@sleepy-ai/cli 0.0.0-main-202607032053 → 0.1.4

package/src/skill/compose/.bundle/subagent/spec-reviewer-prompt.md

@@ -0,0 +1,118 @@
+# Spec Compliance Reviewer Prompt Template
+
+Use this template when dispatching a spec compliance reviewer subagent.
+
+**Purpose:** Verify the implementation matches the spec it claims to cover — nothing
+missing, nothing misinterpreted, nothing extra — and return a machine-checkable
+verdict the controller can gate on.
+
+This reviewer runs in **two phases**. Dispatch phase 1 first. Dispatch phase 2 only
+if phase 1 flags anything (if phase 1 is all-pass there is nothing to downgrade, so
+skip phase 2).
+
+## Phase 1 — independent judgment (no implementer report)
+
+Dispatch with the spec section text and the diff ONLY. Do NOT include the
+implementer's report — its claims would anchor the reviewer toward confirming what
+was reported and away from finding what was silently omitted.
+
+Dispatch a spec-compliance reviewer as a `general` subagent via the `actor` tool,
+following the syntax in that tool's own description. Use a title like "Spec
+review Task N — phase 1" and give it this prompt:
+
+~~~
+You are verifying whether an implementation matches its specification. Judge
+INDEPENDENTLY. You are given the spec sections the task must satisfy and the
+code diff — nothing else. There is deliberately no implementer report; do not
+ask for one.
+
+## Spec sections this task covers
+
+[Controller pastes verbatim text of the covered [Sn] spec sections]
+
+## Git range to review
+
+[If the work was done in an isolated worktree, add a line here: "Run all commands
+from `<worktree path>` — `cd` there first." Omit this if there's no separate
+worktree; the current checkout is correct by default.]
+
+**Base:** {BASE_SHA}
+**Head:** {HEAD_SHA}
+
+```bash
+git diff {BASE_SHA}..{HEAD_SHA}
+```
+
+## Your job
+
+1. Read each covered spec section and enumerate the distinct, checkable CLAIMS
+   inside it (a section usually contains several). A claim is one verifiable
+   statement about required behavior.
+2. For each claim, decide if it is in scope for THIS task. The task covers a
+   subset of the section; claims other tasks own are out of scope here.
+3. For each in-scope claim, verify it against the diff. Remember: the diff shows
+   what changed, not what is missing. A required behavior with no corresponding
+   code is a FAIL even though no diff line points to it — actively look for
+   omissions.
+4. Evidence is mandatory. A claim's status is backed by a test name, command
+   execution output, or a `file:line` reference. A status asserted without such
+   evidence is `fail`. Prose like "looks implemented" is NOT evidence.
+5. If a claim describes runtime behavior you cannot judge from the diff alone,
+   run the relevant test or command and cite the output. If you cannot verify it,
+   mark it `unverifiable` — never a silent pass.
+
+## Output format (return EXACTLY this structure)
+
+**Status**: pass | fail
+(pass only if every in-scope claim is `pass` with evidence)
+
+**Claims**:
+- [Sn · "<short claim text>"] in-scope · status: pass
+  evidence: <test name | command output | file:line>
+- [Sn · "<short claim text>"] in-scope · status: fail
+  evidence: <what's missing or wrong, with file:line if applicable>
+- [Sn · "<short claim text>"] out-of-scope-for-this-task
+- [Sn · "<short claim text>"] in-scope · status: unverifiable
+  evidence: <why it can't be verified from available material>
+
+**Extra work not traced to any covered claim**:
+- <file:line — what was built that no covered claim required, or "(none)">
+~~~
+
+## Phase 2 — rationale reconciliation (sees the report)
+
+Only if phase 1 flagged any `fail`, `unverifiable`, or extra work. Give the SAME
+reviewer its phase-1 verdict plus the implementer's report. The report may explain a
+flagged diff ("that odd line is a deliberate decision described in my report").
+
+Dispatch the same reviewer again as a `general` subagent via the `actor` tool,
+with a title like "Spec review Task N — phase 2", and this prompt:
+
+~~~
+Here is your phase-1 verdict and the implementer's report. Use the report ONLY
+to explain items you flagged. You may downgrade a flagged item to a phase-2 note
+if the report justifies it. You CANNOT add new passes and CANNOT upgrade a
+`fail` to `pass` — a report claim is not evidence. If a fail genuinely needs
+re-verification with fresh evidence (test/exec/file:line), that belongs in a new
+phase-1 re-review after the implementer acts, not here.
+
+## Your phase-1 verdict
+[paste phase-1 output]
+
+## Implementer report
+[paste implementer's report]
+
+## Output format
+**Status**: pass | fail  (unchanged unless a downgrade clears the last failure)
+**Claims**: [same structure as phase 1, with any downgraded items annotated]
+**Phase-2 notes**:
+- [Sn · "<claim>"] downgraded: <report's justification> — was: <prior status>
+~~~
+
+**Placeholders:** `{BASE_SHA}`, `{HEAD_SHA}` — commit range for this task. If an
+isolated worktree was used, also add a `cd <worktree path>` instruction (see the
+note in the Git range section); otherwise the current checkout is correct.
+
+**Reviewer returns:** structured Status + per-claim verdicts. The controller gates on
+this (see `compose:subagent`): the task is not complete while any in-scope claim is
+`fail` or `unverifiable`.

package/src/skill/compose/.bundle/tdd/SKILL.md

@@ -0,0 +1,360 @@
+---
+name: compose:tdd
+hidden: true
+description: Use when implementing any feature or bugfix, before writing implementation code
+---
+
+# Test-Driven Development (TDD)
+
+## 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.**
+
+## When to Use
+
+**Always:**
+- New features
+- Bug fixes
+- Refactoring
+- Behavior changes
+
+**Exceptions (raise them through `compose:ask`; if no user is available, use your best judgment and proceed):**
+- 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
+
+**The cycle:** RED → verify fails → GREEN → verify passes → REFACTOR → verify still green → next test → RED …
+
+1. **RED** — Write one failing test
+   - Verify it fails correctly (wrong failure → fix the test, back to RED)
+2. **GREEN** — Write minimal code to pass
+   - Verify all tests pass (still failing → keep coding, stay in GREEN)
+3. **REFACTOR** — Clean up while staying green
+   - Verify tests still pass after each cleanup (broke something → undo, stay in REFACTOR)
+4. **Next** — back to RED with the next behavior
+
+### RED - Write Failing Test
+
+Write one minimal test showing what should happen.
+
+<Good>
+```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
+</Bad>
+
+**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.
+
+<Good>
+```typescript
+async function retryOperation<T>(fn: () => Promise<T>): Promise<T> {
+  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
+</Good>
+
+<Bad>
+```typescript
+async function retryOperation<T>(
+  fn: () => Promise<T>,
+  options?: {
+    maxRetries?: number;
+    backoff?: 'linear' | 'exponential';
+    onRetry?: (attempt: number) => void;
+  }
+): Promise<T> {
+  // YAGNI
+}
+```
+Over-engineered
+</Bad>
+
+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**
+```bash
+$ npm test
+PASS
+```
+
+**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
+
+| Problem | Solution |
+|---------|----------|
+| Don't know how to test | Write wished-for API. Write assertion first. Ask through `compose:ask`; if no user is available, use the simplest testable approach. |
+| 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, read @testing-anti-patterns.md to avoid common pitfalls:
+- Testing mock behavior instead of real behavior
+- Adding test-only methods to production classes
+- Mocking without understanding dependencies
+
+## Final Rule
+
+```
+Production code → test exists and failed first
+Otherwise → not TDD
+```
+
+No exceptions without your human partner's permission.