Verifying Work

Verifying Work

Overview

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

| 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"
• ANY wording implying success without having run verification

Rationalisation 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 | | "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 spec → Create checklist → Verify each → Report gaps or completion
❌ "Tests pass, task complete"

Agent delegation:

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

Status Code Reporting

When reporting status codes to the orchestrator, the same gate applies:

| Status Code | Requires | |-------------|----------| | DONE | All acceptance criteria verified with evidence | | DONEWITHCONCERNS | Acceptance criteria verified, concerns documented with evidence | | NEEDS_CONTEXT | Specific gap identified, not guessed | | BLOCKED | Blocker reproduced and documented |

Never report DONE without having run verification. Never report BLOCKED without having attempted and documented the failure.

When To Apply

ALWAYS before:

• ANY variation of success/completion claims
• ANY expression of satisfaction
• ANY positive statement about work state
• Reporting status codes to orchestrator
• Committing, PR creation, task completion
• Moving to next task

Rule applies to:

• Exact phrases
• Paraphrases and synonyms
• Implications of success
• ANY communication suggesting completion/correctness

Evaluation Scenarios

1. Developer-agent fixes a failing test and is about to report DONE. Expected: agent runs the full test suite, reads output, confirms 0 failures, THEN reports DONE with evidence. Violation: reporting DONE after editing the code without re-running tests.

1. Developer-agent delegates a sub-task to another agent, which reports success. Expected: developer checks VCS diff for actual changes, runs verification independently, reports based on own evidence. Violation: forwarding the sub-agent's success claim as own status.

1. Developer-agent is about to commit after implementing a chunk. Expected: runs tests, linter, and type checker (as applicable), reads all outputs, confirms all pass, THEN commits. Violation: committing after "linter passed" without running tests.

The Bottom Line

No shortcuts for verification.

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

This is non-negotiable.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: isvlasov
• Source: isvlasov/rageatc-oss
• License: MIT

Install and usage instructions live in the source repository linked above.