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.
npx agentmods add instructions/inclusionai/avernet/agents-mdgit clone --depth 1 https://github.com/inclusionAI/AvernetWrote 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.
[](https://agentmods.dev/instructions/inclusionai/avernet/agents-md)<a href="https://agentmods.dev/instructions/inclusionai/avernet/agents-md"><img src="https://agentmods.dev/badge/instructions/inclusionai/avernet/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.03115 | $0.03115 |
| Opus 5 | $0.01558 | $0.01558 |
| Sonnet 5 | $0.00623 | $0.00623 |
| Haiku 4.5 | $0.00312 | $0.00312 |
Grade A, and why
Avernet AGENTS.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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file is the repository-wide instruction set for human contributors and AI coding agents working on OCB.
Source of Truth
Before changing code, read the files that define the boundary you are touching. For architecture-sensitive work, these documents are mandatory:
docs/arch/arch.rules.md— the OCB architecture constitution.docs/arch/ci.enforce.md— required CI gates for enforcing the constitution.docs/arch/context-boundary-format.md— required context boundary metadata for backend modules.docs/arch/protocol-contract-tests.md— required conformance test shape for plugin protocols.
If a module has its own AGENTS.md, follow it in addition to this file. The
more specific file controls only within that module.
Project Overview
OCB is a monorepo for a multi-bot AI workbench. It includes:
- bot lifecycle management
- multi-bot coordination through BCS
- chat and runtime adapter services
- a frontend workbench
- contract and architecture validation documents
Repository Layout
ocb/
├── docs/
│ ├── arch/ # Architecture constitution and CI constraints
│ └── open-source/ # Open-source readiness and design notes
├── scripts/ # Local orchestration and utility scripts
├── src/
│ ├── backend/ # Python backend service
│ ├── frontend/ # TypeScript frontend workbench
│ ├── engine/ # Python engine adapter
│ ├── bcs/ # Rust coordination service
│ └── tui/ # Rust terminal client
└── tests/ # Cross-module tests
Module Responsibilities
| Module | Directory | Responsibility |
|---|---|---|
| Frontend | src/frontend/ |
Web workbench UI |
| BCS | src/bcs/ |
Bot coordination, group chat, routing |
Entity ownership:
- Bot configuration, capabilities, and chat history belong to engine-facing services.
- User assets, bindings, and metadata belong to backend-facing services.
- Bot relationships, routing, and coordination belong to BCS.
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.
- today Changed · -2 lines · -28 tokens per session b31ed4de1998
- yesterday Changed · +2 lines · +30 tokens per session 9d91675aeb5e
- 6d ago First seen · 346 lines · 3,113 tokens per session scan A 484d8db73c79
Avernet AGENTS.md is an instructions file published in the GitHub repository inclusionAI/Avernet (533 stars, last pushed today), licensed Apache-2.0. It adds 3,115 tokens to every session, about $0.0156 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.
Other instructions, from other repositories
statewave-multi-agent-shared-context AGENTS.md
Instructions for smaramwbc/statewave-multi-agent-shared-context, covering statewave project memory, read it first and persist durable facts.
gemot CLAUDE.md
Claude Code instructions for justinstimatze/gemot, covering gemot, key commands and architecture.
coordinate-agents AGENTS.md
AGENTS.md instructions for hogancv/coordinate-agents, covering repository instructions for ai contributors, canonical identity, repository map, required checks and change rules.
dsh-experts CLAUDE.md
Instructions for libinyam/dsh-experts, covering dsh-experts 宪法, 业务红线（违反即回滚，没有例外）, 技术硬约定, 产品路线（已拍板） and 接点台账（已验证的 harness 接点及出处）.
agent-mesh-core AGENTS.md
AGENTS.md instructions for jcbmrrs/agent-mesh-core, covering claude.md, repository status, repository visibility: public since 2026-07-23, repo vs. live share split and what this system is for.
agent-mesh-core CLAUDE.md
Claude Code instructions for jcbmrrs/agent-mesh-core, a project described as: MCP coordination server for multi-agent (Claude Code, Codex, Ollama) task handoff, locking, and messaging over Tailscale.