Boundary: End-to-end bug entry point — history check → RCA (via diagnose-root) → fix approach → TDD plan → bug file. Delegates the 4-phase RCA to diagnose-root; does not re-implement it.

Investigate a reported problem, find its root cause, and write a TDD fix plan to specs/bugs/BUG-*.md. This is a mostly hands-off workflow — minimize questions to the user.

Before starting diagnosis:

1. Read specs/bugs/registry.yaml (if it exists) — check for prior bugs in the same scope or with similar symptoms.
2. If a relevant prior bug is found, read the corresponding specs/bugs/BUG-*.md file to understand previous root cause analysis and fix approach.
3. Note in your investigation whether this is a recurrence, a related issue, or novel.

Get a brief description of the issue from the user. If they haven’t provided one, ask ONE question: “What’s the problem you’re seeing?”

Do NOT ask follow-up questions yet. Start investigating immediately.

Security-impact assessment — After capturing the problem, assess and document: Security impact: NONE / LOW / MEDIUM / HIGH / CRITICAL. If HIGH or CRITICAL, assign bug severity HIGH and document the exploit path in findings. If MEDIUM+, include exploit path in the bug file. Document “no security exploit path identified” for NONE/LOW.

Run the 4-phase root-cause analysis via the diagnose-root skill (Reproduce → Isolate → Hypothesize → Verify). That skill is the canonical RCA engine — do not re-implement the phases here.

Also look at:

• Recent changes to affected files (git log --oneline <file>)
• Existing tests (what’s tested, what’s missing)
• Similar patterns elsewhere in the codebase that work correctly

HARD GATE — Do NOT proceed to Step 3 (Fix Approach) until diagnose-root Phase 4 produces a verified root cause. “It probably is X” is not verified.

Based on your investigation, determine:

• The minimal change needed to fix the root cause
• Which modules/interfaces are affected
• What behaviors need to be verified via tests
• Whether this is a regression, missing feature, or design flaw
• Risk level: Low / Medium / High

Create a concrete, ordered list of RED-GREEN cycles. Each cycle is one vertical slice:

• RED: Describe a specific test that captures the broken/missing behavior
• GREEN: Describe the minimal code change to make that test pass

Rules:

• Tests verify behavior through public interfaces, not implementation details
• One test at a time, vertical slices (NOT all tests first, then all code)
• Each test should survive internal refactors
• Include a final refactor step if needed
• Durability: Only suggest fixes that would survive radical codebase changes. Tests assert on observable outcomes (API responses, UI state, user-visible effects), not internal state.

Save the investigation and fix plan to specs/bugs/BUG-NNN-slug.md. Create the specs/bugs/ directory if it doesn’t exist.

After writing, append a row to specs/bugs/registry.yaml with: bug_id (same timestamp), date, severity, priority, scope, summary, and file path. Create specs/bugs/registry.yaml if it doesn’t exist.

<diagnosis-template>

A clear description of the bug or issue, including:

• What happens (actual behavior)
• What should happen (expected behavior)
• How to reproduce (if applicable)

Describe what you found during investigation:

• The code path involved
• Why the current code fails
• Any contributing factors
• Risk level: Low / Medium / High

Do NOT include specific file paths, line numbers, or implementation details that couple to current code layout. Describe modules, behaviors, and contracts instead.

A numbered list of RED-GREEN cycles:

1. RED: Write a test that [describes expected behavior] GREEN: [Minimal change to make it pass] verify: [runnable command]

2. RED: Write a test that [describes next behavior] GREEN: [Minimal change to make it pass] verify: [runnable command]

REFACTOR: [Any cleanup needed after all tests pass]

• Criterion 1
• Criterion 2
• All new tests pass
• Existing tests still pass

<!– filled in by validate-fix –>

</diagnosis-template>

After writing the bug file, print a one-line summary of the root cause and suggest running kickoff-branch next to create a fix branch.

<!– story: e35s10 –>

• Feathers’ Seams & Characterization Tests — seam types, characterization tests, and the legacy code change algorithm
• Fowler’s Code Smells — identifying structural problems by smell before investigating