verify-gate
Skill0 starsChanged 5 months agoMITView on GitHub
Evidence-only verification gate that runs the project's real test suite, coverage, linter, type checker and security scan, reports each command with its exit code, and returns VERIFY PASS only when every check exits 0. Use before saying a task is done, before committing or opening a pull request, after an agent claims "all tests pass", or whenever you need proof that the code works rather than an assertion that it does.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- kuhlman-labs/fishhawktheir own version, first seen Oct 31, 2026
- Jaxsbr/sabstheir own version, first seen Oct 20, 2026
- feelthefusion/skill-starter-kittheir own version, first seen Oct 13, 2026
- limoaCatherine/game-studio-harnesstheir own version, first seen Sep 20, 2026
- svy04/ballasttheir own version, first seen Aug 23, 2026
- piprail/piprailtheir own version, first seen Jun 10, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- pskoett/pskoett-ai-skills★ 327same name
- svy04/ballast★ 73same name
- kuhlman-labs/fishhawk★ 9same name
- piprail/piprail★ 9same name
- limoaCatherine/game-studio-harness★ 4same name
- feelthefusion/skill-starter-kit★ 0same name
- Jaxsbr/sabs★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- adversarial-review-gateSkill
- done-gateSkill
- launch-checkSkill
- proven-code-reviewSkill
- spec-trace-gateSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Coverage: use the project's configured threshold.
- Very specific: line 27
Secret scan: if gitleaks or trufflehog is installed, run it.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Verify gate: measure substance, not claims
Trust no completion claim, including your own. A check counts only if you ran it in this session and saw its exit code.
Procedure
- Find the project's own checks first. The CI definition is the source of truth: read
.github/workflows/*.yml,.gitlab-ci.yml,Makefile,package.jsonscripts,tox.ini,noxfile.pyor the equivalent and mirror those commands exactly. Fall back to the per-stack defaults inreferences/stack-commands.mdonly for checks the project does not define. - Pick the five check families: tests, coverage, lint, types, security (static analysis plus
a secret scan). Not every stack has all five; record a missing family as
N/A (no tool for this stack), never as PASS. - Run each check as its own command and capture its exit code. Do not chain with
&&: one failure would hide the others. - Never install packages, edit configuration, lower thresholds or add ignore rules to make a
check pass. A tool that is not installed is
SKIPPED (not installed); tell the user the exact install command and let them decide. - Coverage: use the project's configured threshold. If none is configured, report the number and do not invent a threshold.
- Secret scan: if
gitleaksortrufflehogis installed, run it. Otherwise search tracked files for credential shapes (private key blocks, cloud access key ids, tokens or passwords assigned to literals) and report matches asfile:linewithout echoing the secret itself. - Do not fix anything during verification. Verifying and repairing are separate steps. If the user asks for fixes, make them, then re-run the whole gate from step 3.
- Write the report with
assets/VERIFY-template.md: one row per check (command, exit code, result) and the last ~20 lines of real output for every failure.
Verdict
VERIFY: PASS: every applicable check ran and exited 0.VERIFY: FAIL: at least one check exited non-zero. List them.VERIFY: INCOMPLETE: nothing failed, but at least one check was skipped. This is not a pass.
Quote command output verbatim. Never summarise a check you did not run, and never report a verdict from memory of an earlier run after the code changed.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.