double-check
Skill1 starsChanged 6 months agoMITView on GitHub
Run the verification stack against work you just produced (code, configs, deps). Use after any substantive change, before reporting it done.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- tony/skillstheir own version, first seen Oct 31, 2026
- p3bot/librarytheir own version, first seen Oct 31, 2026
- conjurer-rich/skillstheir own version, first seen Oct 25, 2026
- mrtooher/fable-modetheir own version, first seen Oct 24, 2026
- allemaar/open-skillstheir own version, first seen Oct 13, 2026
- mehrad-dm/mastermindtheir own version, first seen Oct 13, 2026
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- mrtooher/fable-mode★ 878same name
- gsarig/skills★ 30same name
- mehrad-dm/mastermind★ 23same name
- allemaar/open-skills★ 15same name
- p3bot/library★ 10same name
- david-vrba/claude-power-skills★ 4same name
- conjurer-rich/skills★ 1same name
- OHOKAYYEAH/claude-skills★ 1same name
- mdalfianahmad/double-check★ 0same name
- tony/skills★ 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 repository16 other files it gives its agents.
- audit-unused-depSkill
- checkpointSkill
- file-adrSkill
- fleetSkill
- fmt-sweepSkill
- forge-mirror-scaffoldSkill
- forgeSkill
- gemini-pullSkill
- loop-from-taskSkill
- loop-healthSkill
- loop-onSkill
- loopSkill
- loopsSkill
- regression-guardSkill
- restoreSkill
- workspace-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 9
Run the checkers relevant to what you touched.
- Very specific: line 31
All alert-only → admin@sacredvote.org + ntfy sv-security.
- Very specific: line 36
Run the matching checkers from the table.
“Common” is measured: kept by at least 6 in 10 of the 10 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
/double-check — verify your own work with the installed checker stack
Convention skill (no binary yet — Rust port welcome per design rule 4). Run the checkers relevant to what you touched; a checker ERROR is a finding, never a skip (fail-closed).
Pick checkers by what changed
| You touched | Run |
Rust (any Cargo.lock repo) | cargo-audit audit -f <repo>/Cargo.lock · cargo-deny check (if deny.toml) · cargo test |
Node/TS (package-lock.json) | npm audit --audit-level=high · project test suite · npx tsc --noEmit |
| Configs / Dockerfiles / IaC | trivy fs --scanners misconfig <dir> |
| Dependency bumps | trivy fs --scanners vuln --severity HIGH,CRITICAL <dir> |
| Any source (patterns) | semgrep (venv per host notes; sacred.vote: vulnerability.sh) |
| Shell scripts | bash -n <file> + run once against harmless input |
| System packages/files | debsums -s <pkg> |
Host fabric (already scheduled — don't duplicate, just don't break)
Weekly Sun (UTC): lynis 10:00 · npm-audit 12:00 · rust-deps-audit 11:30
(/usr/local/bin/rust-deps-check.sh) · trivy 12:00 (trivy-weekly.sh,
SBOM → /var/lib/trivy-reports/). Daily: rootkit-scan 10:00/10:15 ·
clamav 09:45 · debsecan. Continuous: osquery-alert (10 min) ·
opencanary (1 min) · fail2ban · auditd · AppArmor (29 enforce).
All alert-only → admin@sacredvote.org + ntfy sv-security.
Steps
- Identify changed surfaces (git status across touched repos).
- Run the matching checkers from the table.
nice -n 19 ionice -c 3anything heavy — production box. - Nonzero exit or
^erroroutput = report it, even if unrelated to your change. Allowed findings live in each repo'saudit.toml/ ignore files — extend those only with user sign-off. - Append a STEP line to your session STATE file in
~/.claude/notes/(crash-safe resume convention) recording what was checked + result.
Net visible tool calls
1–3 Bash (checker runs) + optional STATE-file append.
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.