Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/victorvvedtion/ouro-loop/claude-mdgit clone --depth 1 https://github.com/VictorVVedtion/ouro-loopWrote 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/victorvvedtion/ouro-loop/claude-md)<a href="https://agentmods.dev/instructions/victorvvedtion/ouro-loop/claude-md"><img src="https://agentmods.dev/badge/instructions/victorvvedtion/ouro-loop/claude-md.svg" alt="Measured on agentmods" 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 | $0.01281 | $0.01281 |
| Opus 5 | $0.00641 | $0.00641 |
| Sonnet 5 | $0.00256 | $0.00256 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
ouro-loop 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 5d 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 — 133 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.
Project Overview
Ouro Loop — an open-source framework providing structured autonomous loops with runtime-enforced guardrails for AI coding agents (Claude Code, Cursor, Aider, Codex). Python 3.10+, zero external dependencies (pure stdlib).
Four-file core:
program.md— methodology instructions (6-stage loop: BOUND → MAP → PLAN → BUILD → VERIFY → LOOP)framework.py— runtime CLI state machine (.ouro/state.json, verification gates, logging)prepare.py— project initialization and scanning (read-only operations)sentinel.py— 24/7 autonomous code review (partition scanning, runner, dashboard)
Commands
Tests
python -m pytest tests/ -v # run all tests
python -m pytest tests/test_framework.py -v # single test file
python -m pytest tests/test_framework.py::TestClassName::test_name -v # single test
Lint (hooks only)
shellcheck hooks/*.sh
Framework CLI (used by agents, not for development)
python framework.py status . # show current state
python framework.py verify . # run verification gates
python framework.py log PASS --path . # record phase result
python framework.py advance . # advance to next stage
python framework.py bound-check . # BOUND compliance check
Prepare CLI
python prepare.py scan . # scan project structure
python prepare.py init . # initialize .ouro/ directory
python prepare.py template claude . # install CLAUDE.md template
Sentinel CLI
ouro-sentinel init . # scan project → generate partitions + config + CLAUDE.md
ouro-sentinel partition . # regenerate partitions
ouro-sentinel status . # show iteration/findings/coverage
ouro-sentinel install . # install runner + dashboard scripts
Docs (MkDocs Material)
pip install mkdocs-material pymdown-extensions
mkdocs serve # local preview
mkdocs build # build static site
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.
- 5d ago First seen · 133 lines · 1,281 tokens per session scan A ed366457bf0d
ouro-loop CLAUDE.md is an instructions file published in the GitHub repository VictorVVedtion/ouro-loop (19 stars, last pushed 5mo ago), licensed MIT. It adds 1,281 tokens to every session, about $0.0064 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 2026-08-30.
Other instructions, from other repositories
pydantic-ai-shields AGENTS.md
Instructions for vstorm-co/pydantic-ai-shields, covering agents.md, project overview, quick reference, architecture and capabilities.
pydantic-ai-shields CLAUDE.md
Instructions for vstorm-co/pydantic-ai-shields, covering claude.md, project overview, development commands, project structure and core components.
claudini CLAUDE.md
Instructions for romovpa/claudini, covering claudini — developer guide, package manager, running benchmarks, run a preset (all methods, all samples) and override method, sample, seed, budget from cli.
Neuroverseos-governance AGENTS.md
Instructions for NeuroverseOS/Neuroverseos-governance, covering neuroverse governance — agent integration guide, what this package does, quick start for agents, install and enforce a world (permanent rules).
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
dev-agent-skills CLAUDE.md
Claude Code instructions for fvadicamo/dev-agent-skills, covering claude.md, project overview, architecture, key file: marketplace.json and skill anatomy.