A linter that checks agent skills for outdated commands to external command-line tools. A linter is a checker that reports problems in code or configuration.

Finding skills whose calls to tools such as Codex, GitHub CLI, or Docker no longer match the installed versions.

Command-line tools can change their flags or subcommands, leaving skills that call them broken without an obvious warning.

skillrot — Plugin by mishanefedov

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add mishanefedov/skillrot

agentmods

npx agentmods add plugins/mishanefedov/skillrot/marketplace

Clone the repo

git clone --depth 1 https://github.com/mishanefedov/skillrot

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

skillrot scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude-plugin/marketplace.json · 20 lines

What it actually says

{
  "name": "skillrot",
  "owner": { "name": "mishanefedov" },
  "description": "skillrot — a linter that audits agent skills for external-CLI drift.",
  "plugins": [
    {
      "name": "skillrot",
      "source": "./",
      "description": "Find skills that call external tools (codex, gh, docker, ...) with flags/subcommands the installed version no longer accepts.",
      "version": "0.1.0",
      "author": { "name": "mishanefedov" },
      "homepage": "https://github.com/mishanefedov/skillrot",
      "repository": "https://github.com/mishanefedov/skillrot",
      "license": "MIT",
      "keywords": ["claude-code", "agent-skills", "cli", "drift", "lint"],
      "category": "dev-tools"
    }
  ]
}

Files

What ships with it

1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

plugin.json 387 B

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 20 lines scan A 081c7db4125b

Subscribe to this mod's changes

skillrot is a plugin published in the GitHub repository mishanefedov/skillrot (2 stars, last pushed 3mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

DevOps and cloud agent-skills ai-agents bun claude-code claude-code-skill cli

skillrot

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What ships with it

What this file has done since we first saw it

Other plugins, from other repositories

security-guidance

ccmux

firecrawl-lean

flutter-agentic

rails-consultant

rails-consultant