agentmods.dev

cc-fleet CLAUDE.md

cc-fleet CLAUDE.md is an instructions file for coding agents from ethanhq/cc-fleet. It costs 2,549 tokens per session, scanned A, original, Apache-2.0.

Project instructions for cc-fleet, a Go command-line tool and Claude Code plugin that runs Claude workers through other compatible AI providers.

In plain words
What is it for?
Use it when developing, building, testing, or operating cc-fleet and its Claude Code integration.
Why use it?
It explains the different ways workers run and sets coding, testing, and attribution rules so changes fit the project.

Instructions file

not rated 210 16d ago A scan 2,549 tokens original Apache-2.0
View the source file ethanhq/cc-fleet
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/ethanhq/cc-fleet/claude-md
Clone the repo
git clone --depth 1 https://github.com/ethanhq/cc-fleet

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 cc-fleet CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/ethanhq/cc-fleet/claude-md.svg)](https://agentmods.dev/instructions/ethanhq/cc-fleet/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/ethanhq/cc-fleet/claude-md"><img src="https://agentmods.dev/badge/instructions/ethanhq/cc-fleet/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,549 This file is loaded in full into every session.
When invoked 2,549 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 $0.02549 $0.02549
Opus 5 $0.01274 $0.01274
Sonnet 5 $0.00510 $0.00510
Haiku 4.5 $0.00255 $0.00255

Measured 5d ago against content hash 4751bb17b21e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

cc-fleet 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 5d 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 · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 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 is

cc-fleet is a Go CLI (+ a Claude Code plugin) that runs third-party LLM providers (DeepSeek, GLM, Kimi, Qwen, MiniMax — anything with an Anthropic-compatible API, plus ChatGPT-subscription codex and OpenAI-protocol endpoints) as real Claude Code workers. The core trick: a provider worker is a genuine claude process whose LLM backend is swapped by launching it with --settings <provider-profile>.json (which sets ANTHROPIC_BASE_URL + an apiKeyHelper) and --model <provider-model-id>. The main session's own auth (OAuth or API key) is never touched.

There are four execution lanes — internalize this split, most of the code maps onto it:

  • Teammate — internal/spawn. A long-lived provider claude in a tmux pane; the user's main session drives it via native TeamCreate/SendMessage. Stateful, reusable. Unix-only.
  • Subagent — internal/subagent. claude -p headless, one-shot (or --background with a job file); classified Result envelope on stdout. The reserved id claude runs the leaf on the user's own Claude login (explicit-only; subagent/workflow lanes only — no profile, no keyget).
  • Workflow — internal/workflow. A detached engine running a JS script on an embedded goja VM; each agent() leaf is a provider subagent. Journaled (--resume), leaves can be held/restarted live, workflow wait is the push-notification verb.
  • Interactive — internal/run. Execs a provider-backed interactive claude in the current terminal. No tmux, no team, no locks.

The skills (skills/{subagent,team,workflow}/SKILL.md) teach the main Claude session when to pick each lane. They are not loaded when you work on this repo — product, not project config.

The full system design — fingerprint recipe, key safety, provider classes/daemon, workflow engine, lock map, platform matrix — is docs/architecture.md. Read it before structural changes; this file keeps only what an editing agent needs constantly. The user-facing references are docs/cli.md (zh mirror docs/cli.zh.md) and docs/workflows.md — update them when you change a command, flag, envelope, or the workflow script API.

Read the full file on GitHub · 159 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. 5d ago First seen · 159 lines · 2,549 tokens per session scan A 4751bb17b21e

Subscribe to this mod's changes

cc-fleet CLAUDE.md is an instructions file published in the GitHub repository ethanhq/cc-fleet (210 stars, last pushed 16d ago), licensed Apache-2.0. It adds 2,549 tokens to every session, about $0.0127 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.

Building agentsGoLanguagesaiai-agentsanthropicanthropic-claudebash-cliclaude
Related

Other instructions, from other repositories

dingtalk-workspace-cli AGENTS.md

AGENTS.md instructions for DingTalk-Real-AI/dingtalk-workspace-cli, covering repository agent guide, build and test, command framework declaration, flag / help / schema homology and agent schema contract.

DingTalk-Real-AI/dingtalk-workspace-cli · 7,929 tokens

azure-sdk-for-go go-code.instructions.md

Instructions for Azure/azure-sdk-for-go: All code should follow the guidelines from the Azure Go SDK Guidelines. This document is a summary of the most important guidelines to follow when contributing to the Azure Go SDK.

Azure/azure-sdk-for-go · 755 tokens

ai-agents push-lock.instructions.md

Instructions for rjmurillo/ai-agents, covering one push lock path, must, must not, historical measurements and commit guard.

rjmurillo/ai-agents · 2,104 tokens

coral CLAUDE.md

Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).

cdknorow/coral · 1,898 tokens

ai-agents security.instructions.md

Instructions for rjmurillo/ai-agents, covering security file rules, must, should, must not and references.

rjmurillo/ai-agents · 832 tokens

oastools GEMINI.md

Instructions for erraggy/oastools, covering gemini.md, project overview, building and running, key commands and development conventions.

erraggy/oastools · 1,091 tokens