agent-3md CLAUDE.md

agent-3md CLAUDE.md is an instructions file for coding agents from CorvidLabs/agent-3md. It costs 57 tokens per session, scanned A, original, MIT.

A repository instruction file that tells Claude Code to follow CorvidLabs' trust and verification process before changing code.

In plain words
What is it for?
Use it when working in that repository to find the standing rules in AGENTS.md and run the required verification commands before making changes.
Why use it?
It prevents changes from skipping required checks and review gates.

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/corvidlabs/agent-3md/claude-md
Clone the repo
git clone --depth 1 https://github.com/CorvidLabs/agent-3md

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 agent-3md CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/corvidlabs/agent-3md/claude-md.svg)](https://agentmods.dev/instructions/corvidlabs/agent-3md/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/corvidlabs/agent-3md/claude-md"><img src="https://agentmods.dev/badge/instructions/corvidlabs/agent-3md/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 57 This file is loaded in full into every session.
When invoked 57 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 $0.00057 $0.00057
Opus 5 $0.00028 $0.00028
Sonnet 5 $0.00011 $0.00011
Haiku 4.5 $0.00006 $0.00006

Measured 5d ago against content hash a9b459522c8d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent-3md 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 · 6 lines

What it actually says

CLAUDE.md

This repo is governed by the CorvidLabs trust toolchain. See AGENTS.md for the standing rules block and follow it before making changes (run fledge lanes run verify; never bypass the augur, attest, or spec gates).

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 · 6 lines · 57 tokens per session scan A a9b459522c8d

Subscribe to this mod's changes

agent-3md CLAUDE.md is an instructions file published in the GitHub repository CorvidLabs/agent-3md (1 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session, about $0.0003 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.