Borrowing it
Nothing to install: this file belongs to agentculture/culture-tools. 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/agentculture/culture-tools/main/CLAUDE.mdgit clone --depth 1 https://github.com/agentculture/culture-toolsWrote 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/agentculture/culture-tools/claude-md)<a href="https://agentmods.dev/instructions/agentculture/culture-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/agentculture/culture-tools/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/agentculture/culture-tools/claude-md"><img src="https://agentmods.dev/badge/instructions/agentculture/culture-tools/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 | $0.03312 | $0.03312 |
| Opus 5 | $0.01656 | $0.01656 |
| Sonnet 5 | $0.00662 | $0.00662 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade A, and why
culture-tools 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 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.
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 — 239 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.
What this repo is
culture-tools is the agent that backs tools.culture.dev — the package index
for agent-first CLI tools that conform to the agentfront contract. Today the
repo is the canonical clonable scaffold (the former culture-agent-template):
an agent-first CLI, a mesh identity, the guildmaster skill kit, and a build/deploy
baseline. The site/index itself is being built out (see "Site build" below); the
Python package is the reference an agent clones to mint a new mesh agent.
The runtime package has zero third-party dependencies (dependencies = [] in
pyproject.toml). This is a hard constraint — whoami/doctor parse
culture.yaml by hand rather than import a YAML library. Do not add a runtime
dependency without an explicit decision to drop the zero-dep property; dev-only
tools belong in [dependency-groups].dev.
Identity, not a name you can assume
This agent runs backend: colleague (see culture.yaml), so its resident
prompt file is AGENTS.colleague.md, not CLAUDE.md. CLAUDE.md (this file)
guides Claude Code working in the repo; AGENTS.colleague.md is the prompt the
colleague mesh resident loads. doctor enforces this mapping
(colleague → AGENTS.colleague.md); a backend change in culture.yaml that isn't
taught to doctor will fail the backend-consistency invariant.
Commands
All Python work goes through uv. Python 3.12+ required.
uv sync # install deps (incl. dev group)
uv run pytest -n auto # full test suite (xdist parallel)
uv run pytest tests/test_cli.py::test_whoami_text # a single test
uv run pytest -k doctor # tests matching a name
uv run culture-tools <verb> # run the CLI (whoami, learn, …)
Lint (CI runs each of these; all must pass):
uv run black --check culture_tools tests
uv run isort --check-only culture_tools tests
uv run flake8 culture_tools tests
uv run bandit -c pyproject.toml -r culture_tools
markdownlint-cli2 "**/*.md" "#node_modules" "#.local" "#.claude/skills" "#.teken"
uv run teken cli doctor . --strict # the agent-first rubric gate
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.
- 9d ago First seen · 239 lines · 3,312 tokens per session scan A 842282068036
culture-tools CLAUDE.md is an instructions file published in the GitHub repository agentculture/culture-tools (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 3,312 tokens to every session, about $0.0166 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 2026-08-31.
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.
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.
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).
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).
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.
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.