Skill: /diagnose — Complex Bug Diagnostic Pipeline

When to invoke (and when NOT to)

Use /diagnose when:

• Bug reproduces but root cause is unclear after one read-pass of the failing code
• Previous fix attempts have been reverted ≥ 2 times (symptoms return)
• Failure is intermittent (flaky test, race condition, timing-dependent)
• Failure occurs in unfamiliar code (agent has no prior context)
• User has explicitly requested /diagnose or "deep investigation"
• Circuit Breaker (Rule 14) tripped on the specialist agent that normally handles this domain

Do NOT use /diagnose when:

• Cause is obvious (null ref, typo, missing import, incorrect import path)
• Fix is < 10 LOC and has a clear success check
• Bug is in code you just wrote this session (read-pass + local reasoning is faster)
• User wants a quick patch and has accepted the tradeoff

Pipeline overview

Feedback Loop -> Investigation -> Verification -> Solution -> Lead Programmer
  (signal)         (hypothesis)    (devil's adv.)   (tradeoffs)   (assign + exec)

  repro/check command      investigation.json      verification.json      solution.json          implementation
  (fast deterministic      (root_cause,           (status: confirmed |    (3 options:           (delegates to
   pass/fail signal)       evidence[],            refuted | inconclusive, Quick/Strategic/     backend-developer,
                           confidence)            reproduction_steps)    Future-Proof)         qa-engineer, etc.)

Each stage produces a required artifact saved to .investigations/<task_id>/ and a handoff contract (per Rule 16) to the next agent.

Stage 0 — Feedback Loop

Goal: Build the fastest reliable pass/fail signal for the exact symptom before explaining the cause.

The feedback loop is the highest-leverage part of diagnosis. Do not proceed to root-cause analysis until there is a loop that can reproduce the user's symptom or a documented reason why no loop is possible.

Try these in roughly this order:

1. Failing test at the seam that reaches the bug.
2. CLI or script invocation with fixture input and expected output.
3. Curl/HTTP request against a running service.
4. Headless browser script with DOM, console, or network assertions.
5. Replay of a captured payload, event, HAR, log, or trace.
6. Throwaway harness that calls the affected code path in isolation.
7. Property/fuzz loop for broad wrong-output symptoms.
8. Bisection or differential loop between known-good and known-bad states.

Improve the loop before investigating:

• Faster: remove unrelated setup and narrow the command.
• Sharper: assert the specific symptom, not merely "does not crash".
• More deterministic: pin time, seed randomness, isolate filesystem/network, or raise intermittent reproduction frequency with stress runs.

Do not treat Stage 0 as warm-up. It is the main leverage point. A bad loop produces fake certainty, weak hypotheses, and symptom-only fixes.

If no credible loop can be built, stop and report what was tried. Ask for access to the reproducing environment, a captured artifact, or permission to add temporary instrumentation. Do not proceed on a vibe.

Stage 1 — Investigation

Agent: diagnostics (Investigation role) Goal: Produce ranked falsifiable root-cause hypotheses backed by empirical evidence.

Inputs

• Symptom description (from user or TODO.md bug ID)
• Reproduction steps (or "cannot reproduce" + environment)
• Relevant log lines, stack traces, error IDs
• Feedback loop command/check from Stage 0, or a documented reason no loop can currently be built

Required output — investigation.json

{
  "task_id": "BUG-417",
  "symptom": "POST /api/orders returns 500 when cart has ≥10 items",
  "reproduction": {
    "steps": ["...", "..."],
    "frequency": "100% | intermittent (~30%) | once",
    "environment": "staging-eu-west-1"
  },
  "feedback_loop": {
    "command": "npm test -- checkout.e2e.test.ts",
    "signal": "Fails with timeout before hydration marker appears",
    "reliable": true
  },
  "ranked_hypotheses": [
    {
      "rank": 1,
      "cause": "Test clicks #submit before React hydration completes on slow CI runners",
      "prediction": "Waiting for the hydration marker will make the failure disappear without adding a fixed sleep"
    },
    {
      "rank": 2,
      "cause": "Submit button selector matches a hidden stale node",
      "prediction": "Asserting the visible button count will expose multiple matching nodes"
    }
  ],
  "hypothesis": {
    "root_cause": "OrderService.calculateTotal() N+1 query exhausts pool when cart.items.length > 9",
    "confidence": "high | medium | low",
    "falsifiable_by": "Run with pool_size=50; if error disappears, cause confirmed"
  },
  "evidence": [
    {"type": "log", "ref": ".investigations/BUG-417/pg-pool-exhausted.log", "summary": "..."},
    {"type": "code", "ref": "src/services/order.service.ts:142", "summary": "Unbounded .map+await"}
  ],
  "unknowns": ["Why only eu-west-1?", "When did this start?"],
  "next_agent": "diagnostics",
  "next_stage": "verification"
}

Quality gate (Lead Programmer rejects if):

• feedback_loop is missing and no blocked-loop explanation exists
• feedback_loop.signal is vague, broad, or does not isolate the user's symptom
• ranked_hypotheses has fewer than 3 items unless the evidence makes a single cause unavoidable
• Any hypothesis lacks a falsifiable prediction
• hypothesis.falsifiable_by is vague ("check if it works")
• evidence has fewer than 2 items (unverifiable)
• unknowns is empty but confidence: low (contradictory)

Stage 2 — Verification

Agent: diagnostics (Verification role) Goal: Attempt to refute the hypothesis. Only confirmed if refutation fails.

Inputs

• investigation.json (from Stage 1)
• Access to staging/test environment
• The Stage 0 feedback loop, rerun before and after each meaningful probe

Verification is invalid if it does not go back through the Stage 0 loop. A fix-looking local observation that bypasses the loop is not confirmation.

Required output — verification.json

{
  "task_id": "BUG-417",
  "status": "confirmed | refuted | inconclusive",
  "triangulation": [
    {"method": "reproduce_with_fix_applied", "result": "Error gone with pool_size=50"},
    {"method": "reproduce_without_fix", "result": "Error returns at 10 items"},
    {"method": "adjacent_test_case", "result": "9 items = OK, 10 items = fail → threshold confirmed"}
  ],
  "counter_hypotheses_ruled_out": [
    "DB slowness (ruled out: p99 < 50ms)",
    "Network flaps (ruled out: no packet loss in window)"
  ],
  "confidence": "high",
  "recommendation": "Proceed to Solution stage — cause confirmed necessary AND sufficient"
}

Decision flow

Stage 3 — Solution

Agent: diagnostics (Solution role) Goal: Generate 3 solution options with explicit tradeoffs; never pick silently.

Required output — solution.json

{
  "task_id": "BUG-417",
  "options": [
    {
      "name": "Quick",
      "description": "Increase pool_size from 20 → 50 in db.ts",
      "scope_loc": 1,
      "risk_tier": "Low",
      "tradeoff": "Masks root cause; higher RAM; future growth hits same wall"
    },
    {
      "name": "Strategic",
      "description": "Rewrite calculateTotal() to batch via IN-clause",
      "scope_loc": 40,
      "risk_tier": "Medium",
      "tradeoff": "Fixes N+1 permanently; requires regression test on discount l