ccteam
01Settings file Claude Code
Agent settings declaring 14 allowed tools.
Settings file Claude Code
Agent settings declaring 14 allowed tools.
Instructions file CodexOpenCode
Repository instructions for coding agents working on ccteam, a service that connects chat systems with multiple coding-agent sessions.
Instructions file
Instructions for firstintent/ccteam, a project described as: ccteam turns the coding agents you already run (Claude Code, Codex, Grok, DeepSeek Harness, Kimi, Pi) into one team — any session can spawn, dispatch, and collect work from any vendor on any machine, while you steer it all from Telegram, Lark, or a browser…
Plugin Claude Code
Protocol-level bridge that lets Claude Code be called by any Agent2Agent (A2A) client and call out to other AI coding agents (Codex, OpenClaw, Hermes) through a uniform adapter interface.
Instructions file
Instructions for firstintent/a2a-bridge, covering claude.md — a2a-bridge, project, language policy — strict, stack and architecture constraints — enforced.
Plugin Claude Code
Bridge Claude Code with other AI coding agents (Codex, OpenClaw, Hermes, ...) through a shared daemon, push channel delivery, and bidirectional reply tooling.
MCP server Claude CodeCodexCursor +2
MCP server "a2a-bridge" as configured in firstintent/a2a-bridge. Launched with bun run ${CLAUDE_PLUGIN_ROOT}/server/bridge-server.js. Needs 1 environment variable to run.
Command
Create or update the A2aBridge project config files in the current workspace.
Hook
Runs when a session starts, executing health-check.sh via bash. From firstintent/a2a-bridge.
Skill Claude CodeCodex
Delegate a long-tail investigation (log dig, audit, transcript analysis) to a peer agent and take back only a summary. Use when the raw output would crowd out 1000+ tokens of the primary session that do not need to live there.
Skill Claude CodeCodex
Spawn N peer agents on genuinely independent subtasks, wait for every result, then merge. Use when subtasks do not read each other's outputs and the wall-clock saving is worth N× the token cost.
Skill Claude CodeCodex
Delegate a verification check to a peer agent and consume a structured pass/fail/needs-info verdict instead of free-form text. Use when you want a second agent to check work against explicit criteria without rewriting it.