Autosearch: Instructions file for Claude Code

CLAUDE.md

Autosearch CLAUDE.md is an instructions file for Claude Code from 0xmariowu/Autosearch. It costs 2,505 tokens per session, scanned C, original, MIT.

Repository instructions for AutoSearch, a self-improving search system where an AI turns a person's intent into search strategies, results, scoring, and iteration.

In plain words
What is it for?
Use them when changing AutoSearch, its search quality, agent workflows, tests, or contribution process.
Why use it?
They define the required tests, branch and commit practices, and rules against weakening tests or project configuration.

Instructions file for Claude Code

Written for Claude Code: Claude Code plugin machinery. Also seen: mentions Claude Code.

This is 0xmariowu/Autosearch's own configuration. It tells Claude Code how to work on Autosearch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Autosearch configures →

Reuse

Borrowing it

Nothing to install: this file belongs to 0xmariowu/Autosearch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/0xmariowu/Autosearch/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/0xmariowu/Autosearch

Made for: Claude Code.

Wrote 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.

agentmods badge for Autosearch CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/0xmariowu/autosearch/claude-md/github.svg)](https://agentmods.dev/instructions/0xmariowu/autosearch/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/0xmariowu/autosearch/claude-md"><img src="https://agentmods.dev/badge/instructions/0xmariowu/autosearch/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.

agentmods 80×15 button for Autosearch CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/0xmariowu/autosearch/claude-md"><img src="https://agentmods.dev/badge/instructions/0xmariowu/autosearch/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,505 This file is loaded in full into every session.
When invoked 2,505 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.02505 $0.02505
Opus 5 $0.01252 $0.01252
Sonnet 5 $0.00501 $0.00501
Haiku 4.5 $0.00250 $0.00250

Measured 9d ago against content hash 3baaf263ca9a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade C, and why

Autosearch CLAUDE.md scanned grade C with 2 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 9d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

- Re-install: `curl -fsSL https://raw.githubusercontent.com/0xmariowu/autosearch/main/scripts/install.sh | bash`

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Re-install: `curl -fsSL https://raw.githubusercontent.com/0xmariowu/autosearch/main/scripts/install.sh | bash`
CLAUDE.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AutoSearch — Project Rules

Behavioral rules for AI agents and human contributors working in this codebase.

What this is

A self-improving search system. The human provides intent. The AI does everything else: understand the goal, generate strategies, run them across all platforms, score results, reflect, iterate, and harvest.

Local test (run before push)

.venv/bin/python -m pytest tests/unit/ -x -q -m "not real_llm and not slow and not network"

Fast subset only (~4s). Full suite runs in CI.

Session Checklist

  1. If working on AVO/skills → read § AVO rules below
  2. If working on search quality → read PRINCIPLES.md

Workflow

  • Branch: feature/{desc}, fix/{desc} — don't develop on main
  • Commit: {type}: {description} (feat/fix/refactor/test/docs/chore)
  • One commit = one logical change. Commit sequence: source code first, tests second, docs/config third. Don't batch. Because: reviewers need to verify tests cover exactly the code that changed.
  • Feature commits without corresponding test commits will not pass review. Because: untested features are untested assumptions.
  • Don't stage the entire repo (git add . / git add -A). Stage specific files only. Because: prevents accidental inclusion of debug files, env changes, or unrelated edits.
  • Don't stage .env*, credentials, node_modules/, __pycache__/, or .git/ internals. Because: these files contain secrets or generated content that must not enter version control.
  • Don't modify linter or formatter config to suppress errors. Fix the code, not the config. Because: suppressing errors hides real problems and compounds technical debt.
  • Run ruff check && ruff format --check before commit. Because: pushing lint failures wastes CI time and blocks other PRs.
  • Tests: pytest -x -q must pass before push.
  • PR stays under 5 commits. Larger → split into smaller PRs first. Because: oversized PRs don't get meaningful review.
  • PR requires review before merge — don't self-merge. Because: self-review misses what a second pair of eyes catches.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 9d ago First seen · 125 lines · 2,505 tokens per session scan C 3baaf263ca9a

Subscribe to this mod's changes

Autosearch CLAUDE.md is an instructions file published in the GitHub repository 0xmariowu/Autosearch (43 stars, last pushed 1mo ago), licensed MIT. It adds 2,505 tokens to every session, about $0.0125 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

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.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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).

microsoft/vscode · 6,785 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

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.

langchain-ai/langchain · 4,469 tokens

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.

deepseek-ai/deepseek-harness · 3,735 tokens