verification-before-completion

name	verification-before-completion
description	Use before claiming work is complete or creating PRs. Run verification commands first; evidence before assertions.
when_to_use	[feedback] Triggered before any completion claim, commit, or PR to verify with evidence.

Verification Before Completion

Overview

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

Loop Detection (Pre-Check)

Before running verification commands, check for doom loops:

bash scripts/loop-detector.sh

Interpret exit codes:

• 0 (OK): Proceed with verification
• 1 (WARNING): Reconsider approach. You may be in a loop. Review recent edits before continuing.
• 2 (HARD STOP): STOP. Do not claim completion. Revert to last known good state or seek external input.

If HARD STOP: Do not proceed with verification. The approach itself needs reconsideration.

Computational Sensors (Pre-Review)

After loop detection, before semantic review, run deterministic checks:

1. Check for .agent-harness/sensors.json:
   • If exists: run each configured sensor
   • If missing: use agent-harness:computational-sensors to set up
2. Run sensors in order: lint → typecheck → test → coverage → build
3. Any sensor failure = verification FAILURE. Do not proceed to semantic review.

Computational before Inferential: Linters and tests catch 80% of issues with zero ambiguity. Run them first.

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

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

• Gate 函数全部通过（loop-detector OK + computational sensors pass + 声称有 fresh evidence）后，emit 阶段 gate（不阻断）：

  scripts/log-phase-metric.sh --phase verification-before-completion --action gate --gate-result passed --spec-topic "$SPEC_TOPIC"