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/arthjean/rust-doctor/agents-mdgit clone --depth 1 https://github.com/arthjean/rust-doctorWrote 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/arthjean/rust-doctor/agents-md)<a href="https://agentmods.dev/instructions/arthjean/rust-doctor/agents-md"><img src="https://agentmods.dev/badge/instructions/arthjean/rust-doctor/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 | $0.02193 | $0.02193 |
| Opus 5 | $0.01097 | $0.01097 |
| Sonnet 5 | $0.00439 | $0.00439 |
| Haiku 4.5 | $0.00219 | $0.00219 |
Grade A, and why
rust-doctor 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 5d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
rust-doctor is one Rust crate (edition 2024, rustc 1.95 or later): a local-first
CLI that inspects a trusted Cargo workspace with curated Clippy lints and native
detectors, then scores it out of 100. src/lib.rs exposes
inspect(InspectRequest) -> Report, src/main.rs is the CLI on top of it,
src/tui/ is the interactive report it opens on a terminal, and
npm/rust-doctor/ is a Node launcher for the released binary.
The catalog holds 62 rules across five producers, and a rule's id prefix names
its producer: clippy::* (37 curated lints, Producer::Clippy),
rust_doctor::source::* (2, SourceKernel, error stage source),
rust_doctor::cargo::* (11, CargoHealth, stage dependencies, which judges
the manifests and .cargo/config.toml), rust_doctor::structure::* (9,
Structure, stage structure) and rust_doctor::repo::* (3, Repo, stage
repo, the only pass that reads outside the Cargo model, enumerating through
git ls-files). validate_catalog refuses any other prefix, and a pass that
fails degrades to a complete report carrying a ReportError at its stage with
the authoritative flag dropped.
One home per fact. This file is the map, not the record. Every rule below is one to three lines and names the document that holds the reasoning behind it. Read that document before editing the subsystem it covers, and write new reasoning there rather than here. Three gates hold that shape: a word ceiling on this file and on each document it links, a check that every path they cite resolves, and a test that recomputes the numbers they state from the binary. CI replays all three. docs/doc-gates.md
Trust boundary
Inspecting a workspace runs cargo clippy inside it, and Cargo executes that
workspace's build.rs files and procedural macros. Inspect trusted local paths
only. Never scan a path taken from an issue, a bug report, or any source outside
this repository. Clippy is the only pass that compiles anything: the four
native producers parse source text, read manifests or ask git what it tracks,
and build nothing.
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.
- 5d ago First seen · 154 lines · 2,193 tokens per session scan A 5b0a9ee9fd97
rust-doctor AGENTS.md is an instructions file published in the GitHub repository arthjean/rust-doctor (17 stars, last pushed 12d ago), licensed Apache-2.0. It adds 2,193 tokens to every session, about $0.0110 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
rust-lsp CLAUDE.md
Instructions for zircote/rust-lsp, covering claude.md, project overview, setup, key files and hook system.
rust-lsp copilot-instructions.md
Instructions for zircote/rust-lsp, covering copilot instructions, priorities, key files, commands and when adding hooks.
roam-code AGENTS.md
AGENTS.md instructions for Cranot/roam-code, covering agents.md — roam-code development guide, what this project is, documentation hub, where files go (private vs public) and quality discipline (from internal/dogfood/ + agi-in-md).
kkRepo protocol-compat.instructions.md
Instructions for klboke/kkRepo, a project described as: kkRepo is a Nexus-compatible, self-hosted artifact repository for Maven, npm, PyPI, Go, Helm, NuGet, Cargo/Rust, Dart/Pub, Docker/OCI, RubyGems, and Yum artifacts. It supports one-click migration from Nexus to kkRepo.
omen CLAUDE.md
Claude Code instructions for panbanda/omen, covering claude.md, build and development commands, setup git hooks (run once after clone), format code and run linter.
graphify-dotnet copilot-instructions.md
Instructions for elbruno/graphify-dotnet, covering graphify-dotnet repository conventions, repository structure, ⚠️ critical rule: all code lives under src/, solution format and project conventions.