What is gnap CLAUDE.md?

Repository instructions for farol-team/gnap, a specification for coordinating AI agents through Git. It explains the protocol's entities, files, states, and onboarding process.

Use them when editing the GNAP specification, its JSON examples, onboarding documentation, contribution guide, or protocol files.

They help an agent understand that the repository defines a protocol rather than a conventional application, preventing changes that conflict with its structure.

How farol-team/gnap configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to farol-team/gnap. 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/farol-team/gnap/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/farol-team/gnap

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/farol-team/gnap/claude-md/github.svg)](https://agentmods.dev/instructions/farol-team/gnap/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/farol-team/gnap/claude-md"><img src="https://agentmods.dev/badge/instructions/farol-team/gnap/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/farol-team/gnap/claude-md"><img src="https://agentmods.dev/badge/instructions/farol-team/gnap/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 564 This file is loaded in full into every session.

When invoked 564 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.

Model	Per session	Once invoked
Fable 5.1	$0.00564	$0.00564
Opus 5.5	$0.00226	$0.00226
Sonnet 5.5	$0.00113	$0.00113
Haiku 4.5	$0.00056	$0.00056

Measured 2mo ago against content hash a0854540c320, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gnap 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 2mo 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 · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 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 Repo Is

GNAP (Git-Native Agent Protocol) — a specification for coordinating AI agent teams using git as the only transport/storage layer. No server required.

Status: Draft v4, March 2026. This is a protocol spec repo, not a traditional software project.

Architecture

AgentHQ (Application Layer)  — budgets, dashboards, workflows (separate repo)
GNAP (Protocol Layer)        — 4 entities: Agent, Task, Run, Message
Git  (Transport)             — push/pull/commit = the message bus

Protocol (GNAP core): Defined in README.md. Four JSON entities live in .gnap/ — agents.json, tasks/*.json, runs/*.json, messages/*.json. Protocol version in .gnap/version.

Key Files

File	Purpose
`README.md`	GNAP protocol spec — the 4 entities, schemas, state machines, transport, onboarding
`ONBOARDING.md`	Detailed step-by-step agent onboarding guide
`CONTRIBUTING.md`	Contribution guidelines
`examples/.gnap/`	Reference data: `agents.json`, `tasks/`, `runs/`, `messages/`, `version`
`docs/gnap-overview.svg`	Visual diagram embedded in README hero section

Core Protocol Concepts

Task states: backlog → ready → in_progress → review → done (also blocked, cancelled). Reverse transitions: review → in_progress (reject), blocked → ready (unblocked).

Commit convention: <agent-id>: <action> <entity> [details] — git history IS the audit log.

Heartbeat loop: Each agent polls on heartbeat_sec interval (default 300s): pull → check status → check tasks → check messages → work → commit → push.

Conflict resolution: git merge/rebase. On conflict: pull + rebase + retry push (max 3).

Editing Guidelines

This is a spec repo. Changes to README.md change the protocol definition.
JSON schemas in the spec docs are normative — keep entity examples consistent across all docs.
The four GNAP entities (Agent, Task, Run, Message) are intentionally minimal. Resist adding new protocol-level entities.
examples/ should always be valid instances of the schemas defined in the spec.
Operational concerns (budget enforcement, stall detection, concurrency control) belong in AgentHQ, not the protocol.

Read the full file on GitHub · 48 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.

2mo ago First seen · 48 lines · 564 tokens per session scan A a0854540c320

Subscribe to this mod's changes

gnap CLAUDE.md is an instructions file published in the GitHub repository farol-team/gnap (87 stars, last pushed 7mo ago), licensed MIT. It adds 564 tokens to every session, about $0.0023 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 2026-08-30.

agent-coordination agent-orchestration agentic ai ai-agents devtools

gnap CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
gnap CLAUDE.mdfarol-team/gnap	Instructions file	87	7mo ago	MIT	A	564	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

gnap: Instructions file for Claude Code