quorum CLAUDE.md

quorum CLAUDE.md is an instructions file for coding agents from berrzebb/quorum. It costs 184 tokens per session, scanned A, original, MIT.

Project instructions for quorum, a tool that checks work across multiple AI models and enforces structural rules. It documents the build, test, and development commands and several design constraints.

In plain words
What is it for?
Use it when developing quorum, running its tests or daemon, designing changes, or checking permissions, specifications, and stored state.
Why use it?
It keeps agents from bypassing the project's rules, such as delegating implementation to worker agents or treating files as the source of truth when the event database is authoritative.

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/berrzebb/quorum/claude-md
Clone the repo
git clone --depth 1 https://github.com/berrzebb/quorum

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 quorum CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/berrzebb/quorum/claude-md.svg)](https://agentmods.dev/instructions/berrzebb/quorum/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/berrzebb/quorum/claude-md"><img src="https://agentmods.dev/badge/instructions/berrzebb/quorum/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 184 This file is loaded in full into every session.
When invoked 184 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 5.1 $0.00184 $0.00184
Opus 5 $0.00092 $0.00092
Sonnet 5 $0.00037 $0.00037
Haiku 4.5 $0.00018 $0.00018

Measured 5d ago against content hash b74428101cf4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

quorum 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 · 23 lines

What it actually says

quorum

Cross-model audit gate with structural enforcement.

Commands

npm run build    # tsc compile
npm test         # node tests/run-suite.mjs all
npm run dev      # tsx daemon/index.ts
# Individual: node --test tests/{name}.test.mjs

Rules

  • Fail-open: all hooks pass through on error, no system lockout
  • Orchestrator never implements — always delegate to worker agents
  • Design before WB — Blueprint naming conventions are binding law
  • Fragment-only: spec.mjs = metadata, domain data in spec.{domain}.mjs fragments only
  • // scan-ignore suppresses runPatternScan findings on that line
  • SQLite (EventStore) = single source of truth — no verdict/state files
  • Deny rules bypass-immune (NFR-18) — no permission mode overrides deny
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 · 23 lines · 184 tokens per session scan A b74428101cf4

Subscribe to this mod's changes

quorum CLAUDE.md is an instructions file published in the GitHub repository berrzebb/quorum (10 stars, last pushed 4mo ago), licensed MIT. It adds 184 tokens to every session, about $0.0009 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.