agent2 CLAUDE.md

agent2 CLAUDE.md is an instructions file for coding agents from Artesiana/agent2. It costs 312 tokens per session, scanned A, original, MIT.

Project instructions for Artesiana's agent2 that explain how to route requests to the project's specialized workflows and keep documentation aligned with the Brain Clone approach.

In plain words
What is it for?
Use them when working on domain experts, agents, knowledge collections, agent capabilities, or related project documentation.
Why use it?
They give the coding agent consistent rules for choosing the right workflow and locating the project's source documentation.

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/artesiana/agent2/claude-md
Clone the repo
git clone --depth 1 https://github.com/Artesiana/agent2

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 agent2 CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/artesiana/agent2/claude-md.svg)](https://agentmods.dev/instructions/artesiana/agent2/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/artesiana/agent2/claude-md"><img src="https://agentmods.dev/badge/instructions/artesiana/agent2/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 312 This file is loaded in full into every session.
When invoked 312 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 $0.00312 $0.00312
Opus 5 $0.00156 $0.00156
Sonnet 5 $0.00062 $0.00062
Haiku 4.5 $0.00031 $0.00031

Measured 6d ago against content hash 852e28f8452e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

agent2 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 6d 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 · 28 lines

What it actually says

@AGENTS.md

Claude Code

Use /brain-clone for new domain expert agents. It should produce agents that look more like agents/procurement-compliance-officer than example-agent.

Keep this file short. Project-wide rules live in AGENTS.md; detailed framework context lives in llms.txt, llms-full.txt, and docs/brain-clone-pattern.md.

When editing skills, preserve the Brain Clone concept. Only update skills to point at current canonical examples, runtime behavior, and docs.

Skill routing

When the user's request matches an available skill, invoke it via the Skill tool. When in doubt, invoke the skill — a false positive is cheaper than an ad-hoc answer that misses the structured workflow.

Key routing rules:

  • New domain expert / "clone my brain" / "brain clone" → invoke /brain-clone
  • New simple agent / "scaffold agent" / "add agent" → invoke /creating-agents
  • Agent needs domain knowledge / documents / books → invoke /building-domain-experts
  • Add knowledge collections / R2R / ingest PDFs → invoke /adding-knowledge
  • Add pause/resume, approval, provider routing → invoke /adding-capabilities
  • Agent errors / 500s / mock data / "agent broken" / "doesn't work" → invoke /debugging-agents
  • Test agent / QA / "does this agent work" / health check → invoke /agent-qa
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. 6d ago First seen · 28 lines · 312 tokens per session scan A 852e28f8452e

Subscribe to this mod's changes

agent2 CLAUDE.md is an instructions file published in the GitHub repository Artesiana/agent2 (36 stars, last pushed 4mo ago), licensed MIT. It adds 312 tokens to every session, about $0.0016 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.