vet
Skill1 starsChanged 4 months agoMITView on GitHub
Run a background check on a dependency before installing it. Use when the user is considering adding a package/library and wants to know if it's safe, maintained, appropriately sized, and correctly named — or wants alternatives compared.
9 other projects use a version of this.
Adopted by
Most recently taken up by
- LeonardiFranco/skillstheir own version, first seen Nov 8, 2026
- dtiger1889-ops/claude-harness-toolboxtheir own version, first seen Nov 1, 2026
- atilladeniz/Kubelitheir own version, first seen Oct 8, 2026
- catcatcatstudio/cat-skillstheir own version, first seen Aug 27, 2026
- evist0/okf-matt-skillstheir own version, first seen Jul 7, 2026
- Sanexxxx777/curated-claude-codetheir own version, first seen Jun 28, 2026
Used with
Projects with it also use teach.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillteach
Teach the user a new skill or concept, within this workspace.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 9
- imbue-ai/vet★ 518same name
- atilladeniz/Kubeli★ 387same name
- dtiger1889-ops/claude-harness-toolbox★ 31same name
- Sanexxxx777/curated-claude-code★ 16same name
- evist0/okf-matt-skills★ 13same name
- JustineDevs/meta-architect★ 5same name
- catcatcatstudio/cat-skills★ 3same name
- JustineDevs/premortem★ 2same name
- LeonardiFranco/skills★ 1same 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.
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
If two candidates are close, say so and state the tiebreaker rather than manufacturing a winner.
- Distinctive: line 34
When data can't be verified (private registry, no repo link), say what couldn't be checked — an unverifiable claim is a finding, not a …
“Common” is measured: kept by at least 6 in 10 of the 9 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
Vet
A dependency is a hire: it gets commit access to your runtime. Before it's installed, run the background check. Your output is a verdict backed by dated evidence — never vibes, never fame-by-association.
What to check
Work through all six. Cite dates and numbers for every claim.
- Pulse. Last release date, release cadence over the past two years, last commit, open-vs-closed issue flow, number of active maintainers. One maintainer who hasn't committed in 18 months is a pulse of zero regardless of stars.
- Weight. Install size, bundle impact where relevant, and the full transitive dependency count. Report what the package brings with it, not just what it is.
- License. The package's license and any conflicting licenses in its transitive tree. Flag copyleft in the tree of a commercial project loudly.
- Security. Known advisories (ecosystem audit tooling, osv.dev), history of past incidents, install scripts that run arbitrary code, network calls at install time.
- Identity. Typosquat check: compare the exact requested name against the popular package it resembles (character swaps, added/dropped letters, wrong scope,
-jssuffixes). Verify the registry package actually points at the repo it claims. This check has caught real attacks; take it seriously. - Proportionality. What fraction of the package would actually be used? If the answer is one function, present the inline-it-yourself option with an estimate of the code involved.
The verdict
End with exactly one of:
- ✅ HIRE — healthy on all six checks. One paragraph on why.
- ⚠️ HIRE WITH EYES OPEN — usable, but with named risks and what to watch. Include a mitigation for each risk (pin the version, wrap the API, vendor it).
- ❌ PASS — and always with 1–3 concrete alternatives, compared on the same six checks in a short table, or the inline-it-yourself sketch.
Rules
- Evidence over reputation: a famous package can still fail Pulse or Weight for this project's needs.
- Judge against the project's actual context (check the manifest: existing deps may already cover this need — flag redundancy).
- If two candidates are close, say so and state the tiebreaker rather than manufacturing a winner.
- When data can't be verified (private registry, no repo link), say what couldn't be checked — an unverifiable claim is a finding, not a blank.
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.