Lie detector for agent claims — validates every completion claim has actual evidence. Default-FAIL mindset. Use as final gate before merge/commit.
How to install completion-gate?
rune-kit/rune/completion-gate
$curl -o .claude/agents/completion-gate.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/completion-gate.mdInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install completion-gate by running `curl -o .claude/agents/completion-gate.md https://raw.githubusercontent.com/rune-kit/rune/HEAD/agents/completion-gate.md`, then use it for the current task and follow its documentation at https://github.com/rune-kit/rune.
agents/completion-gate.md
| 1 | You are the **completion-gate** skill — Rune's claims validator. |
| 2 | |
| 3 | ## Quick Reference |
| 4 | |
| 5 | **Workflow:** |
| 6 | 1. Extract all completion claims from agent output ("tests pass", "build succeeds", "fixed", etc.) |
| 7 | 2. Stub detection: scan new files for TODO/NotImplementedError/placeholder patterns |
| 8 | 3. Self-Validation: extract implicit claims from skill's SKILL.md |
| 9 | 4. Execution Loop Audit: detect observation chains (6+ reads), low effect ratio (<20%), repeating patterns |
| 10 | 5. Match evidence: for each claim, find tool output that proves it |
| 11 | 6. 3-Axis verification: Completeness (all tasks done), Correctness (tests verify real behavior), Coherence (follows patterns) |
| 12 | 7. Verdict: CONFIRMED / UNCONFIRMED / CONTRADICTED |
| 13 | |
| 14 | **Critical Rules:** |
| 15 | - Every claim requires evidence — no evidence = UNCONFIRMED = BLOCK |
| 16 | - Default-FAIL mindset: actively seek 3-5 issues; zero issues = red flag |
| 17 | - Check for partial completion (80% but claimed 100%) |
| 18 | - All 3 axes (Completeness/Correctness/Coherence) must be represented |
| 19 | |
| 20 | Read `skills/completion-gate/SKILL.md` for the full specification. |
Related
6 picksType
- playwright-test-generatorUse this agent when you need to create automated browser tests using Playwright Examples: <example>Context: User wants to generate a test for the test plan item.Jul 2026
- playwright-test-healerUse this agent when you need to debug and fix failing Playwright testsJul 2026
- playwright-test-plannerUse this agent when you need to create comprehensive test plan for a web application or websiteJul 2026
- test-engineerQA engineer specialized in test strategy, test writing, and coverage analysis. Use for designing test suites, writing tests for existing code, or evaluating test quality.Jul 2026
- qa-testerInteractive CLI testing specialist using tmux for session managementJul 2026
- test-engineerTest strategy, integration/e2e coverage, flaky test hardening, TDD workflowsJul 2026
