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.
npx agentmods add instructions/jacksenechal/scan-mcp/agents-mdgit clone --depth 1 https://github.com/jacksenechal/scan-mcpWhat 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 | $0.00327 | $0.00327 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
scan-mcp 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 3d 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
Agent Guidelines
Build, Test, and Development Commands
- Run commands from this directory.
make installinstalls dependencies.make lint,make typecheck,make test,make build, andmake verifymirrorpackage.jsonscripts.npm testruns the Vitest suite.
Code & Project Conventions
- See CONVENTIONS.md for coding style, project structure, security, and testing guidelines.
Commit & Pull Request Guidelines
- Use conventional commit prefixes when practical (
feat:,fix:,docs:, etc.). - Keep commits focused and run
make verifybefore sending a PR. - PRs should include a concise summary and relevant command output.
Releases (release-please)
- This repo uses release-please to automate versioning and changelog generation.
- Do not manually bump versions in
package.jsonor other manifests. - Use conventional commits; release-please derives the next version from commit history.
- If you need to force a specific version for a PR, include a line in the merge (squash) commit message body:
Release-As: x.y.z
- CI will open or update a release PR; merging it publishes the release per the configured workflow.
Network and Approvals Policy
- Network access is allowed for installing packages, fetching docs, or calling external APIs.
- If the sandbox blocks a command, re-run it with elevated permissions and a brief justification.
- Do not commit secrets; document required environment variables instead.
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.
- 3d ago First seen · 29 lines · 327 tokens per session scan A 9c76cf5c6a33
scan-mcp AGENTS.md is an instructions file published in the GitHub repository jacksenechal/scan-mcp (6 stars, last pushed 1mo ago), licensed MIT. It adds 327 tokens to every session, about $0.0016 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.
Other instructions, from other repositories
nuclear copilot-instructions.md
Copilot instructions for nukeop/nuclear, covering nuclear music player - copilot instructions, project overview, key features, tech stack and packages.
react-svg AGENTS.md
Instructions for tanem/react-svg, covering agents.md, writing, architecture, build & test and releases.
best-claude-hud AGENTS.md
Instructions for GaoSSR/best-claude-hud, covering project agent instructions and release work.
OpenDeck AGENTS.md
AGENTS.md instructions for nekename/OpenDeck, covering opendeck development guide, token efficiency, architecture overview, core architecture pattern and project structure.
mcp-screenshot-server CLAUDE.md
Instructions for sethbang/mcp-screenshot-server, covering claude.md, what this is, commands, environment variables and architecture.
typetype AGENTS.md
Instructions for whynusn/typetype, covering typetype 项目开发指南, 📍 文档导航卡（你在这里）, 🧭 ai 阅读顺序, 📚 文档维护指南 and 文档职责速查.