Use when about to claim work is complete, fixed, or passing; run verification and read the output before any success claim.
The English summary is being prepared. Showing the original description.
See how to installReview the instructions the agent will receive before you install.
Evidence before claims. Run the command, read the output, THEN claim the result. No shortcuts. No "should work." No exceptions.
$codex-verification-discipline, $verify, or $evidence.Announce at start: "I'm verifying before claiming completion."
NO COMPLETION CLAIMS WITHOUT FRESH VERIFICATION EVIDENCE
If you haven't run the verification command in this message, you cannot claim it passes.
Violating the letter of this rule is violating the spirit of this rule.
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
| 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 |
If you catch yourself thinking or writing:
| Excuse | Reality |
|---|---|
| "Should work now" | RUN the verification |
| "I'm confident" | Confidence ≠ evidence |
| "Just this once" | No exceptions |
| "Linter passed" | Linter ≠ compiler ≠ tests |
| "Agent said success" | Verify independently |
| "Partial check is enough" | Partial proves nothing |
| "Different words so rule doesn't apply" | Spirit over letter |
| "It's trivial" | Trivial things break. Run it. |
Tests:
✅ [Run test command] → [See: 34/34 pass] → "All tests pass"
❌ "Should pass now" / "Looks correct"
Regression tests (TDD Red-Green):
✅ Write → Run (FAIL) → Implement → Run (PASS) → "Regression test verified"
❌ "I've written a regression test" (without red-green verification)
Build:
✅ [Run build] → [See: exit 0] → "Build passes"
❌ "Linter passed" (linter ≠ build)
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
ALWAYS before:
| Skill | How Verification Integrates |
|---|---|
codex-test-driven-development | Verify RED and GREEN steps with actual test output |
codex-execution-quality-gate | Gate scripts provide the evidence; this skill ensures you actually READ the output |
codex-systematic-debugging | Verify root cause fix with regression test evidence |
codex-subagent-execution | Verify subagent output with VCS diff, not agent reports |
codex-branch-finisher | Verify tests before presenting completion options |
--help first.No shortcuts for verification.
Run the command. Read the output. THEN claim the result.
This is non-negotiable.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work — guides completion of development work by presenting structured options for merge, PR, or cleanup
The English summary is being prepared. Showing the original description.
Use when a project has 50+ files, missing context, or explicit $codex-genome request; generates multi-layer project context to reduce hallucination.
The English summary is being prepared. Showing the original description.
Use for DESIGN.md visual identity contracts; author, scaffold, lint, diff, and export design contracts with the upstream spec and CLI.
The English summary is being prepared. Showing the original description.
Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks.
The English summary is being prepared. Showing the original description.
Use when code changes may require documentation updates; maps git diff to candidate docs without auto-editing documentation.
The English summary is being prepared. Showing the original description.
Use for documents, reports, memos, guides, academic papers, or formal text that needs clear structure, reliable tone, formatting, and diagrams.
The English summary is being prepared. Showing the original description.