mu-code

name	mu-code
description	Use when you have an implementation plan ready to execute - supports subagent-driven and inline execution modes with TDD, worktree isolation, and review gates

Code

Overview

Execute implementation plan task by task. Two modes: subagent-driven (recommended) or inline.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

Announce at start: "I'm using the mu-code skill to implement this plan."

Process

digraph process_overview {
    rankdir=TB;

    "Read plan, extract tasks" [shape=box];
    "Step 1: Worktree Setup" [shape=box style=filled fillcolor=lightyellow];
    "Step 2: Select Execution Mode" [shape=diamond];
    "Subagent-Driven Mode" [shape=box];
    "Inline Mode" [shape=box];
    "Parallel Dispatch" [shape=box];
    "Per-task loop: implement → review → next" [shape=box];
    "All tasks complete" [shape=diamond];
    "Chain to mu-review" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract tasks" -> "Step 1: Worktree Setup";
    "Step 1: Worktree Setup" -> "Step 2: Select Execution Mode";
    "Step 2: Select Execution Mode" -> "Subagent-Driven Mode" [label="subagents available\n(recommended)"];
    "Step 2: Select Execution Mode" -> "Inline Mode" [label="no subagents /\nparallel session"];
    "Step 2: Select Execution Mode" -> "Parallel Dispatch" [label="multiple independent\nfailures/tasks"];
    "Subagent-Driven Mode" -> "Per-task loop: implement → review → next";
    "Inline Mode" -> "Per-task loop: implement → review → next";
    "Parallel Dispatch" -> "Per-task loop: implement → review → next";
    "Per-task loop: implement → review → next" -> "All tasks complete";
    "All tasks complete" -> "Chain to mu-review" [label="yes"];
    "All tasks complete" -> "Per-task loop: implement → review → next" [label="no - next task"];
}

Step 1: Worktree Setup

Git worktrees create isolated workspaces sharing the same repository, allowing work on multiple branches simultaneously without switching.

Core principle: Systematic directory selection + safety verification = reliable isolation.

Directory Selection Process

Follow this priority order:

1. Check Existing Directories

# Check in priority order
ls -d .worktrees 2>/dev/null     # Preferred (hidden)
ls -d worktrees 2>/dev/null      # Alternative

If found: Use that directory. If both exist, .worktrees wins.

2. Check CLAUDE.md

grep -i "worktree.*director" CLAUDE.md 2>/dev/null

If preference specified: Use it without asking.

3. Ask User

If no directory exists and no CLAUDE.md preference:

No worktree directory found. Where should I create worktrees?

1. .worktrees/ (project-local, hidden)
2. ~/.config/devmuse/worktrees/<project-name>/ (global location)

Which would you prefer?

Safety Verification

For Project-Local Directories (.worktrees or worktrees)

MUST verify directory is ignored before creating worktree:

# Check if directory is ignored (respects local, global, and system gitignore)
git check-ignore -q .worktrees 2>/dev/null || git check-ignore -q worktrees 2>/dev/null

If NOT ignored:

Per Jesse's rule "Fix broken things immediately":

1. Add appropriate line to .gitignore
2. Commit the change
3. Proceed with worktree creation

Why critical: Prevents accidentally committing worktree contents to repository.

For Global Directory (~/.config/devmuse/worktrees)

No .gitignore verification needed - outside project entirely.

Creation Steps

1. Detect Project Name

project=$(basename "$(git rev-parse --show-toplevel)")

2. Create Worktree

# Determine full path
case $LOCATION in
  .worktrees|worktrees)
    path="$LOCATION/$BRANCH_NAME"
    ;;
  ~/.config/devmuse/worktrees/*)
    path="~/.config/devmuse/worktrees/$project/$BRANCH_NAME"
    ;;
esac

# Create worktree with new branch
git worktree add "$path" -b "$BRANCH_NAME"
cd "$path"

3. Run Project Setup

Auto-detect and run appropriate setup:

# Node.js
if [ -f package.json ]; then npm install; fi

# Rust
if [ -f Cargo.toml ]; then cargo build; fi

# Python
if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
if [ -f pyproject.toml ]; then poetry install; fi

# Go
if [ -f go.mod ]; then go mod download; fi

4. Verify Clean Baseline

Run tests to ensure worktree starts clean:

# Examples - use project-appropriate command
npm test
cargo test
pytest
go test ./...

If tests fail: Report failures, ask whether to proceed or investigate.

If tests pass: Report ready.

5. Report Location

Worktree ready at <full-path>
Tests passing (<N> tests, 0 failures)
Ready to implement <feature-name>

Worktree Quick Reference

Situation	Action
.worktrees/ exists	Use it (verify ignored)
worktrees/ exists	Use it (verify ignored)
Both exist	Use .worktrees/
Neither exists	Check CLAUDE.md → Ask user
Directory not ignored	Add to .gitignore + commit
Tests fail during baseline	Report failures + ask
No package.json/Cargo.toml	Skip dependency install

Common Worktree Mistakes

Skipping ignore verification

• Problem: Worktree contents get tracked, pollute git status
• Fix: Always use git check-ignore before creating project-local worktree

Assuming directory location

• Problem: Creates inconsistency, violates project conventions
• Fix: Follow priority: existing > CLAUDE.md > ask

Proceeding with failing tests

• Problem: Can't distinguish new bugs from pre-existing issues
• Fix: Report failures, get explicit permission to proceed

Hardcoding setup commands

• Problem: Breaks on projects using different tools
• Fix: Auto-detect from project files (package.json, etc.)

Step 2: Execution Mode Selection

digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Subagents available?" [shape=diamond];
    "Subagent-Driven Mode" [shape=box];
    "Inline Mode" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Subagents available?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Subagents available?" -> "Subagent-Driven Mode" [label="yes (recommended)"];
    "Subagents available?" -> "Inline Mode" [label="no / parallel session"];
}

Subagent-Driven Mode (Recommended)

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Per-Task Process

digraph process {
    rankdir=TB;

    subgraph cluster_per_task {
        label="Per Task";
        "Dispatch implementer subagent (@../../agents/mu-coder.md)" [shape=box];
        "Implementer subagent asks questions?" [shape=diamond];
        "Answer questions, provide context" [shape=box];
        "Implementer subagent implements, tests, commits, self-reviews" [shape=box];
        "Dispatch spec reviewer subagent (@../../agents/mu-reviewer.md review-compliance)" [shape=box];
        "Spec reviewer subagent confirms code matches spec?" [shape=diamond];
        "Implementer subagent fixes spec gaps" [shape=box];
        "Dispatch code quality reviewer subagent (@../../agents/mu-reviewer.md review-code)" [shape=box];
        "Code quality reviewer subagent approves?" [shape=diamond];
        "Implementer subagent fixes quality issues" [shape=box];
        "Mark task complete in TodoWrite" [shape=box];
    }

    "Read plan, extract all tasks with full text, note context, create TodoWrite" [shape=box];
    "More tasks remain?" [shape=diamond];
    "Chain to mu-review for final review" [shape=box style=filled fillcolor=lightgreen];

    "Read plan, extract all tasks with full text, note context, create TodoWrite" -> "Dispatch implementer subagent (@../../agents/mu-coder.md)";
    "Dispatch implementer subagent (@../../agents/mu-coder.md)" -> "Implementer subagent asks questions?";
    "Implementer subagent asks questions?" -> "Answer questions, provide context" [label="yes"];
    "Answer questions, provide context" -> "Dispatch implementer subagent (@../../agents/mu-coder.md)";
    "Implementer subagent asks questions?" -> "Implementer subagent implements, tests, commits, self-reviews" [label="no"];
    "Implementer subagent implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent (@../../agents/mu-reviewer.md review-compliance)";
    "Dispatch spec reviewer subagent (@../../agents/mu-reviewer.md review-compliance)" -> "Spec reviewer subagent confirms code matches spec?";
    "Spec reviewer subagent confirms code matches spec?" -> "Implementer subagent fixes spec gaps" [label="no"];
    "Implementer subagent fixes spec gaps" -> "Dispatch spec reviewer subagent (@../../agents/mu-reviewer.md review-compliance)" [label="re-review"];
    "Spec reviewer subagent confirms code matches spec?" -> "Dispatch code quality reviewer subagent (@../../agents/mu-reviewer.md review-code)" [label="yes"];
    "Dispatch code quality reviewer subagent (@../../agents/mu-reviewer.md review-code)" -> "Code quality reviewer subagent approves?";
    "Code quality reviewer subagent approves?" -> "Implementer subagent fixes quality issues" [label="no"];
    "Implementer subagent fixes quality issues" -> "Dispatch code quality reviewer subagent (@../../agents/mu-reviewer.md review-code)" [label="re-review"];
    "Code quality reviewer subagent approves?" -> "Mark task complete in TodoWrite" [label="yes"];
    "Mark task complete in TodoWrite" -> "More tasks remain?";
    "More tasks remain?" -> "Dispatch implementer subagent (@../../agents/mu-coder.md)" [label="yes"];
    "More tasks remain?" -> "Chain to mu-review for final review" [label="no"];
}

Model Selection

Choose between two tiers only. Do not use haiku — implementation and review quality suffers too much to be worth the savings.

Simple implementation tasks (isolated functions, clear specs, 1-2 files, mechanical edits): use sonnet.

Everything else (multi-file integration, judgment calls, debugging, architecture, design, review): use opus.

Task complexity signals:

• Touches 1-2 files with a complete, mechanical spec → sonnet
• Touches multiple files, requires integration/judgment → opus
• Requires design judgment or broad codebase understanding → opus

When in doubt, prefer opus. Never pass model: "haiku" when dispatching mu-coder or mu-reviewer.

Handling Implementer Status

Implementer subagents report one of four statuses. Handle each appropriately:

DONE: Proceed to spec compliance review.

DONE_WITH_CONCERNS: The implementer completed the work but flagged doubts. Read the concerns before proceeding. If the concerns are about correctness or scope, address them before review. If they're observations (e.g., "this file is getting large"), note them and proceed to review.

NEEDS_CONTEXT: The implementer needs information that wasn't provided. Provide the missing context and re-dispatch.

BLOCKED: The implementer cannot complete the task. Assess the blocker:

1. If it's a context problem, provide more context and re-dispatch with the same model
2. If the task requires more reasoning, re-dispatch with a more capable model
3. If the task is too large, break it into smaller pieces
4. If the plan itself is wrong, escalate to the human

Never ignore an escalation or force the same model to retry without changes. If the implementer said it's stuck, something needs to change.

Subagent-Driven Example Workflow

You: I'm using the mu-code skill to implement this plan.

[Read plan file once: docs/plans/feature-plan.md]
[Extract all 5 tasks with full text and context]
[Create TodoWrite with all tasks]

Task 1: Hook installation script

[Get Task 1 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: "Before I begin - should the hook be installed at user or system level?"

You: "User level (~/.config/devmuse/hooks/)"

Implementer: "Got it. Implementing now..."
[Later] Implementer:
  - Implemented install-hook command
  - Added tests, 5/5 passing
  - Self-review: Found I missed --force flag, added it
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: ✅ Spec compliant - all requirements met, nothing extra

[Get git SHAs, dispatch code quality reviewer]
Code reviewer: Strengths: Good test coverage, clean. Issues: None. Approved.

[Mark Task 1 complete]

Task 2: Recovery modes

[Get Task 2 text and context (already extracted)]
[Dispatch implementation subagent with full task text + context]

Implementer: [No questions, proceeds]
Implementer:
  - Added verify/repair modes
  - 8/8 tests passing
  - Self-review: All good
  - Committed

[Dispatch spec compliance reviewer]
Spec reviewer: ❌ Issues:
  - Missing: Progress reporting (spec says "report every 100 items")
  - Extra: Added --json flag (not requested)

[Implementer fixes issues]
Implementer: Removed --json flag, added progress reporting

[Spec reviewer reviews again]
Spec reviewer: ✅ Spec compliant now

[Dispatch code quality reviewer]
Code reviewer: Strengths: Solid. Issues (Important): Magic number (100)

[Implementer fixes]
Implementer: Extracted PROGRESS_INTERVAL constant

[Code reviewer reviews again]
Code reviewer: ✅ Approved

[Mark Task 2 complete]

...

[After all tasks]
[Chain to mu-review for final review]
Final reviewer: All requirements met, ready to merge

Done!

Inline Mode

Load plan, review critically, execute all tasks directly without subagents, report when complete.

Note: If subagents are available, use Subagent-Driven Mode instead for significantly higher quality output.

Step 1: Load and Review Plan

1. Read plan file
2. Review critically - identify any questions or concerns about the plan
3. If concerns: Raise them with your human partner before starting
4. If no concerns: Create TodoWrite and proceed

Step 2: Execute Tasks

For each task:

1. Mark as in_progress
2. Follow each step exactly (plan has bite-sized steps)
3. Run verifications as specified
4. Mark as completed

Step 3: Complete Development

After all tasks complete and verified:

• Chain to mu-review for final review
• Follow that skill to verify tests, present options, execute choice

When to Stop and Ask for Help

STOP executing immediately when:

• Hit a blocker (missing dependency, test fails, instruction unclear)
• Plan has critical gaps preventing starting
• You don't understand an instruction
• Verification fails repeatedly

Ask for clarification rather than guessing.

When to Revisit Earlier Steps

Return to Review (Step 1) when:

• Partner updates the plan based on your feedback
• Fundamental approach needs rethinking

Don't force through blockers - stop and ask.

Inline Mode Reminders

• Review plan critically first
• Follow plan steps exactly
• Don't skip verifications
• Reference skills when plan says to
• Stop when blocked, don't guess
• Never start implementation on main/master branch without explicit user consent
• Before any branch operation (checkout, create, rebase), follow Git Safety Protocol (@../../knowledge/principles/git-safety.md): verify current state before acting

Parallel Dispatch

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.

When to Use Parallel Dispatch

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}

Use when:

• 3+ test files failing with different root causes
• Multiple subsystems broken independently
• Each problem can be understood without context from others
• No shared state between investigations

Don't use when:

• Failures are related (fix one might fix others)
• Need to understand full system state
• Agents would interfere with each other

The Pattern

1. Identify Independent Domains

Group failures by what's broken:

• File A tests: Tool approval flow
• File B tests: Batch completion behavior
• File C tests: Abort functionality

Each domain is independent - fixing tool approval doesn't affect abort tests.

2. Create Focused Agent Tasks

Each agent gets:

• Specific scope: One test file or subsystem
• Clear goal: Make these tests pass
• Constraints: Don't change other code
• Expected output: Summary of what you found and fixed

3. Dispatch in Parallel

// In Claude Code / AI environment
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently

4. Review and Integrate

When agents return:

• Read each summary
• Verify fixes don't conflict
• Run full test suite
• Integrate all changes

Agent Prompt Structure

Good agent prompts are:

1. Focused - One clear problem domain
2. Self-contained - All context needed to understand the problem
3. Specific about output - What should the agent return?

Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:

1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0

These are timing/race condition issues. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
   - Replacing arbitrary timeouts with event-based waiting
   - Fixing bugs in abort implementation if found
   - Adjusting test expectations if testing changed behavior

Do NOT just increase timeouts - find the real issue.

Return: Summary of what you found and what you fixed.

Common Parallel Dispatch Mistakes

Too broad: "Fix all the tests" - agent gets lost Specific: "Fix agent-tool-abort.test.ts" - focused scope

No context: "Fix the race condition" - agent doesn't know where Context: Paste the error messages and test names

No constraints: Agent might refactor everything Constraints: "Do NOT change production code" or "Fix tests only"

Vague output: "Fix it" - you don't know what changed Specific: "Return summary of root cause and changes"

When NOT to Use Parallel Dispatch

Related failures: Fixing one might fix others - investigate together first Need full context: Understanding requires seeing entire system Exploratory debugging: You don't know what's broken yet Shared state: Agents would interfere (editing same files, using same resources)

Parallel Dispatch Verification

After agents return:

1. Review each summary - Understand what changed
2. Check for conflicts - Did agents edit same code?
3. Run full suite - Verify all fixes work together
4. Spot check - Agents can make systematic errors

Tidy First Discipline

Separate all changes into two distinct types:

1. STRUCTURAL — Rearranging code without changing behavior
2. BEHAVIORAL — Adding or modifying actual functionality

• Never mix structural and behavioral changes in the same commit
• Always make structural changes first when both are needed
• Commit messages must state whether the commit is structural or behavioral
• Before restructuring or removing existing code, apply Chesterton's Fence (@../../knowledge/principles/chestertons-fence.md): understand why the code exists before changing it

TDD Discipline

Write the test first. Watch it fail. Write minimal code to pass.

Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.

Violating the letter of the rules is violating the spirit of the rules.

When to Use TDD

Always:

• New features
• Bug fixes
• Refactoring
• Behavior changes

Exceptions (ask your human partner):

• Throwaway prototypes
• Generated code
• Configuration files

Thinking "skip TDD just this once"? Stop. That's rationalization.

The Iron Law

NO PRODUCTION CODE WITHOUT A FAILING TEST FIRST

Write code before the test? Delete it. Start over.

No exceptions:

• Don't keep it as "reference"
• Don't "adapt" it while writing tests
• Don't look at it
• Delete means delete

Implement fresh from tests. Period.

Red-Green-Refactor

digraph tdd_cycle {
    rankdir=LR;
    red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"];
    verify_red [label="Verify fails\ncorrectly", shape=diamond];
    green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"];
    verify_green [label="Verify passes\nAll green", shape=diamond];
    refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"];
    next [label="Next", shape=ellipse];

    red -> verify_red;
    verify_red -> green [label="yes"];
    verify_red -> red [label="wrong\nfailure"];
    green -> verify_green;
    verify_green -> refactor [label="yes"];
    verify_green -> green [label="no"];
    refactor -> verify_green [label="stay\ngreen"];
    verify_green -> next;
    next -> red;
}

RED - Write Failing Test

Write one minimal test showing what should happen.

```typescript test('retries failed operations 3 times', async () => { let attempts = 0; const operation = () => { attempts++; if (attempts < 3) throw new Error('fail'); return 'success'; };

const result = await retryOperation(operation);

expect(result).toBe('success'); expect(attempts).toBe(3); });

Clear name, tests real behavior, one thing
</Good>

<Bad>
```typescript
test('retry works', async () => {
  const mock = jest.fn()
    .mockRejectedValueOnce(new Error())
    .mockRejectedValueOnce(new Error())
    .mockResolvedValueOnce('success');
  await retryOperation(mock);
  expect(mock).toHaveBeenCalledTimes(3);
});

Vague name, tests mock not code

Requirements:

• One behavior
• Clear name
• Real code (no mocks unless unavoidable)

Verify RED - Watch It Fail

MANDATORY. Never skip.

npm test path/to/test.test.ts

Confirm:

• Test fails (not errors)
• Failure message is expected
• Fails because feature missing (not typos)

Test passes? You're testing existing behavior. Fix test.

Test errors? Fix error, re-run until it fails correctly.

GREEN - Minimal Code

Write simplest code to pass the test.

```typescript async function retryOperation(fn: () => Promise): Promise { for (let i = 0; i < 3; i++) { try { return await fn(); } catch (e) { if (i === 2) throw e; } } throw new Error('unreachable'); } ``` Just enough to pass ```typescript async function retryOperation( fn: () => Promise, options?: { maxRetries?: number; backoff?: 'linear' | 'exponential'; onRetry?: (attempt: number) => void; } ): Promise { // YAGNI } ``` Over-engineered

Don't add features, refactor other code, or "improve" beyond the test.

Verify GREEN - Watch It Pass

MANDATORY.

npm test path/to/test.test.ts

Confirm:

• Test passes
• Other tests still pass
• Output pristine (no errors, warnings)

Test fails? Fix code, not test.

Other tests fail? Fix now.

REFACTOR - Clean Up

After green only:

• Remove duplication
• Improve names
• Extract helpers

Keep tests green. Don't add behavior.

Repeat

Next failing test for next feature.

Good Tests

Quality	Good	Bad
Minimal	One thing. "and" in name? Split it.	test('validates email and domain and whitespace')
Clear	Name describes behavior	test('test1')
Shows intent	Demonstrates desired API	Obscures what code should do

UC-ID Traceability

When the plan includes Covers: UC-xxx per task, ensure the coder annotates tests with UC-ID comments. This enables the review-coverage mode to verify all use cases are implemented.

The coder agent handles this automatically when given the Covers: field — see @../../agents/mu-coder.md Test Traceability section.

Why Order Matters

"I'll write tests after to verify it works"

Tests written after code pass immediately. Passing immediately proves nothing:

• Might test wrong thing
• Might test implementation, not behavior
• Might miss edge cases you forgot
• You never saw it catch the bug

Test-first forces you to see the test fail, proving it actually tests something.

"I already manually tested all the edge cases"

Manual testing is ad-hoc. You think you tested everything but:

• No record of what you tested
• Can't re-run when code changes
• Easy to forget cases under pressure
• "It worked when I tried it" ≠ comprehensive

Automated tests are systematic. They run the same way every time.

"Deleting X hours of work is wasteful"

Sunk cost fallacy. The time is already gone. Your choice now:

• Delete and rewrite with TDD (X more hours, high confidence)
• Keep it and add tests after (30 min, low confidence, likely bugs)

The "waste" is keeping code you can't trust. Working code without real tests is technical debt.

"TDD is dogmatic, being pragmatic means adapting"

TDD IS pragmatic:

• Finds bugs before commit (faster than debugging after)
• Prevents regressions (tests catch breaks immediately)
• Documents behavior (tests show how to use code)
• Enables refactoring (change freely, tests catch breaks)

"Pragmatic" shortcuts = debugging in production = slower.

"Tests after achieve the same goals - it's spirit not ritual"

No. Tests-after answer "What does this do?" Tests-first answer "What should this do?"

Tests-after are biased by your implementation. You test what you built, not what's required. You verify remembered edge cases, not discovered ones.

Tests-first force edge case discovery before implementing. Tests-after verify you remembered everything (you didn't).

30 minutes of tests after ≠ TDD. You get coverage, lose proof tests work.

Common Rationalizations

Excuse	Reality
"Too simple to test"	Simple code breaks. Test takes 30 seconds.
"I'll test after"	Tests passing immediately prove nothing.
"Tests after achieve same goals"	Tests-after = "what does this do?" Tests-first = "what should this do?"
"Already manually tested"	Ad-hoc ≠ systematic. No record, can't re-run.
"Deleting X hours is wasteful"	Sunk cost fallacy. Keeping unverified code is technical debt.
"Keep as reference, write tests first"	You'll adapt it. That's testing after. Delete means delete.
"Need to explore first"	Fine. Throw away exploration, start with TDD.
"Test hard = design unclear"	Listen to test. Hard to test = hard to use.
"TDD will slow me down"	TDD faster than debugging. Pragmatic = test-first.
"Manual test faster"	Manual doesn't prove edge cases. You'll re-test every change.
"Existing code has no tests"	You're improving it. Add tests for existing code.

TDD Red Flags - STOP and Start Over

• Code before test
• Test after implementation
• Test passes immediately
• Can't explain why test failed
• Tests added "later"
• Rationalizing "just this once"
• "I already manually tested it"
• "Tests after achieve the same purpose"
• "It's about spirit not ritual"
• "Keep as reference" or "adapt existing code"
• "Already spent X hours, deleting is wasteful"
• "TDD is dogmatic, I'm being pragmatic"
• "This is different because..."

All of these mean: Delete code. Start over with TDD.

TDD Bug Fix Example

Bug: Empty email accepted

RED

test('rejects empty email', async () => {
  const result = await submitForm({ email: '' });
  expect(result.error).toBe('Email required');
});

Verify RED

$ npm test
FAIL: expected 'Email required', got undefined

GREEN

function submitForm(data: FormData) {
  if (!data.email?.trim()) {
    return { error: 'Email required' };
  }
  // ...
}

Verify GREEN

$ npm test
PASS

REFACTOR Extract validation for multiple fields if needed.

TDD Verification Checklist

Before marking work complete:

• Every new function/method has a test
• Watched each test fail before implementing
• Each test failed for expected reason (feature missing, not typo)
• Wrote minimal code to pass each test
• All tests pass
• Output pristine (no errors, warnings)
• Tests use real code (mocks only if unavoidable)
• Edge cases and errors covered

Can't check all boxes? You skipped TDD. Start over.

When Stuck

Problem	Solution
Don't know how to test	Write wished-for API. Write assertion first. Ask your human partner.
Test too complicated	Design too complicated. Simplify interface.
Must mock everything	Code too coupled. Use dependency injection.
Test setup huge	Extract helpers. Still complex? Simplify design.

Debugging Integration

Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression.

Never fix bugs without a test.

Testing Anti-Patterns

When adding mocks or test utilities, avoid these common pitfalls:

• Testing mock behavior instead of real behavior
• Adding test-only methods to production classes
• Mocking without understanding dependencies

TDD Final Rule

Production code → test exists and failed first
Otherwise → not TDD

No exceptions without your human partner's permission.

Review Gates

Two-stage review after each task ensures both correctness and quality.

Stage 1: Spec Compliance Review

Before dispatching: verify BASE_SHA and HEAD_SHA are set (git rev-parse). If reviewer returns files in "NOT reviewed" list, re-dispatch for remaining files.

Dispatch reviewer using @../../agents/mu-reviewer.md review-compliance:

• Does the implementation match the task specification?
• Missing requirements?
• Extra features not requested?

If issues found: Implementer fixes, reviewer re-reviews. Repeat until approved.

Must pass before Stage 2. Starting code quality review before spec compliance is approved is wrong order.

Stage 2: Code Quality Review

Before dispatching: verify BASE_SHA and HEAD_SHA are set (git rev-parse). If reviewer returns files in "NOT reviewed" list, re-dispatch for remaining files.

Dispatch reviewer using @../../agents/mu-reviewer.md review-code:

• Code quality, readability, maintainability
• Test quality and coverage
• Error handling, edge cases

If issues found: Implementer fixes, reviewer re-reviews. Repeat until approved.

Final Review

After all tasks complete, chain to mu-review for comprehensive review of entire implementation.

Red Flags

Never:

• Start implementation on main/master branch without explicit user consent
• Switch branches, create branches, or run destructive git commands without verifying current state first (@../../knowledge/principles/git-safety.md)
• Skip reviews (spec compliance OR code quality)
• Proceed with unfixed issues
• Dispatch multiple implementation subagents in parallel (conflicts)
• Make subagent read plan file (provide full text instead)
• Skip scene-setting context (subagent needs to understand where task fits)
• Ignore subagent questions (answer before letting them proceed)
• Accept "close enough" on spec compliance (spec reviewer found issues = not done)
• Skip review loops (reviewer found issues = implementer fixes = review again)
• Let implementer self-review replace actual review (both are needed)
• Start code quality review before spec compliance is approved (wrong order)
• Move to next task while either review has open issues
• Create worktree without verifying it's ignored (project-local)
• Skip baseline test verification
• Proceed with failing baseline tests without asking
• Assume worktree directory location when ambiguous
• Skip CLAUDE.md check for worktree preferences
• Write code before test (TDD violation)
• Write test after implementation (TDD violation)
• Keep code written without TDD as "reference" (delete means delete)
• Skip verifying test fails (RED) or passes (GREEN)
• Rationalize skipping TDD "just this once"
• Dispatch parallel agents for related/coupled failures

If subagent asks questions:

• Answer clearly and completely
• Provide additional context if needed
• Don't rush them into implementation

If reviewer finds issues:

• Implementer (same subagent) fixes them
• Reviewer reviews again
• Repeat until approved
• Don't skip the re-review

If subagent fails task:

• Dispatch fix subagent with specific instructions
• Don't try to fix manually (context pollution)

Integration

• mu-plan creates the plan this skill executes
• Chain to mu-review after all tasks complete
• Agent references: @../../agents/mu-coder.md, @../../agents/mu-reviewer.md