Borrowing it
Nothing to install: this file belongs to mondoohq/skillcheck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mondoohq/skillcheck/main/AGENTS.mdgit clone --depth 1 https://github.com/mondoohq/skillcheckWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/mondoohq/skillcheck/agents-md)<a href="https://agentmods.dev/instructions/mondoohq/skillcheck/agents-md"><img src="https://agentmods.dev/badge/instructions/mondoohq/skillcheck/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mondoohq/skillcheck/agents-md"><img src="https://agentmods.dev/badge/instructions/mondoohq/skillcheck/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00528 | $0.00528 |
| Opus 5.5 | $0.00211 | $0.00211 |
| Sonnet 5.5 | $0.00106 | $0.00106 |
| Haiku 4.5 | $0.00053 | $0.00053 |
Grade A, and why
skillcheck 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 18d 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.
What it actually says
AGENTS.md
Working instructions for an AI agent operating in this repository (agents.md convention).
What this is
skillcheck is a Go CLI that (1) scans a machine for known-malicious installed AI agent
skills and (2) validates a skills repository against the Agent Skills and AGENTS.md specs
(skillcheck validate). It embeds the MQL engine with
the OS + core providers compiled in.
Layout
cmd/skillcheck/— the cobra CLI (default scan + thevalidatesubcommand).internal/engine/— the embedded MQL runtime;schemas/holds the embedded resource JSON.internal/hasher,internal/mondoo,internal/reporter— hashing, the Mondoo API client, output.internal/validate/—validate;policy/repo-contract.mql.yamlis the embedded MQL policy whose checks it runs (the rules are data, not Go).
Build, test, lint
make build # CGO_ENABLED=0 go build
make install # go install into $GOBIN (or $GOPATH/bin)
make test # go test ./... -count=1
make lint # golangci-lint run ./...
Run all three before opening a PR. TestSearchByHash_LiveAPI needs network to the Mondoo API
and is skipped under go test -short.
Conventions
- Every Go and YAML source file carries the Apache-2.0 copyright header
(
copywrite headers); CI enforces it.**/*.jsonand**/testdata/**are exempt. - After bumping mql in
go.mod, regenerate the embedded MQL schemas withmake schemas(generates them from the pinned mql module); CI checks they match. - The
validatepolicy is a standard cnspec bundle — keep it runnable bycnspecas well as by the embedded runner.
Security
- The scan is fail-open: a skill not in the database shows as clean and never blocks a workflow. Preserve that.
- Don't commit secrets; the live-API test hits a public endpoint only.
PRs
One focused change per PR. Run make test and make lint first; state what you verified.
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.
- 18d ago Changed · +1 lines · +19 tokens per session e69ccabf0053
- 19d ago First seen · 50 lines · 509 tokens per session scan A fc9daf45045f
skillcheck AGENTS.md is an instructions file published in the GitHub repository mondoohq/skillcheck (17 stars, last pushed 12d ago), licensed Apache-2.0. It adds 528 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-10-09.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.