By xiaolai
Bridge Claude Code, Codex CLI, and Gemini CLI into a unified workflow with a single AGENTS.md, shared skills, mirrored hooks and MCP servers, and bidirectional delegation — enabling multi-round audit-fix-verify cycles, agent creation, code review, and setup health management across all three AI coding tools from one plugin.
Create a new cc-suite advisor agent — a project-scoped value-over-rules persona registered as an MCP server in both .mcp.json and .codex/config.toml. Optional preset arg copies a curated template.
Agent auditor — audit Claude Code agent definitions for triggering accuracy, system prompt quality, tool appropriateness, and example coverage
Command auditor — audit Claude Code slash commands for schema, workflow clarity, tool selection, error handling, and output specification
Audit→fix→verify loop — finds issues, fixes them, verifies fixes, repeats until clean or you stop
Repo-wide natural language programming auditor — discover and audit all NL artifacts (prompts, skills, agents, commands, rules, hooks, plugins, specs, plans) in any repository
Use when creating, editing, or reviewing a cc-suite advisor agent (a value-over-rules persona under `.cc-suite/agents/`). Covers system-prompt phrasing, model choice, tool restrictions, working-dir scoping, budget/turn limits, and the file format. Use proactively whenever the user asks to "add an agent", "make an advisor", "write a reviewer", or edits anything under `.cc-suite/agents/`.
Full audit→fix→verify cycle: Claude audits, Codex fixes, Claude verifies. Repeats up to 3 rounds until all issues are resolved or the user stops. Claude does all code reading and judgment; Codex does all file editing.
Ask Claude Code to audit a file or set of files and return structured findings. Claude reads the code with fresh eyes and independent judgment — Codex does not self-review. Supports mini (5-dimension) and full (9-dimension) depth.
Canonical reference for Claude Code plugin artifact schemas, hook events, frontmatter fields, and naming conventions. Used to inject domain knowledge into Codex audit prompts. Run /cc-suite:refresh-knowledge to update from latest docs.
Send a bug or failing test to Claude Code for root-cause analysis and fix. Use when you've hit an error you can't trace, a test is failing for unclear reasons, or a behavior is wrong and the cause is deep in the codebase.
Runs pre-commands
Contains inline bash commands via ! syntax
Bash prerequisite issue
Uses bash pre-commands but Bash not in allowed tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
One Claude Code plugin to synchronize Claude Code, Codex CLI, and Gemini CLI on the same project — and let them delegate work to each other.
Each tool reads from its own files. CLAUDE.md, AGENTS.md, GEMINI.md sit next to each other and drift. Skills written for Claude aren't visible to Codex. Hooks must be maintained in two places. MCP servers declared in .mcp.json are invisible to Codex's .codex/config.toml. And there's no built-in way to say "ask Codex for an adversarial review" from Claude, or "ask Claude to plan this" from Codex.
cc-suite fixes all of this with a single plugin install:
| Feature | What it does |
|---|---|
| Single-source instructions | AGENTS.md is the source of truth. CLAUDE.md and GEMINI.md become thin @AGENTS.md imports. |
| Shared skills | .agents/skills/ is symlinked to .claude/skills/. Every Claude skill is automatically visible to Codex and Gemini. |
| Mirrored hooks | Syncs the five shared hook events from .claude/settings.json into .codex/hooks.json. Same scripts, both tools. |
| MCP parity | Mirrors .mcp.json project servers into .codex/config.toml so Codex sees the same servers. |
| Claude → Codex delegation | Registers the codex-cli MCP server in .mcp.json. Claude can call /audit, /implement, /bug-analyze, and more directly. Full Codex job tracking, background mode, and stop-time review gate included. |
| Codex → Claude delegation | Registers the claude-code MCP server (claude-octopus) in .codex/config.toml. Codex skills $claude-review, $claude-plan, $claude-implement, $claude-debug delegate to Claude and return structured results. |
| Codex reads Claude session history | The same claude-code MCP server exposes claude_code_sessions (list this repo's Claude Code sessions, or all projects with all_projects: true) and claude_code_transcript (read a session by id). Codex can enumerate and read past Claude conversations for the repo. |
Two install paths — both reach the same code. Pick one:
Via Anthropic's official community marketplace (curated; updates lag the maintainer's marketplace by up to ~24h):
claude plugin marketplace add anthropics/claude-plugins-community
claude plugin install cc-suite@claude-community --scope project
Via the xiaolai marketplace (latest version lands here first):
claude plugin marketplace add xiaolai/claude-plugin-marketplace
claude plugin install cc-suite@xiaolai --scope project
npx -y at runtime, no pre-install needed. Uses the same credential store as Claude CLI (~/.claude/.credentials.json)./cc-suite:init
Walks through the full setup: AGENTS.md bridge, MCP server registration, and project audit config. All steps are idempotent — safe to re-run.
After init, edit AGENTS.md — all three tools pick up changes automatically.
| Command | What it does |
|---|---|
/cc-suite:init | Full setup: bridge init, Codex MCP, Claude MCP, project config. Idempotent. |
/cc-suite:bridge-skills | Create .agents/skills → .claude/skills symlink. |
/cc-suite:bridge-hooks | Mirror .claude/settings.json hooks → .codex/hooks.json. |
/cc-suite:status | Bridge health, MCP registration, and Codex runtime checks. |
/cc-suite:unbridge | Tear down bridge artifacts, restoring CLAUDE.md from AGENTS.md. |
All commands delegate to Codex via the codex-cli MCP server. Codex runs in a sandboxed subprocess; Claude tracks jobs, handles background mode, and can continue threads.
npx claudepluginhub xiaolai/claude-plugin-marketplace --plugin cc-suiteNatural-Language Programming Manager — score, check, fix, and test NL artifacts across Claude Code, Codex CLI, and Antigravity. Tier-aware scoring with per-tool overlays.
A 260-token system prompt that overrides three structural presumptions every RLHF-trained LLM inherits from training: that you want confirmation, that old scarcity still applies, that best practices are ceilings.
English language coach for non-native speakers — auto-corrects prompts, translates non-English, refines with :: prefix, tracks improvement over time
Auto-updated multi-skill reference for the whole Anthropic doc ecosystem. 8 skills covering claude-code, claude-agent-sdk, anthropic-api, anthropic-platform-features, claude-connectors, claude-cowork, mcp-spec, and anthropic-pulse (news + research digests). Pipeline refreshes daily.
Initialize a multi-agent workspace with shared configuration for Claude Code, Codex CLI, and Gemini CLI
Hub plugin for cc-multi-cli-plugin: contains the companion runtime, subagents, setup wizard, and customization skills.
Unified capability management center for Skills, Agents, and Commands.
Harness for Claude Code — skills, /harness:* slash commands, persona subagents, lifecycle hooks, and MCP tools without per-repo `harness setup`. Sibling plugins exist for Cursor, Gemini CLI, and Codex.
Complete collection of battle-tested Claude Code configs from an Anthropic hackathon winner - agents, skills, hooks, and rules evolved over 10+ months of intensive daily use
Sub-agent runner — runs agent definitions on Codex, Claude Code, Cursor CLI, or Gemini CLI from any host AI tool.
Bridge Claude Code and Codex with a shared daemon, push channel delivery, and bidirectional reply tooling.