rigour CLAUDE.md

rigour CLAUDE.md is an instructions file for coding agents from rigour-labs/rigour. It costs 2,015 tokens per session, scanned A, original, MIT.

Repository instructions for Rigour, a project that uses automated quality gates to check engineering work.

In plain words
What is it for?
Use them when implementing or reviewing code under Rigour’s governance process, including explaining and fixing failed checks.
Why use it?
They require agents to recall project guidance, check established patterns, and run verification before declaring a task complete.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/rigour-labs/rigour/claude-md
Clone the repo
git clone --depth 1 https://github.com/rigour-labs/rigour

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 rigour CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rigour-labs/rigour/claude-md.svg)](https://agentmods.dev/instructions/rigour-labs/rigour/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rigour-labs/rigour/claude-md"><img src="https://agentmods.dev/badge/instructions/rigour-labs/rigour/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,015 This file is loaded in full into every session.
When invoked 2,015 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.02015 $0.02015
Opus 5 $0.01007 $0.01007
Sonnet 5 $0.00403 $0.00403
Haiku 4.5 $0.00201 $0.00201

Measured 5d ago against content hash 046b7e0aa2ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rigour 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.

CLAUDE.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - Project Instructions for Claude Code

This file provides Claude Code with context about this project.

Project Overview

This project uses Rigour for quality gates. Always run npx @rigour-labs/cli check before marking tasks complete.

Commands

# Verify quality gates
npx @rigour-labs/cli check

# Get fix packet for failures
npx @rigour-labs/cli explain

# Self-healing agent loop
npx @rigour-labs/cli run -- claude "<task>"

🛡️ Rigour: Mandatory Engineering Governance Protocol

You are an AI Engineering Agent governed by Rigour.

Your access to this codebase is conditional upon your strict adherence to the Rigour Governance Protocol. This is an automated requirement for every engineering task.

🚦 The Mandatory Governance Loop

You MUST execute this loop for every task. No code changes will be accepted as "Done" until they pass all Rigour quality gates.

  1. Context Loading: Call rigour_recall (MCP) to align with project-specific engineering memory.
  2. Verify Patterns: Before implementing new logic, call rigour_check_pattern to prevent reinvention and ensure security compliance.
  3. Audit Enforcement: Before finishing, you MUST call npx @rigour-labs/cli check.
  4. Failure Remediation: If the check returns FAIL, you MUST implement all required engineering refinements.
  5. PASS or REJECT: You may only declare a task complete when the check returns PASS.

⚖️ Transparency & Accountability

Every action, tool call, and logic shift you perform is automatically logged to the project's local audit trail. This data is visible in real-time in the human-monitored Rigour Studio.

🤖 CRITICAL INSTRUCTION FOR AI

When asked to implement a feature or fix an issue:

  1. FIRST: Read ALL relevant rules files (e.g., .cursor/rules/*.mdc, .clinerules, docs/AGENT_INSTRUCTIONS.md).
  2. NEVER claim "done" until you can demonstrate the feature WORKS or the fix is verified.
  3. ALWAYS run npx @rigour-labs/cli check before claiming completion.
  4. CONNECTivity:
    • If you create backend code, you MUST wire it to the frontend.
    • If you create a service, you MUST connect it to the UI.

Read the full file on GitHub · 246 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. 5d ago First seen · 246 lines · 2,015 tokens per session scan A 046b7e0aa2ab

Subscribe to this mod's changes

rigour CLAUDE.md is an instructions file published in the GitHub repository rigour-labs/rigour (26 stars, last pushed 14d ago), licensed MIT. It adds 2,015 tokens to every session, about $0.0101 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.