anchor CLAUDE.md

anchor CLAUDE.md is an instructions file for coding agents from peva3/anchor. It costs 213 tokens per session, scanned A, original, MIT.

A project instruction file for Anchor that directs coding agents to read AGENTS.md before changing code. It points to rules for testing, commits, project structure, linting, and agent collaboration.

In plain words
What is it for?
It is for guiding code changes in the Anchor project, including required checks, commit practices, file locations, and project-specific architecture guidance.
Why use it?
It helps agents follow the project’s established rules and avoid unauthorized changes such as creating pull requests or other GitHub activity.

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/peva3/anchor/claude-md
Clone the repo
git clone --depth 1 https://github.com/peva3/anchor

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 anchor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/peva3/anchor/claude-md.svg)](https://agentmods.dev/instructions/peva3/anchor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/peva3/anchor/claude-md"><img src="https://agentmods.dev/badge/instructions/peva3/anchor/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 213 This file is loaded in full into every session.
When invoked 213 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 $0.00213 $0.00213
Opus 5 $0.00106 $0.00106
Sonnet 5 $0.00043 $0.00043
Haiku 4.5 $0.00021 $0.00021

Measured 4d ago against content hash 13d0850a69bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

anchor 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 · 18 lines

What it actually says

CLAUDE.md — Claude Code Agent Instructions

This file provides instructions to Claude Code (Anthropic's CLI agent). For full project guidance, see AGENTS.md.

All project rules, patterns, and requirements are defined in AGENTS.md.

Read AGENTS.md before making any changes. Follow every section:

  • Section 1: Core Principles (no dead code, test-first, proven integration)
  • Section 2: Commit Protocol (auto-push after validation if gh works)
  • Section 5: Project Structure (tests/, docs/, research/ folders required)
  • Section 9: Linting (full vulture sweep before every commit)
  • Section 15: Human-sounding commits (WHY-focused, not AI-sounding)
  • Section 22-26: Multi-agent patterns, verification gates, failure modes, gotchas

Never go rogue. Do not create PRs, issues, or GitHub activity without explicit user approval.

For system architecture details, see DEEPDIVE.md in the project root.

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 · 18 lines · 213 tokens per session scan A 13d0850a69bc

Subscribe to this mod's changes

anchor CLAUDE.md is an instructions file published in the GitHub repository peva3/anchor (8 stars, last pushed 15d ago), licensed MIT. It adds 213 tokens to every session, about $0.0011 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.