agentmods.dev

ouro: Instructions file for Claude Code

CLAUDE.md

ouro CLAUDE.md is an instructions file for Claude Code from ouro-ai-labs/ouro. It costs 2,117 tokens per session, scanned A, original, MIT.

Repository instructions for ouro-ai-labs/ouro, an AI coding project, that explain how an agent should inspect, change, test, and publish code.

In plain words
What is it for?
Use them when setting up local development, finding available commands, planning changes, running checks, formatting, building, or publishing ouro.
Why use it?
They reduce mistakes caused by guessing commands or editing before understanding the codebase. They provide a repeatable workflow for checking work and keeping changes reviewable.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is ouro-ai-labs/ouro's own configuration. It tells Claude Code how to work on ouro 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 ouro configures →

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is # each worktree (example: ../ouro-my-branch).

not rated 47repo +1 3mo ago A scan 2,117 tokens original MIT
View source ↗ ouro-ai-labs/ouro
Reuse

Borrowing it

Nothing to install: this file belongs to ouro-ai-labs/ouro. 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/ouro-ai-labs/ouro/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/ouro-ai-labs/ouro

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 ouro CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/ouro-ai-labs/ouro/claude-md"><img src="https://agentmods.dev/badge/instructions/ouro-ai-labs/ouro/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,117 This file is loaded in full into every session.
When invoked 2,117 The same file — it is already loaded in full.
Security scan A 0 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 $0.02117 $0.02117
Opus 5.5 $0.00847 $0.00847
Sonnet 5.5 $0.00423 $0.00423
Haiku 4.5 $0.00212 $0.00212

Measured 2mo ago against content hash e61a207c45c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ouro 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.

CLAUDE.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ouro — Agent Instructions

This file defines the operational workflow for making changes in this repo (how to set up, run, test, format, build, and publish). Keep it short, specific, and executable; link to docs for long explanations.

Note: AGENTS.md is a symlink to this file (CLAUDE.md) for compatibility with multiple agent/rules systems.

Prerequisites: Python 3.12+ and uv (https://github.com/astral-sh/uv).

Command Discovery (No Guessing)

IMPORTANT: Never assume a CLI flag or dev command exists.

  • For ouro CLI flags: run python main.py -h (and python main.py --mode interactive -h if relevant).
  • For repo workflow commands: run ./scripts/dev.sh --help.

Core Workflow (Verify → Explore → Plan → Implement → Ship)

This repo expects a verification-driven workflow:

  • Verify: always define how correctness will be checked (tests, expected output, smoke command).
  • Explore: read/grep before editing; confirm where the behavior lives.
  • Plan: for multi-file or unfamiliar areas, write a short step plan + test plan before changing code.
  • Implement: make the smallest change that satisfies acceptance criteria; keep diffs reviewable.
  • Ship: run ./scripts/dev.sh check + update PR summary/checklist.

Skip the explicit plan only when the change is truly tiny and local (e.g., typo, small refactor in one file).

Quickstart (Local Dev)

./scripts/bootstrap.sh
source .venv/bin/activate
./scripts/dev.sh test

Optional (recommended): enable git hooks:

pre-commit install

Three-Layer Architecture (Read First)

The codebase is organized into three namespace subpackages with a strict import direction enforced by import-linter:

ouro.interfaces  →  ouro.capabilities  →  ouro.core

Reverse imports are forbidden. Run ./scripts/dev.sh importlint to verify. See ouro/CLAUDE.md for the layer contract.

Scoped Instructions (Read When Touching These Areas)

This repo uses directory-scoped rule files for focus. If you modify code/docs under these paths, also read the matching file first:

Read the full file on GitHub · 225 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. 2mo ago First seen · 225 lines · 2,117 tokens per session scan A e61a207c45c8

Subscribe to this mod's changes

ouro CLAUDE.md is an instructions file published in the GitHub repository ouro-ai-labs/ouro (47 stars, last pushed 3mo ago), licensed MIT. It adds 2,117 tokens to every session, about $0.0085 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.

agentaiai-agentsbotclawcoding-agent
Related

ouro CLAUDE.md compared with instructions from other repositories

ouro CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
ouro CLAUDE.mdouro-ai-labs/ouroInstructions file473mo agoMITA2,117Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode