---
name: mastermind-verify
description: Mastermind verification gate — enforces evidence-before-claims before any completion, commit, PR, or agent-delegation step. The Iron Law of verification.
type: domain-skill
default_mode: auto
---

# Mastermind Verify

This skill is invoked by `mastermind:master` or directly via `/mastermind:verify`.

Claiming work is complete without verification is dishonesty, not efficiency.

**Core principle:** Evidence before claims, always.

**Violating the letter of this rule is violating the spirit of this rule.**

---

## Inputs

- `brain_context`: BRAIN CONTEXT block (injected by master, or loaded standalone via mastermind-protocol/SKILL.md brain load)
- `prompt`: what to verify and what claim is being made
- `project_name`: monotask space name
- `board_id`: monotask board ID (set by master, or created standalone)
- `mode`: auto | confirm

---

## The Iron Law

```
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
```

If you haven't run the verification command in this message, you cannot claim it passes.

---

## The Gate Function

```
BEFORE claiming any status or expressing satisfaction:

1. IDENTIFY: What command proves this claim?
2. RUN: Execute the FULL command (fresh, complete)
3. READ: Full output, check exit code, count failures
4. VERIFY: Does output confirm the claim?
   - If NO: State actual status with evidence
   - If YES: State claim WITH evidence
5. ONLY THEN: Make the claim

Skip any step = lying, not verifying
```

---

## Common Failures

| Claim | Requires | Not Sufficient |
|-------|----------|----------------|
| Tests pass | Test command output: 0 failures | Previous run, "should pass" |
| Linter clean | Linter output: 0 errors | Partial check, extrapolation |
| Build succeeds | Build command: exit 0 | Linter passing, logs look good |
| Bug fixed | Test original symptom: passes | Code changed, assumed fixed |
| Regression test works | Red-green cycle verified | Test passes once |
| Agent completed | VCS diff shows changes | Agent reports "success" |
| Requirements met | Line-by-line checklist | Tests passing |

---

## Red Flags - STOP

- Using "should", "probably", "seems to"
- Expressing satisfaction before verification ("Great!", "Perfect!", "Done!", etc.)
- About to commit/push/PR without verification
- Trusting agent success reports
- Relying on partial verification
- Thinking "just this once"
- Tired and wanting work over
- **ANY wording implying success without having run verification**

---

## Rationalization Prevention

| Excuse | Reality |
|--------|---------|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler |
| "Agent said success" | Verify independently |
| "I'm tired" | Exhaustion ≠ excuse |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |

---

## Key Patterns

**Tests:**
```
✅ [Run test command] [See: 34/34 pass] "All tests pass"
❌ "Should pass now" / "Looks correct"
```

**Regression tests (TDD Red-Green):**
```
✅ Write → Run (pass) → Revert fix → Run (MUST FAIL) → Restore → Run (pass)
❌ "I've written a regression test" (without red-green verification)
```

**Build:**
```
✅ [Run build] [See: exit 0] "Build passes"
❌ "Linter passed" (linter doesn't check compilation)
```

**Requirements:**
```
✅ Re-read plan → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, phase complete"
```

**Agent delegation:**
```
✅ Agent reports success → Check VCS diff → Verify changes → Report actual state
❌ Trust agent report
```

---

## Execution

### Complexity Assessment

**Simple (direct verification):** Single command, one claim:
- "Do the tests pass?"
- "Does the build succeed?"
- Run the command, report the output.

**Complex (multi-gate verification):** Multiple claims or multi-step requirements:
- "Is this feature complete?" → decompose into requirement checklist, run each gate
- Spawn a Verification Coordinator if needed

### Steps

1. **Parse the claim or task being verified.** If the prompt is empty or vague, ask: "What claim or task needs verification?"

2. **Identify all verification gates.** For each claim, determine the exact command that proves or disproves it.

3. **Run each gate fresh.** Execute commands in this session. Do not rely on prior output.

4. **Collect evidence.** Exit code, line counts, failure messages, diff output.

5. **Report findings with evidence.** Never summarize without quoting relevant output.

---

## When To Apply

**ALWAYS before:**
- ANY variation of success/completion claims
- ANY expression of satisfaction
- ANY positive statement about work state
- Committing, PR creation, task completion
- Moving to next task
- Delegating to agents

**Rule applies to:**
- Exact phrases
- Paraphrases and synonyms
- Implications of success
- ANY communication suggesting completion/correctness

---

## Why This Matters

From failure patterns:
- Trust broken when claiming done without checking
- Undefined functions shipped — would crash
- Missing requirements shipped — incomplete features
- Time wasted on false completion → redirect → rework
- Violates: "Honesty is a core value. If you lie, you'll be replaced."

---

## The Bottom Line

**No shortcuts for verification.**

Run the command. Read the output. THEN claim the result.

This is non-negotiable.