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/kingingwang/crates-docs/agents-mdgit clone --depth 1 https://github.com/KingingWang/crates-docsWhat 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 | $0.02240 | $0.02240 |
| Opus 5 | $0.01120 | $0.01120 |
| Sonnet 5 | $0.00448 | $0.00448 |
| Haiku 4.5 | $0.00224 | $0.00224 |
Grade A, and why
crates-docs 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 — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides comprehensive guidance to agents when working with code in this repository.
CI/CD Workflow & Code Gates
Project Structure
- Rust Edition: 2021
- Default Features: server, stdio, macros, cache-memory, logging, api-key
- Optional Features: cache-redis, tls, auth, hyper-server, sse, streamable-http
Build Commands
# Standard build
cargo build
# Build with all features
cargo build --all-features
# Build with specific feature
cargo build --features cache-redis
# Release build
cargo build --release
Code Quality Gates (Must Pass Before Merge)
1. Formatting Check
cargo fmt -- --check
- Checks if code is properly formatted
- Use
cargo fmtto auto-fix formatting issues
2. Clippy Linting
# Check without optional features
cargo clippy --all-targets -- -D warnings
# Check with all features (required - feature-gated code)
cargo clippy --all-features --all-targets -- -D warnings
Critical: Run both commands because Redis/auth code is feature-gated and checked separately.
-D warningstreats all warnings as errors--all-targetsincludes lib, bins, tests, benches
3. Security Audit
cargo install cargo-audit
cargo audit
Testing Commands
Test Target Structure
Tests are split across THREE targets (not one suite):
# Unit tests (primary - new code goes here)
cargo test --test unit
# Legacy unit tests
cargo test --test unit_tests
# Integration tests
cargo test --test integration_tests
# E2E tests
cargo test --test e2e
Running Single Tests
Important: Use the correct target when running a single test:
# Correct: specify --test unit
cargo test --test unit test_oauth_config_github
# Correct: for tools_docs tests
cargo test --test unit test_lookup_crate_tool_execute_markdown
# Incorrect: will search all targets and may fail
cargo test test_oauth_config_github
Feature-Gated Testing
# Test with Redis cache (only when Redis is available)
cargo test --features cache-redis
# Test unit with Redis feature
cargo test --test unit --features cache-redis
# Test all features
cargo test --all-features
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 · 364 lines · 2,240 tokens per session scan A 38221f826789
crates-docs AGENTS.md is an instructions file published in the GitHub repository KingingWang/crates-docs (13 stars, last pushed 29d ago), licensed MIT. It adds 2,240 tokens to every session, about $0.0112 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
docs-mcp AGENTS.md
Instructions for mmgeorge/docs-mcp, covering agents.md — developer and agent guide, project overview, data sources, key types and rustdoc json (format version 57).
docs-mcp CLAUDE.md
Instructions for mmgeorge/docs-mcp: See AGENTS.md for project architecture, conventions, and development guidance.
jira-commands CLAUDE.md
Claude Code instructions for mulhamna/jira-commands, covering claude.md — rust jira cli, claude rules — must follow, common commands, project overview and workspace structure.
jira-commands AGENTS.md
AGENTS.md instructions for mulhamna/jira-commands, a project described as: Jira toolkit for terminals, coding assistants, and bots.
jira-commands GEMINI.md
Gemini CLI instructions for mulhamna/jira-commands, a project described as: Jira toolkit for terminals, coding assistants, and bots.
social_dive CLAUDE.md
Claude Code instructions for krishddd/social_dive, covering social dive — developer conventions, language & environment, architecture rules, version sync and testing.