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/nwiizo/cargo-coupling/agents-mdgit clone --depth 1 https://github.com/nwiizo/cargo-couplingWrote 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/nwiizo/cargo-coupling/agents-md)<a href="https://agentmods.dev/instructions/nwiizo/cargo-coupling/agents-md"><img src="https://agentmods.dev/badge/instructions/nwiizo/cargo-coupling/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 | $0.00691 | $0.00691 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
cargo-coupling 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 — 20 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/main.rs contains the Clap entrypoint; src/lib.rs re-exports the public API. Core analysis and reporting live in src/analyzer.rs, src/metrics.rs, src/balance.rs, src/volatility.rs, src/report.rs, src/config.rs, src/workspace.rs, and src/cli_output.rs. Web backend code is under src/web/; shipped frontend assets live in web-assets/. Benchmarks are in benches/analysis_benchmark.rs, and screenshots/docs are in docs/images/.
Build, Test, and Development Commands
Use cargo build --release for the production build path used in CI. Run cargo test --all-features for the full unit-test suite. Format with cargo fmt --all; CI uses cargo fmt --all -- --check. Lint with cargo clippy --all-targets --all-features -- -D warnings. For a local smoke test, run cargo run -- coupling ./src. For the browser UI, run cargo run -- coupling --web --no-open ./src and open http://localhost:3000. Use cargo bench --bench analysis_benchmark when changing analyzer performance.
Coding Style & Naming Conventions
Target Rust 2024 and keep rustfmt defaults with 4-space indentation. Follow standard Rust naming: snake_case for modules, functions, and tests; PascalCase for types and enums; SCREAMING_SNAKE_CASE for constants. Keep CLI flags, README examples, and output formatting aligned when behavior changes. Prefer small focused modules instead of growing main.rs.
Testing Guidelines
Tests are colocated with implementation in #[cfg(test)] mod tests; there is no top-level tests/ directory at present. Add regression tests for parser edge cases, config loading, CLI output, and web graph/report generation when touching those paths. After analyzer or scoring changes, rerun cargo run -- coupling --summary ./src to confirm behavior on the repository itself.
Commit & Pull Request Guidelines
Follow the Conventional Commit style already used in history: feat(analysis): ..., fix(test): ..., deps: ..., ci: .... Keep commit subjects imperative and scoped. PRs should summarize user-visible changes, note new flags or config keys, link related issues when available, and include screenshots for CLI/Web UI output changes. Before pushing, ensure fmt, clippy, tests, and the release build all pass.
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 · 20 lines · 691 tokens per session scan A 7f6eeeed47bf
cargo-coupling AGENTS.md is an instructions file published in the GitHub repository nwiizo/cargo-coupling (96 stars, last pushed 5d ago), licensed MIT. It adds 691 tokens to every session, about $0.0035 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 2026-09-01.
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).
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.