auditing-tool-currency
Skill10 starsChanged 44 days agoMITView on GitHub
Guides auditing the repository's externally sourced, version-pinned tooling against canonical origins - the GitHub Actions pins, the Go tool module under tools/go, the npm tool module under tools/node, the pinned Supabase CLI and the Go consumer floor. Use when asked which tools could be upgraded, whether pins are stale or to prepare an upgrade report or plan. Audit and report only: applying a bump is the changing-build-and-continuous-integration skill's territory.
In this repository7 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 6
Run scripts/tools-audit.sh first: it is the executable inventory of every pin, reporting current against latest from each canonical origin …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Run scripts/tools-audit.sh first: it is the executable inventory of every pin, reporting current against latest from each canonical origin with the bump route and release-notes link for each, and it never modifies anything.
The following documents will be helpful:
| Document | For |
DEVELOPMENT.md | The audit script's scope and the pins it cannot see, the supply-chain pinning approach and per-tool upgrade procedures such as the pinned Supabase CLI bump. |
decisions.md | Why the update cadence is manual rather than Dependabot-driven and why everything executed from outside the repository is digest-pinned. |
When asked for an upgrade report or plan, follow the release-notes links the script prints for each candidate and summarize what the newer version offers (features, fixes, security advisories) and any breaking changes, placing the script's bump route alongside. Recommend only: never apply an upgrade as part of this activity.
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.