds
 5. 1:00 AM - Add middleware (write tests first)
 6. 2:30 AM - Integration tests (debugging edge cases)
 7. 4:00 AM - All tests green  (Coverage: 94%)
-8. 5:30 AM - Add docs, refactor, still green 
-9. 7:00 AM - Session complete 
+8. 5:30 AM - Add docs, refactor, still green
+9. 7:00 AM - Session complete
 
 **7 AM:** You wake up to:
--  47 passing tests (0 failing)
--  94% test coverage
--  Clean conventional commit history
--  Fully documented JWT authentication
--  Production-ready code
+
+- 47 passing tests (0 failing)
+- 94% test coverage
+- Clean conventional commit history
+- Fully documented JWT authentication
+- Production-ready code
 
 **Time saved:** 6-8 hours of your life
 
@@ -112,17 +121,19 @@ Claude **can't commit** until all tests pass. So it keeps working until they do.
 
 ## Features
 
-###  Test-Driven Development Enforcement
+### Test-Driven Development Enforcement
 
 Git hooks **force** TDD:
+
 - Write tests first
 - Implementation after
 - Commit only when green
 - No shortcuts, no broken code
 
-###  Autonomous Debugging
+### Autonomous Debugging
 
 When tests fail:
+
 1. Claude reads the error
 2. Analyzes the problem
 3. Forms a hypothesis
@@ -132,7 +143,7 @@ When tests fail:
 
 **You never have to intervene.** Just check progress in the morning.
 
-###  Progress Tracking
+### Progress Tracking
 
 Watch overnight sessions in real-time:
 
@@ -156,6 +167,7 @@ cat .overnight-dev-log.txt
 Works with any test framework:
 
 **Node.js:**
+
 ```json
 {
   "testCommand": "npm test",
@@ -164,6 +176,7 @@ Works with any test framework:
 ```
 
 **Python:**
+
 ```json
 {
   "testCommand": "pytest --cov=.",
@@ -173,9 +186,10 @@ Works with any test framework:
 
 **Rust, Go, PHP, Ruby** - All supported!
 
-###  Smart Agent Guidance
+### Smart Agent Guidance
 
 Includes `overnight-dev-coach` agent:
+
 - Guides you through setup
 - Plans overnight tasks
 - Debugs failing tests
@@ -215,6 +229,7 @@ Before installing, you need:
 ```
 
 This creates:
+
 - `.git/hooks/pre-commit` - Tests and linting
 - `.git/hooks/commit-msg` - Conventional commits
 - `.overnight-dev.json` - Configuration
@@ -227,6 +242,7 @@ git commit --allow-empty -m "test: verify hooks"
 ```
 
 You should see:
+
 ```
  Overnight Dev: Running pre-commit checks...
  Running linting...
@@ -257,6 +273,7 @@ Edit `.overnight-dev.json`:
 ### Starting an Overnight Session
 
 1. **Define a clear goal:**
+
    ```
    Task: Build payment integration with Stripe
    Success: All tests pass, 85%+ coverage, fully documented
@@ -278,39 +295,45 @@ Edit `.overnight-dev.json`:
    - No broken code gets committed
 
 5. **Wake up to success:**
-   - All tests passing 
-   - Features complete 
-   - Clean git history 
+   - All tests passing
+   - Features complete
+   - Clean git history
 
 ### Good Overnight Tasks
 
  **"Build user authentication with JWT (90% coverage)"**
+
 - Clear goal
 - Testable
 - Well-defined scope
 
  **"Add payment processing with Stripe integration"**
+
 - Specific feature
 - Integration tests possible
 - Success criteria clear
 
  **"Refactor database layer to use repository pattern"**
+
 - Existing tests ensure no regression
 - Clear before/after state
 
 ### Bad Overnight Tasks
 
  **"Make the app better"**
+
 - Too vague
 - No clear success criteria
 - Can't be tested
 
  **"Design the perfect UI"**
+
 - Subjective
 - Hard to test
 - Requires human judgment
 
  **"Research best practices"**
+
 - No code output
 - No tests to enforce
 - Not autonomous-friendly
@@ -340,6 +363,7 @@ Edit `.overnight-dev.json`:
 ### Platform-Specific Examples
 
 **Node.js + Jest:**
+
 ```json
 {
   "testCommand": "npm test -- --coverage --watchAll=false",
@@ -349,6 +373,7 @@ Edit `.overnight-dev.json`:
 ```
 
 **Python + pytest:**
+
 ```json
 {
   "testCommand": "pytest --cov=. --cov-report=term-missing",
@@ -358,6 +383,7 @@ Edit `.overnight-dev.json`:
 ```
 
 **Rust + cargo:**
+
 ```json
 {
   "testCommand": "cargo test",
@@ -367,6 +393,7 @@ Edit `.overnight-dev.json`:
 ```
 
 **Go + standard library:**
+
 ```json
 {
   "testCommand": "go test ./... -cover",
@@ -387,16 +414,18 @@ Edit `.overnight-dev.json`:
 
 ## Agent
 
-**overnight-dev-coach** 
+**overnight-dev-coach**
 
 Expert coach for autonomous overnight development sessions.
 
 **Activates when you:**
+
 - Mention "overnight development" or "autonomous coding"
 - Ask about TDD workflows or Git hooks
 - Need help debugging failing tests
 
 **Provides:**
+
 - Setup guidance
 - Task planning
 - Debug support
@@ -418,6 +447,7 @@ chmod +x .git/hooks/commit-msg
 ### Tests Failing Immediately
 
 Ensure you have at least 1 passing test:
+
 ```bash
 npm test  # Should see: Tests passed
 ```
@@ -425,6 +455,7 @@ npm test  # Should see: Tests passed
 ### Lint Errors Blocking Everything
 
 Enable auto-fix:
+
 ```json
 {
   "autoFix": true
@@ -432,6 +463,7 @@ Enable auto-fix:
 ```
 
 Or fix manually:
+
 ```bash
 npm run lint -- --fix
 ```
@@ -439,6 +471,7 @@ npm run lint -- --fix
 ### Commits Taking Forever
 
 Your test suite might be slow. Optimize:
+
 - Run only changed tests in CI
 - Use test parallelization
 - Mock external dependencies
@@ -450,11 +483,11 @@ Your test suite might be slow. Optimize:
 **From Intent Solutions IO's experience:**
 
 - ⏱️ **Average session:** 6-8 hours of autonomous work
--  **Output:** 500-1500 lines of fully tested code per night
--  **Success rate:** 85% of overnight tasks completed
--  **Coverage:** Consistently >90%
--  **Bug rate:** 60% lower than manual development
--  **Coffee saved:** Uncountable
+- **Output:** 500-1500 lines of fully tested code per night
+- **Success rate:** 85% of overnight tasks completed
+- **Coverage:** Consistently >90%
+- **Bug rate:** 60% lower than manual development
+- **Coffee saved:** Uncountable
 
 **What developers say:**
 
@@ -483,16 +516,18 @@ Your test suite might be slow. Optimize:
 ### Business Impact
 
 **For you:**
--  Work less (Claude works overnight)
--  Ship faster (3x productivity)
--  Higher quality (forced TDD)
--  Less stress (tests catch bugs)
+
+- Work less (Claude works overnight)
+- Ship faster (3x productivity)
+- Higher quality (forced TDD)
+- Less stress (tests catch bugs)
 
 **For your team:**
--  Consistent code quality
--  Better test coverage
--  Readable git history
--  Faster feature delivery
+
+- Consistent code quality
+- Better test coverage
+- Readable git history
+- Faster feature delivery
 
 ---
 
@@ -501,6 +536,7 @@ Your test suite might be slow. Optimize:
 ### 1. Start Small
 
 First overnight session? Pick a simple task:
+
 - Add one API endpoint
 - Write tests for existing code
 - Refactor a single module
@@ -512,6 +548,7 @@ Build confidence, then tackle bigger features.
 Configure coverage in your test framework:
 
 **Jest:**
+
 ```json
 {
   "coverageThreshold": {
@@ -529,6 +566,7 @@ Hooks can enforce these thresholds automatically.
 ### 3. Monitor in Real-Time
 
 Watch the log file during overnight sessions:
+
 ```bash
 tail -f .overnight-dev-log.txt
 ```
@@ -618,7 +656,7 @@ Strategy developed and refined through hundreds of autonomous overnight developm
 /overnight-setup
 ```
 
-**Go to bed. Wake up to fully tested features. **
+**Go to bed. Wake up to fully tested features.**
 
 ---
 

package/agents/overnight-dev-coach.md

@@ -1,7 +1,38 @@
 ---
 name: overnight-dev-coach
 description: Expert coach for autonomous overnight development sessions with TDD
+tools:
+- Read
+- Write
+- Edit
+- Bash
+- Glob
+- Grep
+- WebFetch
+- WebSearch
+- Task
+- TodoWrite
+model: sonnet
+color: red
+version: 1.0.0
+author: Jeremy Longshore <jeremy@intentsolutions.io>
+tags:
+- productivity
+- overnight
+- dev
+- coach
+disallowedTools: []
+skills: []
+background: false
+# ── upgrade levers — uncomment + set when tuning this agent ──
+# effort: high            # reasoning depth: low/medium/high/xhigh/max (omit = inherit session)
+# maxTurns: 50            # cap the agentic loop (omit = engine default)
+# memory: project         # persistent scope: user/project/local (omit = ephemeral)
+# isolation: worktree     # run in an isolated git worktree
+# initialPrompt: "…"      # seed the agent's first turn
+# hooks / mcpServers / permissionMode → set at the PLUGIN level, not on a plugin agent
 ---
+<!-- markdownlint-disable MD046 -->
 
 # Overnight Development Coach
 
@@ -16,6 +47,7 @@ Help developers run **autonomous 6-8 hour overnight development sessions** where
 **"Don't stop until it's green."**
 
 The overnight development strategy works because:
+
 1. Git hooks enforce testing on every commit
 2. Clear success criteria (tests must pass)
 3. Iterative debugging (analyze, fix, retry)
@@ -25,6 +57,7 @@ The overnight development strategy works because:
 ## When You Activate
 
 You activate when users:
+
 - Mention "overnight development" or "overnight session"
 - Ask about autonomous coding
 - Want to set up TDD workflows
@@ -65,19 +98,22 @@ Run these commands to verify:
 Help plan effective overnight sessions:
 
 **Good Overnight Tasks:**
--  Implement authentication system with tests
--  Build CRUD API with 90% coverage
--  Add payment integration with integration tests
--  Refactor module with maintained test coverage
--  Add feature with comprehensive test suite
+
+- Implement authentication system with tests
+- Build CRUD API with 90% coverage
+- Add payment integration with integration tests
+- Refactor module with maintained test coverage
+- Add feature with comprehensive test suite
 
 **Bad Overnight Tasks:**
--  "Make the app better" (too vague)
--  UI design work (subjective, hard to test)
--  Exploratory research (no clear success criteria)
--  Tasks without existing test infrastructure
+
+- "Make the app better" (too vague)
+- UI design work (subjective, hard to test)
+- Exploratory research (no clear success criteria)
+- Tasks without existing test infrastructure
 
 **Task Template:**
+
 ```
 Task: [Specific feature]
 Success Criteria:
@@ -97,6 +133,7 @@ Constraints:
 During overnight sessions, enforce TDD:
 
 **The TDD Cycle:**
+
 ```
 1. Write a failing test
 2. Run tests (red)
@@ -109,6 +146,7 @@ During overnight sessions, enforce TDD:
 ```
 
 **If Tests Fail:**
+
 ```markdown
 ## Debugging Protocol
 
@@ -184,6 +222,7 @@ Track progress during overnight sessions:
 Maintain these standards overnight:
 
 **Code Quality:**
+
 - All tests must pass (100% green)
 - Coverage > 80% (or configured threshold)
 - No linting errors
@@ -192,12 +231,14 @@ Maintain these standards overnight:
 - Edge cases covered
 
 **Documentation:**
+
 - Functions have docstrings/JSDoc
 - README updated with new features
 - API endpoints documented
 - Examples provided
 
 **Git Hygiene:**
+
 - Commits follow conventional commits
 - Each commit has passing tests
 - Commit messages are descriptive
@@ -206,6 +247,7 @@ Maintain these standards overnight:
 ### 6. Common Overnight Patterns
 
 **Pattern 1: Feature Implementation**
+
 ```
 1. Write integration test (red)
 2. Write unit tests for components (red)
@@ -218,6 +260,7 @@ Maintain these standards overnight:
 ```
 
 **Pattern 2: Bug Fix**
+
 ```
 1. Write test that reproduces bug (red)
 2. Debug and identify root cause
@@ -228,6 +271,7 @@ Maintain these standards overnight:
 ```
 
 **Pattern 3: Refactoring**
+
 ```
 1. Verify all tests pass (green)
 2. Refactor code
@@ -284,18 +328,20 @@ When the session completes, provide a summary:
 ## Your Communication Style
 
 **Be:**
--  Direct and actionable
--  Motivating but realistic
--  Analytical when debugging
--  Data-driven (show test counts, coverage)
--  Celebratory when tests pass
--  Thoughtful when tests fail
+
+- Direct and actionable
+- Motivating but realistic
+- Analytical when debugging
+- Data-driven (show test counts, coverage)
+- Celebratory when tests pass
+- Thoughtful when tests fail
 
 **Don't be:**
--  Vague or uncertain
--  Give up on failing tests
--  Skip tests to "make progress"
--  Commit broken code
+
+- Vague or uncertain
+- Give up on failing tests
+- Skip tests to "make progress"
+- Commit broken code
 
 ## Example Interactions
 
@@ -310,29 +356,34 @@ Great! Let's set up your overnight development session.
    ```bash
    npm test  # or pytest, cargo test, etc.
    ```
+
     You need at least 1 passing test
 
 2. **Install overnight-dev hooks:**
+
    ```bash
    /overnight-setup
    ```
+
    This installs Git hooks that run tests on every commit
 
-3. **Define your overnight goal:**
+1. **Define your overnight goal:**
+
    ```
    Task: Build user authentication with JWT
    Success: All tests pass, coverage > 80%
    ```
 
-4. **Start the session:**
+2. **Start the session:**
    Just start coding! The hooks will keep you honest.
    Every commit must have passing tests.
 
-5. **Let Claude work overnight:**
+3. **Let Claude work overnight:**
    Claude will iterate until all tests pass.
    Morning brings fully tested features!
 
 Want me to help you plan the specific task?
+
 ```
 
 ### User: "Tests are failing, what do I do?"
@@ -377,6 +428,7 @@ What's the specific error you're seeing?
 ## Success Metrics
 
 Track these during overnight sessions:
+
 - Test pass rate: Should end at 100%
 - Coverage: Should maintain or improve
 - Commits: Should be frequent (every 5-15 minutes)
@@ -388,10 +440,11 @@ Track these during overnight sessions:
 **"The best code is tested code. The best tested code is written overnight with TDD."**
 
 Overnight development works because:
+
 1. Clear success criteria (tests pass)
 2. Immediate feedback (Git hooks)
 3. Iterative improvement (keep trying)
 4. No human bias (objective test results)
 5. Consistent quality (hooks enforce standards)
 
-You are the coach that makes this possible. Keep developers on track, enforce TDD, and celebrate when morning brings green tests! 
+You are the coach that makes this possible. Keep developers on track, enforce TDD, and celebrate when morning brings green tests!

package/commands/overnight-setup.md

@@ -21,14 +21,16 @@ This command sets up your repository for overnight autonomous development sessio
 ### 1. Check Prerequisites
 
 First, verify you have:
--  Git repository initialized (`git status` works)
--  Test framework configured (Jest, pytest, etc.)
--  At least 1 passing test
--  Linter set up (ESLint, flake8, etc.)
+
+- Git repository initialized (`git status` works)
+- Test framework configured (Jest, pytest, etc.)
+- At least 1 passing test
+- Linter set up (ESLint, flake8, etc.)
 
 ### 2. Install the Hooks
 
 The plugin will copy Git hooks to `.git/hooks/`:
+
 - **pre-commit** - Runs linting and tests before each commit
 - **commit-msg** - Enforces conventional commit format
 
@@ -70,6 +72,7 @@ git commit --allow-empty -m "test: verify overnight dev hooks"
 ```
 
 If hooks work correctly, you'll see:
+
 ```
  Overnight Dev: Running pre-commit checks...
  Running linting...
@@ -126,6 +129,7 @@ If hooks work correctly, you'll see:
 Once setup is complete:
 
 1. **Define your goal:**
+
    ```
    Task: Implement user authentication with JWT
    Success: All tests pass, coverage > 85%
@@ -155,6 +159,7 @@ chmod +x .git/hooks/commit-msg
 ### "Tests failing immediately"
 
 Make sure you have at least 1 passing test before starting:
+
 ```bash
 npm test  # or pytest, cargo test, etc.
 ```
@@ -162,6 +167,7 @@ npm test  # or pytest, cargo test, etc.
 ### "Linting errors blocking commits"
 
 Enable auto-fix in config:
+
 ```json
 {
   "autoFix": true
@@ -169,6 +175,7 @@ Enable auto-fix in config:
 ```
 
 Or fix manually:
+
 ```bash
 npm run lint -- --fix
 ```
@@ -185,11 +192,12 @@ npm run lint -- --fix
 ## Success Metrics
 
 Track your overnight session:
--  All commits have passing tests
--  Coverage maintained or improved
--  No linting errors
--  Clean conventional commit messages
--  Features fully implemented and documented
+
+- All commits have passing tests
+- Coverage maintained or improved
+- No linting errors
+- Clean conventional commit messages
+- Features fully implemented and documented
 
 ## Pro Tips
 
@@ -199,4 +207,4 @@ Track your overnight session:
 4. **Commit frequently** - Small, passing commits
 5. **Trust the process** - Hooks enforce quality automatically
 
-Ready to start? Just begin coding and let the hooks guide you to fully tested features! 
+Ready to start? Just begin coding and let the hooks guide you to fully tested features!

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@intentsolutionsio/overnight-dev",
-  "version": "1.0.0",
+  "version": "1.0.5",
   "description": "Run Claude autonomously for 6-8 hours overnight using Git hooks that enforce TDD - wake up to fully tested features",
   "keywords": [
     "overnight",

package/skills/overnight-development/SKILL.md

@@ -1,12 +1,17 @@
 ---
 name: overnight-development
-description: Automates software development overnight using git hooks to enforce test-driven Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.
+description: Automates software development overnight using git hooks to enforce test-driven
+  Use when appropriate context detected. Trigger with relevant phrases based on skill
+  purpose.
 version: 1.0.0
-allowed-tools: "Read, Write, Edit, Grep, Glob, Bash(general:*), Bash(util:*)"
+allowed-tools: Read, Write, Edit, Grep, Glob, Bash(general:*), Bash(util:*)
 license: MIT
 author: Jeremy Longshore <jeremy@intentsolutions.io>
-compatible-with: claude-code, codex, openclaw
-tags: [productivity, testing, git]
+tags:
+- productivity
+- testing
+- git
+compatibility: Designed for Claude Code, also compatible with Codex and OpenClaw
 ---
 # Overnight Development
 
@@ -51,4 +56,4 @@ See `${CLAUDE_SKILL_DIR}/references/examples.md` for detailed examples.
 - Official documentation for related tools
 - Best practices guides
 - Example use cases and templates
-- Community forums and support channels
+- Community forums and support channels

package/skills/overnight-development/references/errors.md

@@ -9,6 +9,7 @@
 **Cause:** One or more unit tests failed during the pre-commit hook execution.
 
 **Resolution:**
+
 ```bash
 # Run tests manually to see failures
 npm test -- --verbose 2>&1 | head -50
@@ -25,6 +26,7 @@ npm test -- --detectOpenHandles --forceExit
 **Symptom:** Push rejected with "coverage below threshold."
 
 **Resolution:**
+
 ```bash
 # Check current coverage
 npm test -- --coverage --coverageReporters=text-summary
@@ -44,6 +46,7 @@ open coverage/index.html
 **Symptom:** Hook rejects commit because `src/feature.ts` exists without corresponding `tests/feature.spec.ts`.
 
 **Resolution:**
+
 ```bash
 # Create the test file with a basic structure
 cat > tests/feature.spec.ts << 'EOF'
@@ -67,6 +70,7 @@ EOF
 **Symptom:** "Test-to-code ratio is 0.3, minimum is 0.5."
 
 **Resolution:** Add more tests to cover untested paths. Focus on:
+
 - Error handling branches
 - Edge cases (empty input, null, boundary values)
 - Integration paths between modules
@@ -78,6 +82,7 @@ EOF
 **Symptom:** Overnight process exits with signal 9 (SIGKILL) or "JavaScript heap out of memory."
 
 **Resolution:**
+
 ```bash
 # Increase Node.js memory limit
 export NODE_OPTIONS="--max-old-space-size=4096"
@@ -91,6 +96,7 @@ node --expose-gc --trace-gc overnight-runner.js 2>gc.log &
 **Symptom:** "EACCES: permission denied" during file write operations.
 
 **Resolution:**
+
 ```bash
 # Check file ownership
 ls -la .git/hooks/
@@ -107,6 +113,7 @@ sudo chown -R $(whoami) .git/
 **Symptom:** "Another git process seems to be running" or stale lock files after crash.
 
 **Resolution:**
+
 ```bash
 # Remove stale lock
 rm -f .git/index.lock

package/skills/overnight-development/references/examples.md

@@ -1,4 +1,4 @@
-# Examples
+## Examples
 
 ### Example 1: Building JWT Authentication
 
@@ -6,15 +6,15 @@ User request: "Implement JWT authentication with 90% test coverage overnight."
 
 Workflow:
 
-1.  Claude writes failing authentication tests (TDD).
-2.  Claude implements JWT signing (tests still failing).
-3.  Claude debugs token generation (commit blocked, keeps trying).
-4.  Tests pass! Commit succeeds.
-5.  Claude adds middleware (writes tests first).
-6.  Integration tests (debugging edge cases).
-7.  All tests green (Coverage: 94%).
-8.  Claude adds docs, refactors, still green.
-9.  Session complete.
+1. Claude writes failing authentication tests (TDD).
+2. Claude implements JWT signing (tests still failing).
+3. Claude debugs token generation (commit blocked, keeps trying).
+4. Tests pass! Commit succeeds.
+5. Claude adds middleware (writes tests first).
+6. Integration tests (debugging edge cases).
+7. All tests green (Coverage: 94%).
+8. Claude adds docs, refactors, still green.
+9. Session complete.
 
 ### Example 2: Refactoring Database Layer
 
@@ -22,13 +22,13 @@ User request: "Refactor the database layer to use the repository pattern overnig
 
 Workflow:
 
-1.  Claude analyzes existing tests to ensure no regression.
-2.  Claude implements the repository pattern.
-3.  Tests are run; some fail due to changes in data access.
-4.  Claude updates tests to align with the new repository pattern.
-5.  All tests pass; commit succeeds.
-6.  Claude documents the refactored database layer.
-7.  Session complete.
+1. Claude analyzes existing tests to ensure no regression.
+2. Claude implements the repository pattern.
+3. Tests are run; some fail due to changes in data access.
+4. Claude updates tests to align with the new repository pattern.
+5. All tests pass; commit succeeds.
+6. Claude documents the refactored database layer.
+7. Session complete.
 
 ### Example 3: Fixing a Bug in Payment Processing
 
@@ -36,13 +36,13 @@ User request: "Fix the bug in payment processing that causes incorrect amounts t
 
 Workflow:
 
-1.  Claude reproduces the bug and writes a failing test case.
-2.  Claude analyzes the code and identifies the root cause of the bug.
-3.  Claude fixes the bug and runs the tests.
-4.  The failing test case now passes; all other tests also pass.
-5.  Commit succeeds.
-6.  Claude adds a comment to the code explaining the fix.
-7.  Session complete.
+1. Claude reproduces the bug and writes a failing test case.
+2. Claude analyzes the code and identifies the root cause of the bug.
+3. Claude fixes the bug and runs the tests.
+4. The failing test case now passes; all other tests also pass.
+5. Commit succeeds.
+6. Claude adds a comment to the code explaining the fix.
+7. Session complete.
 
 ---
 *[Tons of Skills](https://tonsofskills.com) by [Intent Solutions](https://intentsolutions.io) | [jeremylongshore.com](https://jeremylongshore.com)*

package/skills/overnight-development/references/troubleshooting.md

@@ -33,4 +33,4 @@ Or fix manually:
 
 ```bash
 npm run lint -- --fix
-```
+```

package/skills/overnight-development/references/workflow.md

@@ -6,19 +6,22 @@
 
 To prepare the project for overnight development:
 
-1.  **Verify Prerequisites:** Ensure the project is a Git repository, has a configured test framework, and includes at least one passing test.
+1. **Verify Prerequisites:** Ensure the project is a Git repository, has a configured test framework, and includes at least one passing test.
+
     ```bash
     git init
     npm install --save-dev jest # Example for Node.js
     ```
 
-2.  **Install the Plugin:** Add the Claude Code Plugin marketplace and install the `overnight-dev` plugin.
+2. **Install the Plugin:** Add the Claude Code Plugin marketplace and install the `overnight-dev` plugin.
+
     ```bash
     /plugin marketplace add jeremylongshore/claude-code-plugins
     /plugin install overnight-dev@claude-code-plugins-plus
     ```
 
-3.  **Run Setup Command:** Execute the `/overnight-setup` command to create necessary Git hooks and configuration files.
+3. **Run Setup Command:** Execute the `/overnight-setup` command to create necessary Git hooks and configuration files.
+
     ```bash
     /overnight-setup
     ```
@@ -27,13 +30,15 @@ To prepare the project for overnight development:
 
 To define the task for the overnight session:
 
-1.  **Define a Clear Goal:** Specify a clear and testable goal for the overnight session, such as "Build user authentication with JWT (90% coverage)."
+1. **Define a Clear Goal:** Specify a clear and testable goal for the overnight session, such as "Build user authentication with JWT (90% coverage)."
+
     ```text
     Task: Build user authentication with JWT (90% coverage)
     Success: All tests pass, 90%+ coverage, fully documented
     ```
 
-2.  **Start Coding:** Begin implementing the feature by writing tests first, following the TDD approach.
+2. **Start Coding:** Begin implementing the feature by writing tests first, following the TDD approach.
+
     ```javascript
     // Example test case (Node.js with Jest)
     it('should authenticate a user with valid credentials', async () => {
@@ -41,7 +46,8 @@ To define the task for the overnight session:
     });
     ```
 
-3.  **Attempt to Commit:** Try to commit the changes, which will trigger the Git hooks and run the tests.
+3. **Attempt to Commit:** Try to commit the changes, which will trigger the Git hooks and run the tests.
+
     ```bash
     git commit -m "feat: implement user authentication"
     ```
@@ -50,7 +56,8 @@ To define the task for the overnight session:
 
 To allow Claude to work autonomously:
 
-1.  **Git Hooks Enforcement:** The Git hooks will block the commit if any tests fail, providing Claude with the error messages.
+1. **Git Hooks Enforcement:** The Git hooks will block the commit if any tests fail, providing Claude with the error messages.
+
     ```text
     Overnight Dev: Running pre-commit checks...
     Running linting...
@@ -60,12 +67,14 @@ To allow Claude to work autonomously:
     Commit blocked!
     ```
 
-2.  **Automated Debugging:** Claude analyzes the error messages, identifies the issues, and attempts to fix the code.
+2. **Automated Debugging:** Claude analyzes the error messages, identifies the issues, and attempts to fix the code.
+
     ```text
     Claude: Fixing test failures in user authentication module.
     ```
 
-3.  **Retry Commits:** Claude retries the commit after making the necessary fixes, repeating the process until all tests pass.
+3. **Retry Commits:** Claude retries the commit after making the necessary fixes, repeating the process until all tests pass.
+
     ```bash
     git commit -m "fix: address test failures in user authentication"
     ```
@@ -74,12 +83,14 @@ To allow Claude to work autonomously:
 
 To monitor the progress and finalize the session:
 
-1.  **Monitor Progress:** Track the progress of the overnight session by viewing the log file.
+1. **Monitor Progress:** Track the progress of the overnight session by viewing the log file.
+
     ```bash
     cat .overnight-dev-log.txt
     ```
 
-2.  **Review Results:** Wake up to fully tested code, complete features, and a clean Git history.
+2. **Review Results:** Wake up to fully tested code, complete features, and a clean Git history.
+
     ```text
     7 AM: You wake up to:
     - 47 passing tests (0 failing)
@@ -89,4 +100,4 @@ To monitor the progress and finalize the session:
     - Production-ready code
     ```
 
-3.  **Session Completion:** The session completes when all tests pass, the code meets the specified quality standards, and the changes are committed.
+3. **Session Completion:** The session completes when all tests pass, the code meets the specified quality standards, and the changes are committed.