Borrowing it
Nothing to install: this file belongs to xiaolai/cc-suite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/xiaolai/cc-suite/main/AGENTS.mdgit clone --depth 1 https://github.com/xiaolai/cc-suiteWrote 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/xiaolai/cc-suite/agents-md)<a href="https://agentmods.dev/instructions/xiaolai/cc-suite/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/cc-suite/agents-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.
<a href="https://agentmods.dev/instructions/xiaolai/cc-suite/agents-md"><img src="https://agentmods.dev/badge/instructions/xiaolai/cc-suite/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03306 | $0.03306 |
| Opus 5.5 | $0.01322 | $0.01322 |
| Sonnet 5.5 | $0.00661 | $0.00661 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade B, and why
cc-suite scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- `~/.gemini/config/` — Antigravity CLI's global MCP/plugin configuration How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Instructions
cc-suite
Guidelines
- Bump the version in
.claude-plugin/plugin.jsonfor every release (patch/minor/major per semver).package.jsonmust carry the same version — a test enforces it. mainalways equals the newest tag. Every commit pushed tomainis a release: bump, commit,git tag -a vX.Y.Z, push both. Do not land a change and leave it untagged "until the next real release" — that includes docs-only anddev-docs/changes, which take a patch bump. Ifgit describe --exact-match HEADfails, the release is unfinished.- New commands go in
commands/; new skills go inskills/cc-suite/<name>/SKILL.md. - Setup and maintenance commands the user types (
bridge-*,sync-mcp,update,unbridge,repair, the preflights,refresh-knowledge,diagnose,migrate-google,remove-agent) setdisable-model-invocation: true, which keeps them out of the always-on skill listing and out of Claude's reach. So no script output, hook text, command or skill may tell Claude to run one: address the user ("ask the user to run/cc-suite:repair", "type/cc-suite:repair"), or, where a flow must chain into one, read${CLAUDE_PLUGIN_ROOT}/commands/<name>.mdand follow it.tests/commands.test.mjsenforces both. - All scripts in
scripts/must be idempotent — running twice must produce the same result. - Write new project-level instructions into
AGENTS.mdonly; never editCLAUDE.mdor legacyGEMINI.mddirectly.
Prerequisites
- Claude Code (≥ 2.0) — primary host for all commands and skills
- Codex CLI (optional) — required for the Claude→Codex delegation lane (
codex exec) andbridge_hooks.py - Python 3 — required by
scripts/bridge_hooks.py, MCP projections, and migration helpers - Antigravity CLI (
agy) (optional) — required for the Google backend,/cc-suite:agy-preflight, and headless agy delegation - Grok Build (
grok, xAI) (optional) — required for the Claude→Grok ACP delegation lane (/cc-suite:grok) and/cc-suite:grok-preflight - Qwen Code (
qwen, ≥ 0.21.0) (optional) — required for the bounded, read-only/cc-suite:qwen-reviewlane and/cc-suite:qwen-preflight - Bash — required by all
scripts/*.shfiles claude-octopus(npm, pinned) — the MCP server cc-suite registers in.codex/config.tomlso Codex can delegate to Claude. cc-suite does not install it explicitly;mcp_claude.shwrites anpx -y claude-octopus@<pin>invocation and npm fetches it on first Codex start. The pin lives inscripts/lib/claude-octopus-pin.txt— single source of truth, read bymcp_claude.sh, the integration suite, and the boot-handshake test.
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.
- 1mo ago Changed · +1 lines · +186 tokens per session b1ff975999c6
- 1mo ago Changed · +4 lines · +270 tokens per session 9947b2e83cfa
- 2mo ago First seen · 126 lines · 2,850 tokens per session scan B c51b09f45018
cc-suite is an instructions file published in the GitHub repository xiaolai/cc-suite (57 stars, last pushed 20d ago), licensed ISC. It adds 3,306 tokens to every session, about $0.0132 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
cc-suite compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cc-suitexiaolai/cc-suite | Instructions file | 57 | 20d ago | ISC | B | 3,306 | Claude Code, Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |