caura-cross-fleet-gov: Instructions file for Claude Code

CLAUDE.md

caura-cross-fleet-gov CLAUDE.md is an instructions file for Claude Code from caura-ai/caura-cross-fleet-gov. It costs 1,402 tokens per session, scanned A, original, MIT.

Repository instructions for working on a multi-agent governance demo using MemClaw, a memory store with separate data partitions for different groups of agents. They cover the project, prerequisites, setup, and gateway commands.

In plain words
What is it for?
Use them when developing or running the Caura cross-fleet governance example, including its local MemClaw service, OpenClaw agents, Docker setup, and model gateway.
Why use it?
They explain how to run the demo and preserve boundaries between sales, legal, and admin data instead of relying only on prompt instructions.

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 caura-ai/caura-cross-fleet-gov's own configuration. It tells Claude Code how to work on caura-cross-fleet-gov 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 caura-cross-fleet-gov configures →

Reuse

Borrowing it

Nothing to install: this file belongs to caura-ai/caura-cross-fleet-gov. 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/caura-ai/caura-cross-fleet-gov/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/caura-ai/caura-cross-fleet-gov

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 caura-cross-fleet-gov CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/caura-ai/caura-cross-fleet-gov/claude-md/github.svg)](https://agentmods.dev/instructions/caura-ai/caura-cross-fleet-gov/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/caura-ai/caura-cross-fleet-gov/claude-md"><img src="https://agentmods.dev/badge/instructions/caura-ai/caura-cross-fleet-gov/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 caura-cross-fleet-gov CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/caura-ai/caura-cross-fleet-gov/claude-md"><img src="https://agentmods.dev/badge/instructions/caura-ai/caura-cross-fleet-gov/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,402 This file is loaded in full into every session.
When invoked 1,402 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 $0.01402 $0.01402
Opus 5 $0.00701 $0.00701
Sonnet 5 $0.00280 $0.00280
Haiku 4.5 $0.00140 $0.00140

Measured 11d ago against content hash ae11798e8940, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

caura-cross-fleet-gov 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 11d 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 · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 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

A multi-agent governance demo showing MemClaw enforcing fleet-scoped memory boundaries across three OpenClaw agents. Three agents (sales, legal, admin) share one MemClaw tenant with three isolated fleet partitions. Fleet boundaries are query predicates at the storage layer - not prompt instructions - so data outside declared fleet_ids is never loaded, scored, or returned. For hard cross-domain isolation (cannot be bypassed at the prompt level), use separate tenants per domain or the managed service.

Prerequisites

  • Node.js 24+
  • Docker (to run MemClaw locally)
  • OpenClaw CLI: npm install -g openclaw@latest
  • LLM gateway API key for DeepSeek V3 (or any OpenAI-compatible model)

This repo defaults to a local MemClaw instance - no cloud account or API key required for MemClaw. Fleet partitions (fleet-org-shared, fleet-sales, fleet-legal) are created automatically on first write.

Environment Setup

# 1. Start MemClaw locally (clone the repo and use docker compose)
git clone https://github.com/caura-ai/caura-memclaw ~/caura-memclaw
cp ~/caura-memclaw/.env.example ~/caura-memclaw/.env
docker compose -f ~/caura-memclaw/docker-compose.yml up -d

# 2. Copy and configure env (only LLM_GATEWAY_API_KEY is required)
copy .env.example .env
# Fill in: LLM_GATEWAY_API_KEY (your LLM gateway key; MEMCLAW_API_KEY can stay blank for local deploy)

The .env variables are consumed by .openclaw/openclaw.json via ${VAR_NAME} interpolation. Default MEMCLAW_API_URL=http://localhost:8000 works out of the box; MEMCLAW_TENANT_ID is auto-resolved from the API key if left blank.

Gateway Commands

# First-time setup
openclaw onboard --install-daemon
# For any OpenAI-compatible endpoint:
openclaw onboard --non-interactive --accept-risk `
  --custom-api-key "your-llm-gateway-key" `
  --custom-base-url "https://your-gateway.example.com/v1" `
  --custom-model-id "your-model-id"
openclaw doctor

# Normal operation
openclaw gateway restart
openclaw agents list --bindings      # verify all three agents registered
openclaw dashboard                   # opens http://127.0.0.1:18789

Read the full file on GitHub · 111 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. 11d ago First seen · 111 lines · 1,402 tokens per session scan A ae11798e8940

Subscribe to this mod's changes

caura-cross-fleet-gov CLAUDE.md is an instructions file published in the GitHub repository caura-ai/caura-cross-fleet-gov (75 stars, last pushed 18d ago), licensed MIT. It adds 1,402 tokens to every session, about $0.0070 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.

Related

Other instructions, from other repositories

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 · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

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 · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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 · 4,469 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, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens