verification-before-completion — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited verification-before-completion (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Require fresh evidence before any completion claim.
Do not claim that work is complete, fixed, passing, ready, or safe to merge unless the proving command or check ran after the final relevant edit and its output was read.
Evidence comes before claims.
Before claiming status:
If the evidence does not prove the claim, report the gap instead of softening the wording.
| Claim | Required evidence |
|---|---|
| Tests pass | Fresh test output with a passing exit code and no failures |
| Lint is clean | Fresh lint output with a passing exit code |
| Build succeeds | Fresh build output with a passing exit code |
| Bug is fixed | The original symptom or regression test now passes |
| Regression test is valid | Red, green, and restored-green evidence |
| Agent completed work | VCS diff plus relevant verification, not the agent report alone |
| Requirements are met | Re-read checklist or spec and verify each item |
| PR is ready | Local verification plus any required pre-PR checks |
Stop and verify before using wording like:
Also stop before committing, pushing, opening a PR, handing work back to the user, or moving to the next task.
If verification fails:
If verification cannot be run:
Use concise evidence:
Verified: bash tests/unit/test-workbench-verification-before-completion-skill.sh, passed.For partial status:
Not fully verified: lint passed, but integration tests were not run because live auth is unavailable.~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.