codymaster 7.0.1 → 7.0.3

package/skills/cm-tdd/SKILL.md

@@ -1,7 +1,14 @@
 ---
 name: cm-tdd
-description: Use when implementing any feature or bugfix, before writing implementation code
+description: Use when implementing any feature or bugfix. Routes to the core Red-Green-Refactor loop, test quality guidance, rationalization handling, examples, or stuck-state recovery.
 token_budget: 1500
+token_core: 380
+token_refs:
+  red-green-refactor: 620
+  test-quality: 360
+  rationalizations: 520
+  bugfix-example: 340
+  stuck-debugging: 260
 compressed: true
 deprecated: false
 ---
@@ -9,373 +16,61 @@ deprecated: false
 # Test-Driven Development (TDD)
 
 ## TL;DR
-- **Use when** writing or fixing any feature/bugfix
-- **Cycle**: red (failing test) → green (minimal code) → refactor
-- **No prod code** without a failing test first
-- **Next**: cm-execution or cm-code-review
-
-## Overview
-
-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.**
+- **Use when** writing or fixing code
+- **Cycle**: Red → Green → Refactor
+- **Rule**: no production code without a failing test first
+- **Next**: `cm-execution` or `cm-code-review`
 
 ## When to Use
-
-**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.
+- new features
+- bug fixes
+- refactors
+- behavior changes
 
 ## The Iron Law
-
-```
+```text
 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
-
-```dot
-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;
-}
-```
-
-### Step 0: Check Working Memory
-
-Before writing ANY test, check `.cm/CONTINUITY.md`:
-
-- **"Mistakes & Learnings"** → Are there known edge cases for this area?
-- **"Working Context"** → What patterns/conventions are being followed?
-- **"Key Decisions"** → Any architecture choices that affect test design?
-
-> **Token savings:** Writes better tests on first try by knowing past failures.
-> **Quality boost:** Tests cover edge cases that caused bugs before.
-
-### 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.**
-
-```bash
-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.**
-
-```bash
-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                        |
-
-
-## 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.                       |
-
-
-## 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.**
-
-## Example: Bug Fix
-
-**Bug:** Empty email accepted
-
-**RED**
-
-```typescript
-test('rejects empty email', async () => {
-  const result = await submitForm({ email: '' });
-  expect(result.error).toBe('Email required');
-});
-```
-
-**Verify RED**
-
-```bash
-$ npm test
-FAIL: expected 'Email required', got undefined
-```
-
-**GREEN**
-
-```typescript
-function submitForm(data: FormData) {
-  if (!data.email?.trim()) {
-    return { error: 'Email required' };
-  }
-  // ...
-}
-```
-
-**Verify GREEN**
+## Choose the Need
 
-```bash
-$ npm test
-PASS
 ```
+Need to execute the normal TDD loop?
+└─ YES → Red-Green-Refactor
 
-**REFACTOR**
-Extract validation for multiple fields if needed.
-
-## 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
-
+Need help designing or reviewing test quality?
+└─ YES → Test Quality
 
-| 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.                     |
+Need to counter "skip TDD" rationalizations?
+└─ YES → Rationalizations
 
+Need a worked bug-fix example?
+└─ YES → Bugfix Example
 
-## Debugging Integration
-
-Bug found? Write failing test reproducing it. Follow TDD cycle. Test proves fix and prevents regression.
-
-Never fix bugs without a test.
-
-## Karpathy Discipline — Goal-Driven Execution
-
-TDD is the canonical form of goal-driven execution. Reinforce it:
-- **Translate vague tasks into verifiable goals before writing code.**
-  - "Add validation" → "Test invalid inputs fail; valid inputs pass."
-  - "Fix the bug" → "Test reproduces it red; fix turns it green."
-  - "Refactor X" → "Same tests green before and after."
-- **Strong success criteria let you loop independently.** Weak criteria ("make it work") force the user to babysit.
-- **Minimum code to pass.** Don't over-implement to "anticipate" the next test — write that test first.
-
-## Final Rule
-
-```
-Production code → test exists and failed first
-Otherwise → not TDD
+Are you blocked or unsure how to continue?
+└─ YES → Stuck / Debugging
 ```
 
-No exceptions without your human partner's permission.
+| Need | Summary | Load |
+|---|---|---|
+| Normal execution | core TDD loop and verification | `references/red-green-refactor.md` |
+| Test quality | what good tests look like | `references/test-quality.md` |
+| Reinforcement | anti-rationalization guidance | `references/rationalizations.md` |
+| Example | concrete bug-fix walkthrough | `references/bugfix-example.md` |
+| Recovery | how to proceed when stuck | `references/stuck-debugging.md` |
+
+## Load Rules
+- Load `red-green-refactor.md` for normal execution.
+- Load `test-quality.md` when designing or reviewing tests.
+- Load `rationalizations.md` only when the user or agent is trying to bypass TDD discipline.
+- Load `bugfix-example.md` only for coaching or example use.
+- Load `stuck-debugging.md` only when blocked.
+
+## Non-Negotiables
+- Watch the test fail before writing production code.
+- Keep implementation minimal until green.
+- Refactor only after green.
+- Re-run verification after each meaningful change.
+
+## The Bottom Line
+**Write the failing test first. Pass it minimally. Refactor only after green.**

package/skills/cm-tdd/references/bugfix-example.md

@@ -0,0 +1,15 @@
+# Bugfix Example
+
+> Use when a concrete example helps teach or reinforce the loop.
+
+## Example Shape
+1. Reproduce the bug with a failing test
+2. Verify the failure matches the bug
+3. Implement the smallest fix
+4. Re-run the failing test and nearby tests
+5. Refactor if needed after green
+
+## Why It Helps
+- shows how to start from symptoms
+- demonstrates proof before implementation
+- gives a concrete mental model for bug-fix TDD

package/skills/cm-tdd/references/rationalizations.md

@@ -0,0 +1,20 @@
+# Common Rationalizations
+
+> Load only when discipline is slipping and TDD needs reinforcement.
+
+## Common Excuses
+- too simple to test
+- I already tested manually
+- I will add tests after
+- deleting the existing code is wasteful
+- being pragmatic means skipping process
+
+## Response Pattern
+- manual testing is not repeatable
+- tests-after do not prove the test would have caught the bug
+- passing immediately proves very little
+- code without trusted tests is technical debt
+- pragmatic shortcuts usually move cost into debugging later
+
+## Rule
+Do not let convenience arguments silently replace the process.

package/skills/cm-tdd/references/red-green-refactor.md

@@ -0,0 +1,33 @@
+# Red-Green-Refactor
+
+> Default reference for normal TDD execution.
+
+## Step 0: Check Working Memory
+- review known edge cases in continuity
+- review working context and key decisions
+
+## RED
+1. Write one failing test for one behavior.
+2. Make sure it fails for the expected reason.
+
+## VERIFY RED
+- run the specific test
+- confirm failure is meaningful, not a typo or setup issue
+
+## GREEN
+1. Write the simplest code that passes.
+2. Avoid speculative options, helpers, or extra behavior.
+
+## VERIFY GREEN
+- rerun the test
+- confirm it passes cleanly
+- confirm related tests still pass if relevant
+
+## REFACTOR
+- improve names
+- reduce duplication
+- keep behavior unchanged
+- rerun tests after cleanup
+
+## Rule
+If you did not see the test fail, you do not know that it tests the right thing.

package/skills/cm-tdd/references/stuck-debugging.md

@@ -0,0 +1,18 @@
+# Stuck / Debugging
+
+> Use when the TDD loop stalls.
+
+## When Stuck
+- simplify the failing scenario
+- isolate one behavior
+- verify the test harness itself
+- reduce mocks
+- use `cm-debugging` if the root cause is unclear
+
+## Escalation
+- if repeated failures do not clarify the issue
+- if you cannot produce a meaningful failing test
+- if the system under test is too tangled to isolate quickly
+
+## Rule
+When blocked, simplify before expanding.

package/skills/cm-tdd/references/test-quality.md

@@ -0,0 +1,19 @@
+# Test Quality
+
+> Use when designing or reviewing tests.
+
+## Good Tests
+- one behavior per test
+- clear name
+- behavior-focused, not implementation-biased
+- minimal mocking unless unavoidable
+- readable enough to act as usage documentation
+
+## Bad Test Signals
+- vague names like `test1`
+- multiple behaviors in one assertion cluster
+- mocks proving the mock, not the real behavior
+- tests that pass before the feature is written
+
+## Rule
+If a test name contains “and”, it probably wants to be split.