agentleFS
TheGoat395TheGoat395/Codex-Skills/skills/frontend-tooling-trust-gate/SKILL.md

frontend-tooling-trust-gate

Skill136 starsChanged 5 months agoMITView on GitHub

Review trust before frontend tooling adoption.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 6 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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
  1. Distinctive:

    Use this skill before installing or recommending a repo, package, MCP, plugin, template, or script.

    line 8
  2. Distinctive:

    Prefer official sources, verified orgs, and vendor-maintained repos.

    line 20
  3. Very specific:

    Use npm view <package> repository license version time maintainers when npm metadata matters.

    line 23
  4. Distinctive:

    Look for preinstall/postinstall scripts, broad permissions, telemetry, token requests, cookie access, or curl-to-shell commands.

    line 24
  5. Distinctive:

    Prefer project-local installs for frontend tools and libraries.

    line 25
  6. Distinctive:

    Avoid global installs unless the tool is an agent-wide CLI and the user explicitly approves it.

    line 26
  7. Distinctive:

    Never expose API keys, browser cookies, SSH keys, tokens, or private files to unknown tools.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Frontend Tooling Trust Gate

Use this skill before installing or recommending a repo, package, MCP, plugin, template, or script.

Trust Classes

  • preferred: official or clearly reputable.
  • acceptable: useful, maintained, and reasonably transparent.
  • inspect manually: promising but insufficiently verified.
  • avoid: suspicious, stale, unsafe, or low-quality.
  • unknown risk: not enough evidence.

Inspection Checklist

  1. Prefer official sources, verified orgs, and vendor-maintained repos.
  2. Inspect README specificity, license, SECURITY.md, recent commits, releases, issues, and package registry links.
  3. Inspect package.json, scripts, dependencies, and install instructions.
  4. Use npm view <package> repository license version time maintainers when npm metadata matters.
  5. Look for preinstall/postinstall scripts, broad permissions, telemetry, token requests, cookie access, or curl-to-shell commands.
  6. Prefer project-local installs for frontend tools and libraries.
  7. Avoid global installs unless the tool is an agent-wide CLI and the user explicitly approves it.
  8. Never expose API keys, browser cookies, SSH keys, tokens, or private files to unknown tools.

Decision Output

Return:

  • source and type
  • trust class
  • evidence
  • red flags
  • install stance: install, project-local only, do not install, or needs user auth
  • safer official alternative if rejected

Scope and evidence

Apply to frontend tooling adoption only. Reuse recent verified adoption decisions if no relevant version, source, permission or requirement changed. Stale maintenance is a factor, not proof of malice. Existing authorization covers routine approved installs; spending and external commitments keep their actual boundaries.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.