agentmods.dev

skillrot AGENTS.md

Repository instructions for Skillrot, a tool that checks whether Agent Skills use command-line options supported by the installed tools.

In plain words
What is it for?
Use them when changing the TypeScript source, CLI, skill definition, tests, or audit logic; the tool checks help and version flags without running real commands.
Why use it?
They help agents preserve the project's layout, safety rule, and test requirements while working on the auditing engine.

Instructions file for CodexOpenCode

2 3mo ago A scan 375 tokens original MIT
View the source file mishanefedov/skillrot
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.

agentmods
npx agentmods add instructions/mishanefedov/skillrot/agents-md
Clone the repo
git clone --depth 1 https://github.com/mishanefedov/skillrot

Made for: Codex, OpenCode.

Per session 375 This file is loaded in full into every session.
When invoked 375 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00375 $0.00375
Opus 5 $0.00187 $0.00187
Sonnet 5 $0.00075 $0.00075
Haiku 4.5 $0.00038 $0.00038

Measured 2d ago against content hash a8acceb8c306, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skillrot AGENTS.md 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.

AGENTS.md · 32 lines

What it actually says

AGENTS.md — guide for coding agents working in this repo

skillrot audits agent skills for external-CLI drift. This file is the tool-agnostic guide (Claude Code, Codex, Cursor, etc. all read it).

Layout

  • src/ — the engine. extract.ts (parse skill bash → invocations), introspect.ts (probe installed CLIs via --help/--version), analyze.ts (compare used flags vs. accepted), report.ts, cli.ts.
  • skills/skillrot/SKILL.md — the skill definition (plugin layout).
  • .claude-plugin/ — Claude Code plugin + marketplace manifests.
  • bin/skillrot — launcher (on PATH under the plugin and via bun link).
  • scripts/gen-logo.ts — regenerates assets/skillrot.svg.
  • test/ — bun test; deterministic fixtures (a fake CLI) so tests don't rot.

Conventions

  • Runtime: Bun. No build step — Bun runs the TypeScript directly.
  • Zero runtime dependencies. Keep it that way; the engine only uses node:*.
  • Before pushing: bun test and bun run typecheck must pass.
  • The engine must never run a skill's real subcommand — only append --help / --version. This is the core safety property.
  • Be conservative: a missing long flag is an error; anything uncertain (short flags, unreadable help, unparseable lines) is a warning. Don't cry wolf.

Dogfood

bun run src/cli.ts skills       # skillrot audits its own skill (CI does this too)
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.

  1. 2d ago First seen · 32 lines · 375 tokens per session scan A a8acceb8c306

Subscribe to this mod's changes

skillrot AGENTS.md is an instructions file published in the GitHub repository mishanefedov/skillrot (2 stars, last pushed 3mo ago), licensed MIT. It adds 375 tokens to every session, about $0.0019 per session on Opus 5. 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.

LanguagesTestingagent-skillsai-agentsbunclaude-codeclaude-code-skillcli
Related

Other instructions, from other repositories

gini-agent AGENTS.md

AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.

Open-Curiosity/gini-agent · 3,639 tokens

stockbit-mcp CLAUDE.md

Instructions for INo-xious/stockbit-mcp, covering claude.md, what this is, commands, the map and three invariants. do not break them; each has a test.

INo-xious/stockbit-mcp · 1,337 tokens

devin-handoff AGENTS.md

Instructions for club-cog/devin-handoff, covering devin handoff — agent guide, what this is, when to hand off, finding the script and how to use.

club-cog/devin-handoff · 542 tokens

agentconfig.org AGENTS.md

Instructions for agentconfig/agentconfig.org, covering agent instructions for agentconfig.org, project overview, target audience, site structure and tech stack.

agentconfig/agentconfig.org · 2,368 tokens

agent-plugins-skills copilot-instructions.md

Instructions for richfrem/agent-plugins-skills, covering copilot instructions for agent-plugins-skills, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.

richfrem/agent-plugins-skills · 6,436 tokens

sandy CLAUDE.md

Instructions for jamestelfer/sandy, covering claude.md, voice, what is sandy, project layout and dev commands.

jamestelfer/sandy · 1,475 tokens