skill-inspector
AGENTS.md2 starsChanged 10 months agoApache-2.0View on GitHub
skill-inspector is a CLI tool designed to inspect Agent Skills (specifically .claude/skills and similar formats) for malicious behaviors, security vulnerabilities, and adherence to project standards.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,700 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository13 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .cursor/rules/tech-stack.mdcCursor rule
- .cursor/rules/typescript-coding-convention.mdcCursor rule
- .cursor/rules/unit-test-manners.mdcCursor rule
- build-and-fixSkill
- clean-projectSkill
- initialize-projectSkill
- lint-and-fixSkill
- node-upgradeSkill
- security-vulnerability-auditSkill
- setup-dev-envSkill
- test-and-fixSkill
- update-llm-modelsSkill
The file
We split this AGENTS.md 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 18
Dependency Strictness: Only use dependencies explicitly declared in package.json.
≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md 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
AGENTS.md
Project Goal
skill-inspector is a CLI tool designed to inspect Agent Skills (specifically .claude/skills and similar formats) for malicious behaviors, security vulnerabilities, and adherence to project standards.
Tech Stack
- Runtime: Node.js (>=22.13.0)
- Package Manager: pnpm (v10.x)
- Language: TypeScript
- Testing: Vitest
- Linting/Formatting: Trunk (manages hermetic tools)
- Core Libraries: Mastra, AI SDK (Anthropic, Google, OpenAI, etc.), Commander, simple-git.
Key Architectural Rules
- Dependency Strictness: Only use dependencies explicitly declared in
package.json. - Unit Test Manners: Strict decoupling from external I/O. Tests must be fast and reliable without mocks.
- Skill Structure: Skills are defined in
.claude/skills/withSKILL.mdand associated assets.
Memory
- Initial Setup: Project bootstrapped from a TypeScript template.
- Agent Context:
CLAUDE.mdandAGENTS.mdcreated to provide persistent guidance for AI agents. - Environment Management: Trunk is used for managed tool chains to ensure consistency across environments.
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.