Borrowing it
Nothing to install: this file belongs to alfredjeanlab/quench. 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/alfredjeanlab/quench/main/CLAUDE.mdgit clone --depth 1 https://github.com/alfredjeanlab/quenchWrote 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/alfredjeanlab/quench/claude-md)<a href="https://agentmods.dev/instructions/alfredjeanlab/quench/claude-md"><img src="https://agentmods.dev/badge/instructions/alfredjeanlab/quench/claude-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/alfredjeanlab/quench/claude-md"><img src="https://agentmods.dev/badge/instructions/alfredjeanlab/quench/claude-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 | $0.00522 | $0.00522 |
| Opus 5.5 | $0.00209 | $0.00209 |
| Sonnet 5.5 | $0.00104 | $0.00104 |
| Haiku 4.5 | $0.00052 | $0.00052 |
Grade A, and why
quench 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 2mo 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.
What it actually says
Quench (Quality Benchmarks)
A fast linting tool for AI agents that measures quality signals.
Configured via quench.toml.
Directory Structure
quench/
├── README.md # Human-focused introduction
├── crates/ # Rust workspace
│ └── cli/ # CLI binary
├── docs/
│ ├── specs/ # Feature specifications (the "what")
│ └── arch/ # Architecture decisions
├── plans/ # Implementation plans (the "how" and "when")
├── tests/
│ ├── specs/ # Behavioral tests (black-box, see tests/specs/CLAUDE.md)
│ └── fixtures/ # Test projects
└── scripts/ # Build and utility scripts
Unit Test Convention
Use sibling _tests.rs files instead of inline #[cfg(test)] modules:
// src/parser.rs
#[cfg(test)]
#[path = "parser_tests.rs"]
mod tests;
// src/parser_tests.rs
#![allow(clippy::unwrap_used, clippy::expect_used, clippy::panic)]
use super::*;
#[test]
fn parses_empty_input() { ... }
Why separate files?
- Shorter source files fit better in LLM context windows
- LOC metrics reflect implementation conciseness, not test volume
- Integration tests remain in
tests/as usual
Development Lifecycle
- Specs are written from
docs/specs/, not from implementation - Write specs first, mark unimplemented with
#[ignore = "TODO: Phase N"] - Implement feature in
src/ - Remove
#[ignore], verify specs pass - List passing specs in commit message
Commits
Use conventional commit format: type(scope): description
Types: feat, fix, chore, docs, test, refactor, perf, ci, build, style
Landing the Plane
Before committing changes:
- Unit tests in sibling
_tests.rsfiles - Bump
CACHE_VERSIONincrates/cli/src/cache.rsif check logic changed - Run
make checkwhich willcargo fmt --allcargo clippy --all -- -D warningscargo build --allcargo test --allcargo run -- check
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.
- 2mo ago First seen · 74 lines · 522 tokens per session scan A df791112fdfc
quench CLAUDE.md is an instructions file published in the GitHub repository alfredjeanlab/quench (2 stars, last pushed 6mo ago), licensed MIT. It adds 522 tokens to every session, about $0.0021 per session on Opus 5.5. 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 2026-08-31.
quench CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| quench CLAUDE.mdalfredjeanlab/quench | Instructions file | 2 | 6mo ago | MIT | A | 522 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 144k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 150k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,086 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 282k | 3d ago | MIT | A | 4,335 | Codex, OpenCode |