ring CLAUDE.md

ring CLAUDE.md is an instructions file for coding agents from LerianStudio/ring. It costs 1,703 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Ring, including rules for creating and reviewing AI-agent files in a software repository.

In plain words
What is it for?
Use them when modifying agent definitions, checking required sections and examples, loading standards, running reviewers, or following test-driven development, where tests are written before implementation.
Why use it?
They require agents to verify their work, follow approval gates, report uncertainty, and use the project's testing and standards process.

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/lerianstudio/ring/claude-md
Clone the repo
git clone --depth 1 https://github.com/LerianStudio/ring

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 ring CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lerianstudio/ring/claude-md.svg)](https://agentmods.dev/instructions/lerianstudio/ring/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/lerianstudio/ring/claude-md"><img src="https://agentmods.dev/badge/instructions/lerianstudio/ring/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,703 This file is loaded in full into every session.
When invoked 1,703 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 $0.01703 $0.01703
Opus 5 $0.00851 $0.00851
Sonnet 5 $0.00341 $0.00341
Haiku 4.5 $0.00170 $0.00170

Measured 4d ago against content hash 1e22499a6f0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ring 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 4d 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 · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 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.

AGENTS.md is a symlink to this file — edit CLAUDE.md only; changes propagate automatically.


⛔ CRITICAL RULES (READ FIRST)

1. Agent Modification = Mandatory Verification

When creating or modifying any agent in */agents/*.md:

  • MUST verify agent has all required sections — see docs/AGENT_DESIGN.md
  • MUST include positive <example> blocks showing correct behavior
  • MUST keep agents under 300 lines (implementation) or 200 lines (reviewers)
  • MUST use selective standards loading via index.md (selective sections only, not monolithic WebFetch).
  • If any section is missing → Agent is INCOMPLETE

2. Agents are EXECUTORS, Not DECISION-MAKERS

  • Agents VERIFY, they DO NOT ASSUME
  • Agents REPORT blockers, they DO NOT SOLVE ambiguity autonomously
  • Agents FOLLOW gates, they DO NOT SKIP gates
  • Agents ASK when uncertain, they DO NOT GUESS

3. Anti-Patterns (MUST NOT do these)

  1. MUST NOT skip ring:using-ring — mandatory, not optional
  2. MUST NOT run reviewers sequentially — dispatch in parallel
  3. MUST NOT skip TDD's RED phase — test must fail before implementation
  4. MUST NOT ignore skill when applicable — "simple task" is not an excuse
  5. ZERO PANIC POLICYpanic(), log.Fatal(), and Must* helpers are FORBIDDEN everywhere (including bootstrap/init). Return (T, error) instead. Only exception: regexp.MustCompile() with compile-time constants.
  6. MUST NOT commit manually — use ring:committing-changes skill
  7. MUST NOT assume compliance — VERIFY with evidence

4. Unified Ring Namespace (MANDATORY)

All Ring components use the unified ring: prefix.

  • ring:code-reviewer, ring:backend-go
  • ❌ omitting ring: prefix (FORBIDDEN)
  • ring-default:ring:code-reviewer (deprecated plugin-specific prefix)

Read the full file on GitHub · 149 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. 4d ago First seen · 149 lines · 1,703 tokens per session scan A 1e22499a6f0b

Subscribe to this mod's changes

ring CLAUDE.md is an instructions file published in the GitHub repository LerianStudio/ring (210 stars, last pushed 15d ago), licensed Apache-2.0. It adds 1,703 tokens to every session, about $0.0085 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.