version: "1.0.0" name: sentinel description: Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Verification Before Completion

Overview

SENTINEL — A sentinel stands at the gate and lets nothing through without challenge. When invoked: blocks any claim of "done" until fresh verification evidence exists — tests run, output checked, edge cases confirmed. No evidence, no completion.

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.

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

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

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

Why This Matters

From 24 failure memories:

• your human partner said "I don't believe you" - trust broken
• 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."

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

Confidence Scoring Gate

After verification passes, score your own confidence BEFORE marking complete:

CONFIDENCE SELF-ASSESSMENT
━━━━━━━━━━━━━━━━━━━━━━━━━━
Ask yourself:
1. Do all edge cases have test coverage?     [Yes/No/Partial]
2. Do I fully understand why the fix works?  [Yes/No]
3. Are there side effects I haven't tested?  [Yes/No]
4. Would I be comfortable in a code review?  [Yes/No]
━━━━━━━━━━━━━━━━━━━━━━━━━━

Score → Action:

Announce score:

CONFIDENCE: HIGH / MEDIUM / LOW
Action: [proceeding / requesting code review / re-investigating]

Never suppress a MEDIUM or LOW score to avoid review. That is the same as lying.

The Bottom Line

No shortcuts for verification. No suppressed confidence.

Run the command. Read the output. Score your confidence. THEN claim the result.

This is non-negotiable.