Borrowing it
Nothing to install: this file belongs to retemper/litmus. 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/retemper/litmus/main/CLAUDE.mdgit clone --depth 1 https://github.com/retemper/litmusWrote 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/retemper/litmus/claude-md)<a href="https://agentmods.dev/instructions/retemper/litmus/claude-md"><img src="https://agentmods.dev/badge/instructions/retemper/litmus/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/retemper/litmus/claude-md"><img src="https://agentmods.dev/badge/instructions/retemper/litmus/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 | $0.00573 | $0.00573 |
| Opus 5.5 | $0.00229 | $0.00229 |
| Sonnet 5.5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
litmus 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
litmus — how to respond to it
litmus is a test-planning guardrail. When it speaks, it is reminding you not to finish a change without deciding how it gets tested.
When a litmus reminder appears
- Advisory message (
🧪 litmus …): a non-blocking nudge. Consider the suggested test types. If the change genuinely needs no tests, say why in one line and move on. Don't ignore it silently. - Block reason (
STOP — litmus (block mode) …): the turn is held. Do exactly what it says, in two steps:- Triage into one markdown table (test type · needed? · one-line reason · existing test path). Call the litmus
list_test_typestool for the full map, and search the repo for existing tests before deciding. Then stop and ask the user which types to write in detail. - Design only the confirmed types — load each type's rules with the litmus
get_guidetool (or readguides/NN-*.md) first, then write cases. Extend existing tests instead of duplicating.
- Triage into one markdown table (test type · needed? · one-line reason · existing test path). Call the litmus
Treat litmus signals as hints, not verdicts
The test types litmus suggests come from regex over file paths and diffs — it cannot read code semantics. Confirm each suggestion against what the change actually does. A medium confidence signal is "consider"; high is "likely needed".
Writing tests
- Always load the relevant guide before writing cases for that type — call the litmus
get_guidetool (e.g.get_guide "unit"), or readguides/NN-*.md. It lists the must-cover cases and the writing principles. - Test observable behaviour through the public interface; don't mock internal collaborators or test private methods.
- Use
/tddto drive a change test-first.
litmus MCP tools
The plugin runs a small MCP server exposing three tools:
list_test_types— the full four-level, nine-type map. Start here when unsure.get_guide— the full guide for one type; accepts a name, file, number, or alias.recommend_guide— suggests guides from a role and/or a short situation.
These read the guides at call time, so guide edits take effect without a rebuild.
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 · 34 lines · 573 tokens per session scan A 8ecca108f211
litmus CLAUDE.md is an instructions file published in the GitHub repository retemper/litmus (0 stars, last pushed 3mo ago), licensed MIT. It adds 573 tokens to every session, about $0.0023 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.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.