Borrowing it
Nothing to install: this file belongs to lennney/mcp-slim-guard. 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/lennney/mcp-slim-guard/main/AGENTS.mdgit clone --depth 1 https://github.com/lennney/mcp-slim-guardWrote 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/lennney/mcp-slim-guard/agents-md)<a href="https://agentmods.dev/instructions/lennney/mcp-slim-guard/agents-md"><img src="https://agentmods.dev/badge/instructions/lennney/mcp-slim-guard/agents-md.svg" alt="Measured on agentmods" 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 | $0.01043 | $0.01043 |
| Opus 5 | $0.00522 | $0.00522 |
| Sonnet 5 | $0.00209 | $0.00209 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
mcp-slim-guard 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slim Guard Agent Contract
This file defines the public repository rules for coding agents. It is a short operational contract. Human contribution rules remain in CONTRIBUTING.md, security reporting remains in SECURITY.md, and architecture details remain in docs/architecture-mcp-slim-guard.md.
Scope and source of truth
- Start from the latest
mainand inspect the current worktree before editing. - Keep one change focused on one user-visible behavior or one maintenance goal.
- Treat existing uncommitted work as user-owned. Do not reset, clean, migrate, or overwrite unrelated changes.
- This public repository is not the source for private workbench plans, hidden evaluation cases, launch drafts, credentials, or private evidence.
- Do not commit, push, publish, tag, or change external settings unless the user explicitly authorizes that action.
Repository map
src/contains the TypeScript runtime and public exports.tests/contains unit, integration, policy, fixture, and adversarial tests.scripts/candidate/contains candidate and package-boundary checks.scripts/integration/contains protocol, Host, and package smoke checks.scripts/benchmark/contains measurement tools. Run them only when the change affects a measured claim.docs/contains public architecture, setup, roadmap, and evidence.
Read the relevant source and tests before changing a public interface. Do not move evaluation or release evidence into runtime modules.
When a directory, command, dependency, public interface, or implementation rule changes, update this file and the relevant human-facing documentation in the same change. Keep this file as the source of truth for agent-facing rules.
Product invariants
Every change must preserve these boundaries:
- Authorization rejects undiscovered and unauthorized Tools.
- A business Tool call reaches the upstream server at most once.
read_resultnever executes the upstream business Tool.- Exact upstream results remain recoverable when delivery is projected.
- Delivery, storage, observer, or audit failures return the exact upstream result.
- Logs and shareable reports exclude credentials, raw arguments, result bodies, local paths, and private capability references.
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.
- 8d ago First seen · 102 lines · 1,043 tokens per session scan A b25fae50b6c8
mcp-slim-guard AGENTS.md is an instructions file published in the GitHub repository lennney/mcp-slim-guard (192 stars, last pushed 25d ago), licensed MIT. It adds 1,043 tokens to every session, about $0.0052 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.