Borrowing it
Nothing to install: this file belongs to sebastienrousseau/noyalib-mcp. 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/sebastienrousseau/noyalib-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/sebastienrousseau/noyalib-mcpWrote 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/sebastienrousseau/noyalib-mcp/agents-md)<a href="https://agentmods.dev/instructions/sebastienrousseau/noyalib-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sebastienrousseau/noyalib-mcp/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/sebastienrousseau/noyalib-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sebastienrousseau/noyalib-mcp/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 | $0.00640 | $0.00640 |
| Opus 5 | $0.00320 | $0.00320 |
| Sonnet 5 | $0.00128 | $0.00128 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
noyalib-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 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on noyalib-mcp with an AI agent
The invariants a contribution must respect, whether typed by a human
or generated with an assistant. DEVELOPMENT.md covers the how; this
file covers the rules that are easy for an agent to violate. The core
repository's AGENTS.md applies to the family; this one adds what is
specific to a satellite.
Versioning and lockstep
- This crate releases at the identical
=0.0.Xasnoyalib, in strict lockstep (core ADR-0005), and increments strictly by +0.0.1. Never propose a 0.1.0 or 1.0 jump, and never release ahead of the core. - The
noyalibdependency is an exact pin. A release branch (feat/vX.Y.Z) carries the new version and pin from creation. - Until the core publishes, the pin cannot resolve from crates.io. The
branch may carry a
[patch.crates-io]git source pointing at the core's release branch. Remove it before tagging:scripts/verify-release-versions.shrefuses to pass while it is present, and cargo-deny is red on the branch for the same reason. After removal:cargo update -p noyalib, thencargo vet regenerate exemptionsandcargo vet --locked. - At most two version branches exist at once: the release in flight and one future branch. Commit or stash everything before any branch switch.
Quality gates
- CI must be green in the same session that turned it red.
- Every behaviour change lands with its test in the same commit.
- Run the local battery before pushing:
cargo fmt --all -- --check(this repo pins rustfmt defaults in.rustfmt.toml; a global rustfmt config must not leak in), clippy with warnings denied, the test suite,cargo deny check,cargo vet --locked,reuse lint, codespell, markdownlint. - Every version-bearing file moves with the version. The gate script is the authority; README install snippets are not yet gate-checked here, so grep for the previous version after a bump.
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 · 58 lines · 640 tokens per session scan A 04115fae8a32
noyalib-mcp AGENTS.md is an instructions file published in the GitHub repository sebastienrousseau/noyalib-mcp (1 stars, last pushed yesterday), licensed Apache-2.0. It adds 640 tokens to every session, about $0.0032 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 2026-09-07.
Other instructions, from other repositories
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.