Borrowing it
Nothing to install: this file belongs to ehmo/autoresearch-skill. 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/ehmo/autoresearch-skill/main/CLAUDE.mdgit clone --depth 1 https://github.com/ehmo/autoresearch-skillWrote 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/ehmo/autoresearch-skill/claude-md)<a href="https://agentmods.dev/instructions/ehmo/autoresearch-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ehmo/autoresearch-skill/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/ehmo/autoresearch-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/ehmo/autoresearch-skill/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 | $0.00557 | $0.00557 |
| Opus 5.5 | $0.00223 | $0.00223 |
| Sonnet 5.5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00056 | $0.00056 |
Grade A, and why
autoresearch-skill 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autoresearch
Autonomous codebase improvement using three independent teams.
Structure
skills/autoresearch/SKILL.md-- the protocol (team prompts, cycle management, all logic)commands/autoresearch.md-- slash command entry pointagents/codex.md-- standalone protocol for Codex and other agentsinstall.sh/uninstall.sh-- symlinks into ~/.claude/sessions/-- per-project session data (gitignored)
How cycles run
- Red team reads code, writes findings report (read-only)
- Coordinator sanitizes findings (strips methodology, keeps what/where/impact)
- Green team fixes issues one at a time with test verification
- Refactor team simplifies recently-changed code
- Coordinator verifies tests, logs results, starts next cycle
Conventions
User-facing text should avoid AI writing patterns. Keep language direct and specific. No promotional phrasing, no filler.
Skimmable Code Rules
Default to code that is obvious on a fast read.
- Keep code short. Prefer fewer lines and fewer moving parts.
- Remove any change that is not strictly required.
- Minimize state. Narrow types, reduce arguments, and do not carry optional values unless they are truly optional.
- Prefer explicit tagged state over loose bags of flags. Use discriminated unions, enums with payloads, or equivalent typed variants.
- Exhaustively handle variant types. Fail fast on unknown cases.
- Trust the types. Do not add defensive code for states the types already rule out.
- Assert required inputs and loaded data at the boundary. If something must exist, assert it instead of using defaults, fallbacks, or try/catch.
- Prefer early returns over deep nesting.
- Keep functions direct. Split code only when it makes the code easier to scan.
- Avoid clever abstractions, override-heavy APIs, and optional parameters that are actually required.
Rob Pike's Programming Rules
Adopt these as the default coding rules for this repo:
- You can't predict where a program will spend its time. Don't add speed hacks until a real bottleneck is proven.
- Measure before tuning. Only optimize after data shows one part of the system dominates the cost.
- Fancy algorithms are often slower when
nis small, andnis usually small. Start simple unless measurements say otherwise. - Fancy algorithms are usually buggier and harder to maintain. Prefer simple algorithms and simple data structures.
- Data dominates. Choose clear, well-shaped data structures first; the right algorithms usually follow from them.
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 · 51 lines · 557 tokens per session scan A 5c7341ff928c
autoresearch-skill CLAUDE.md is an instructions file published in the GitHub repository ehmo/autoresearch-skill (54 stars, last pushed 6mo ago), licensed MIT. It adds 557 tokens to every session, about $0.0022 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 2026-08-30.
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.