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/zircote/rlm-rs/claude-mdgit clone --depth 1 https://github.com/zircote/rlm-rsWrote 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/zircote/rlm-rs/claude-md)<a href="https://agentmods.dev/instructions/zircote/rlm-rs/claude-md"><img src="https://agentmods.dev/badge/instructions/zircote/rlm-rs/claude-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 | $0.01656 | $0.01656 |
| Opus 5 | $0.00828 | $0.00828 |
| Sonnet 5 | $0.00331 | $0.00331 |
| Haiku 4.5 | $0.00166 | $0.00166 |
Grade A, and why
rlm-rs CLAUDE.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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
rlm_rs is a Rust crate built with modern tooling, strict type safety, and zero-cost abstractions.
Project Structure
src/
├── lib.rs # Library entry point and public API
├── main.rs # Binary entry point (optional)
├── error.rs # Error types (if separated)
└── ... # Additional modules
tests/
└── integration_test.rs # Integration tests
benches/ # Benchmarks (with criterion)
examples/ # Example programs
Build Commands
This project uses Cargo as the build system.
# Build the project
cargo build
# Build with optimizations
cargo build --release
# Run tests
cargo test
# Run tests with output
cargo test -- --nocapture
# Run specific test
cargo test test_name
# Run benchmarks
cargo bench
# Run linting
cargo clippy --all-targets --all-features
# Format code
cargo fmt
# Check formatting
cargo fmt -- --check
# Generate documentation
cargo doc --open
# Check supply chain security
cargo deny check
# Run with MIRI (undefined behavior detection)
cargo +nightly miri test
# Run all checks (lint + format + test + doc + deny)
cargo fmt -- --check && cargo clippy --all-targets --all-features -- -D warnings && cargo test && cargo doc --no-deps && cargo deny check
Code Style Requirements
This project uses clippy with pedantic and nursery lints, and rustfmt for formatting.
Key Rules
- Line length: 100 characters
- Edition: 2024
- MSRV: 1.95
- Unsafe code: Forbidden unless explicitly justified
- Panics: Not allowed in library code (
unwrap,expect,panic!)
Error Handling
Always use Result types for fallible operations. Never panic in library code:
// Good - Returns Result
pub fn parse(input: &str) -> Result<Value, ParseError> {
if input.is_empty() {
return Err(ParseError::EmptyInput);
}
// parsing logic
Ok(value)
}
// Bad - Panics
pub fn parse(input: &str) -> Value {
input.parse().unwrap() // Never do this in library code
}
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 · 297 lines · 1,656 tokens per session scan A e1bd944a1692
rlm-rs CLAUDE.md is an instructions file published in the GitHub repository zircote/rlm-rs (59 stars, last pushed 5d ago), licensed MIT. It adds 1,656 tokens to every session, about $0.0083 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
zeph rust.instructions.md
Instructions for bug-ops/zeph, covering rust file review, lints, async patterns, type conventions and test code.
sema CLAUDE.md
Claude Code instructions for sema-lisp/sema, a project described as: A Lisp with first-class LLM primitives, implemented in Rust.
flow-like CLAUDE.md
Claude Code instructions for Rheosoph/flow-like, covering claude.md — flow-like, repository layout, build & dev commands, rust and full workspace check.
flow-like copilot-instructions.md
Copilot instructions for Rheosoph/flow-like, covering flow-like wasm node development — rust, project overview, build & test, architecture and pin types.
flow-like frontend.instructions.md
Instructions for Rheosoph/flow-like, covering project coding standards for typescript and react, typescript guidelines, react guidelines, ui framework and code quality.
obsidian-mcp-rs CLAUDE.md
Instructions for MrRefactoring/obsidian-mcp-rs, covering claude.md, commands, build / run, tests and lint gates enforced by ci (.github/workflows/ci.yml).