dependency-vetting
Skill20 starsChanged 52 days agoMITView on GitHub
Verify a package or tool is authentic before installing, adding, upgrading, or recommending it. Use whenever a task would add a dependency to a project, suggest a CLI tool, or pull a package from npm, PyPI, crates.io, Go modules, RubyGems, Homebrew, or any other registry. Also use when a registry page, install command, or installed artifact looks inconsistent with the project that supposedly publishes it.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- ToddGBenson/keeltheir own version, first seen Aug 15, 2026
- TheDecipherist/claude-code-mastery-project-starter-kittheir own version, first seen Jun 26, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- TheDecipherist/claude-code-mastery-project-starter-kit★ 337same name
- ToddGBenson/keel★ 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 repository41 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ask-supermattSkill
- babysit-prSkill
- codebase-designSkill
- code-reviewSkill
- commitSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- fix-findingsSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- ideateSkill
- implementSkill
- implement-specSkill
- improve-architectureSkill
- improve-file-structureSkill
- improve-testsSkill
- jurySkill
- orchestrateSkill
- prototypeSkill
- prSkill
- qaSkill
- recover-ciSkill
- refactorSkill
- researchSkill
- resolving-merge-conflictsSkill
- retroSkill
- setup-supermatt-skillsSkill
- ship-prSkill
- tddSkill
- teachSkill
- to-questionnaireSkill
- to-specSkill
- to-ticketsSkill
- triageSkill
- wait-whatSkill
- wayfinderSkill
- what-would-you-doSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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 13
Follow the link from the upstream project to the install command.
- Distinctive: line 21
Use the registry's own independent signal where one exists:
≈ “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
Dependency vetting
The rule: never install, add, or recommend a package until you have opened the upstream project's own repo or docs and used the install command or import path published there. The sections below are the full reasoning behind it.
Direction of trust
Follow the link from the upstream project to the install command. Never work the other direction, from a search result or a registry page back to a project.
Treat unverified registry metadata as publisher-supplied claims: author, email, homepage, repository link, README, and license. Where the registry independently verifies a field or attestation, check what that verification establishes and compare the verified identity with the intended upstream project. Still open the upstream repository or docs and confirm the published installation instructions.
If upstream documents no registry install, then there is no registry package, whatever the registry shows. Stop and say so. Do not install it, do not pin around it, and do not quietly swap in an alternative. Pinning untrusted code to a SHA is the same code with better bookkeeping, not a fix.
Registry signals worth using
Use the registry's own independent signal where one exists:
| Registry | Signal |
| npm | npm audit signatures |
| PyPI | "Verified details" plus PEP 740 attestations |
| GitHub release binaries | gh attestation verify |
| crates.io, Go modules, most others | checksum only, so the upstream link carries all the weight |
Download counts, stars, and search ranking are not evidence of authenticity.
Stop signals
Any mismatch between the installed artifact and upstream docs is a stop signal: a different executable name, version, file set, or dependency list. Confirm with the user. Never record it as a quirk and move on.
Keep it proportionate
A tool a project genuinely publishes passes these checks in seconds, so this costs nothing in the normal case and fires only when something is actually wrong. Do not turn it into pin-everything ceremony.
Separately: do not add or suggest outdated dependencies. Check the current release before pinning a version.
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.