agentmods.dev

Avernet: Instructions file for Claude Code

CLAUDE.md

Avernet CLAUDE.md is an instructions file for Claude Code from inclusionAI/Avernet. It costs 4,356 tokens per session, scanned A, original, Apache-2.0.

Repository instructions for Avernet, an open-source infrastructure project for persistent, coordinated systems made of multiple agents. They describe the project architecture, its Git remotes, branches, and rules for making changes.

In plain words
What is it for?
Use them before changing Avernet architecture or Rust and application code, especially when selecting a branch, remote, or repository context.
Why use it?
They prevent changes from being made in the wrong repository, branch, or architectural layer. They also clarify which upstream can receive pushes and which is only a mirror.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code; mentions AGENTS.md.

This is inclusionAI/Avernet's own configuration. It tells Claude Code how to work on Avernet itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Avernet configures →

not rated 593repo +53 today A scan 4,356 tokens original Apache-2.0
View source ↗ inclusionAI/Avernet avernet.cc
Reuse

Borrowing it

Nothing to install: this file belongs to inclusionAI/Avernet. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/inclusionAI/Avernet/dev/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/inclusionAI/Avernet

Made for: Claude Code.

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 Avernet CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/inclusionai/avernet/claude-md/github.svg)](https://agentmods.dev/instructions/inclusionai/avernet/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/inclusionai/avernet/claude-md"><img src="https://agentmods.dev/badge/instructions/inclusionai/avernet/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Avernet CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/inclusionai/avernet/claude-md"><img src="https://agentmods.dev/badge/instructions/inclusionai/avernet/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,356 This file is loaded in full into every session.
When invoked 4,356 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.04356 $0.04356
Opus 5.5 $0.01742 $0.01742
Sonnet 5.5 $0.00871 $0.00871
Haiku 4.5 $0.00436 $0.00436

Measured 6d ago against content hash 65ea884937bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

Avernet 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 · 362 lines

How it starts

The opening of the file, as written. The whole thing — 362 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.

What this repository is

Avernet (inclusionAI/Avernet) is the open-source infrastructure layer for persistent, coordinated, multi-agent systems at organizational scale. It is the upstream / community codebase that ocb consumes as a git submodule; this checkout is standalone (no agentclaw.corp, no MOSN, no company-internal services). When changing code here, you are changing the OSS project — keep it public-clean and reproducible from public dependencies.

The two Git remotes are not interchangeable:

  • github → github.com/inclusionAI/Avernet — push here (the real source).
  • origin → code.alipay.com/mirrors/Avernet — AntCode mirror, fetch-only. Pushing to origin is rejected for lack of write permission and an email check; do not rewrite the dev upstream history to work around either.

Integration branch is dev (rebase, never merge). Some CI gates (architecture-checks.yml) only run on main; unit-tests.yml / frontend-nextgen.yml run on dev, main, and REL*. Spawn fix/feature branches from dev, not from a REL tip — a REL-based PR diff swallows the full release history.

Read before touching architecture-sensitive code

The AGENTS.md at the root is the binding contributor contract. For boundary work also read:

  • CONTEXT-MAP.md — the entry point that routes you to the right module context.
  • CONTEXT.md — shared product vocabulary (Skill lifecycle, Spaces, Bot consumption, external publication). This glossary is the authority for naming in product, code, schemas, and review.
  • docs/arch/arch.rules.md — the Microkernel Architecture Constitution v3.1 (contracts are the single authority; every plugin Protocol has local/ and prod/ implementations plus Noop/Mock; conformance tests under tests/contracts/; configuration-driven wiring — no scattered if is_local).
  • docs/adr/ — accepted/superseded system decisions.
  • Module-local AGENTS.md / CLAUDE.md override the root only within their module. Currently: apps/bcs/CLAUDE.md + apps/bcs/AGENTS.md, apps/frontend-nextgen/CLAUDE.md, apps/frontend/AGENTS.md.

Read the full file on GitHub · 362 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. 6d ago First seen · 362 lines · 4,356 tokens per session scan A 65ea884937bb

Subscribe to this mod's changes

Avernet CLAUDE.md is an instructions file published in the GitHub repository inclusionAI/Avernet (593 stars, last pushed today), licensed Apache-2.0. It adds 4,356 tokens to every session, about $0.0174 per session on Opus 5.5. 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 2026-10-20.

Building agentsGit and workflowagent-coordinationagent-infrastructureagent-organizationdsh-pluginshuman-in-the-loop-aimulti-agent-coordination
Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,581 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 4,261 tokens