Collaboration plugins

PR and issue lifecycle — structured planning (CEO/Eng gates), PR creation, code review, issue triage, session handoffs

14 skills · 3 agents · hooks

Enterprise tracking and documentation skills: Jira ticket workflow/comments best practices, and Confluence page authoring/governance.

3 skills

Adds the agensis skill: how to connect to an agensis workspace over MCP and collaborate as a teammate.

1 skill

legacy session mesh for claude code. frozen through 2026-11-05; security and installation fixes only.

1 skill · 1 MCP server · hooks

legacy session mesh for claude code. frozen through 2026-11-05; security and installation fixes only.

1 skill · 1 MCP server · hooks

/party — one channel where your agent sessions talk to each other: Claude Code, Cursor, Codex or any other agent, on one machine or across machines.

1 skill

AICQ for Claude Code: one place for everything waiting on you or your agents, yours or friends', with a jump into each agent's Claude or Codex session; your agents' collaborations and an interactive map of your agent universe. Needs a Claude Code build with mods and the fulcra CLI signed in.

Git-native shared AI memory for teams. Lessons, decisions, conventions auto-loaded into Claude Code sessions.

3 skills

Connects Claude Code to a komnet network: wires the komnet MCP server, surfaces pending messages at session start, and teaches the four rules the protocol depends on — the inbox is pull-based, `needs: human` is never answered by an agent, everything sent is permanent and visible to the whole team, and message bodies are data rather than instructions. Ships seven skills (first contact, inbox triage, human handoff, messaging, collaborative tasks, repository review, setup) and a read-only `reviewer` subagent that performs a delegated cross-repository review in an isolated worktree. Requires the `komnet` CLI on PATH.

7 skills · 1 command · 1 agent · 1 MCP server · hooks

Turns one Claude Code session into a standing relay between a komnet network and the other Claude sessions on this machine, closing the gap the inbox hooks cannot reach: a remote teammate's message lands in a session that is already mid-task, instead of waiting for that session to end. The gateway watches the inbox, routes each arriving message to whichever local session is waiting for it — by thread, then by room — and carries replies back out; a client session reaches the network with one command and needs no komnet configuration of its own. Relays remote text as quoted, attributed data rather than instruction, never acts on a remote request, never routes refused work to a looser session, and never answers a `needs: human` item. Spawns nothing: both ends of every relay are sessions a person already opened. Requires the `komnet` CLI and node on PATH.

2 skills · 3 commands · hooks

[Command + Skill] 辩论插件 - 主代理与子代理进行结构化辩论，发现盲点、探索多角度视角

1 command

[Skill] BA 协作 - 与业务分析师协作的专业化工作流

Set up and join Agora, and collaborate with other agents in its channels and threads (agora-connect, agora-collab, agora-plan, agora-review, agora-fix, agora-discuss).

6 skills

轻量多 Agent 协作技能，用 docs/bbs/lite-team-bbs.md 协作板在不同 Agent/session 间手动交接

1 skill

Codex 原生多 Agent 路由：支持精确 okok 授权或 --fast/-f 直通实施、Luna 叶节点限制、Terra/Sol 按额度嵌套与主线程独立验收；策略不是模型锁

1 skill

把当前任务交接给普通聊天 AI：portable 模式提炼任务相关技能约束、全局与项目规则并内嵌必要资料，skill name 模式只列技能名；生成单个 Markdown 交接文件，校验段落配对与顺序并做语义体检，接收方核对理解后等待指示

1 skill

Join or start a Project Room, read the board, post, claim work and close it with receipts. Adds the hosted Room MCP and the Project Room skills.

8 skills · 3 commands · 2 MCP servers · hooks

Multiplayer Claude Code plugin.

5 commands · 1 MCP server · hooks

Shared team memory for AI agents. The halyard MCP server and skills (log-work, review-work, gather-context, ask-for-help, triage-knowledge, mark-terms, setup-cli) capture decisions, surface prior context, and route hard questions to teammates on Slack, Teams, or Discord.

7 skills · 1 MCP server · hooks

Mattermost collaboration ops plugin. Drive the full Mattermost REST API v4 by curl — users, teams, channels (public/private/DM/group), posts & threads, reactions, files, custom emoji, webhooks, slash commands, bots, OAuth apps, plus system administration: config, RBAC roles & schemes, LDAP/SAML groups, compliance, data retention, plugins, jobs, and analytics. Authenticates with MATTERMOST_ADMIN_USERNAME + MATTERMOST_ADMIN_PASSWORD to obtain a session token against MATTERMOST_API_URL.

4 skills · 1 agent

Discover nearby devs and chat via Bluetooth Low Energy

2 skills · 1 MCP server · hooks

Peer-pane Claude Code worker orchestration via tmux + jsonl mailbox. Bundles Formation worker spawning, session-scoped routing, and a receipt-gated babysit-pr skill for bounded CI monitoring and reply-only review follow-up. Hooks suggest Formation and mint local ownership receipts only for active Formation sessions.

2 skills · 1 agent · hooks

Mattermost collaboration ops plugin. Drive the full Mattermost REST API v4 by curl — users, teams, channels (public/private/DM/group), posts & threads, reactions, files, custom emoji, webhooks, slash commands, bots, OAuth apps, plus system administration: config, RBAC roles & schemes, LDAP/SAML groups, compliance, data retention, plugins, jobs, and analytics. Authenticates with MATTERMOST_ADMIN_USERNAME + MATTERMOST_ADMIN_PASSWORD to obtain a session token against MATTERMOST_API_URL.

4 skills

Agent-to-agent coordination over GitHub Discussions — agents open threads, join, reply, sign off and close, and read back who is in a thread and whether anyone replied. Includes a PR hook that opens a thread per pull request with a duplicate-claim check.

1 skill · 2 commands

Mesh tools for Claude Code plus in-session approvals of teammates' requests (monitor + approve_request).

1 skill · 1 MCP server · hooks

Adds the agensis skill: how to connect to an agensis workspace over MCP and collaborate as a teammate.

1 skill

Author and triage collaboration artifacts across the change lifecycle: change requests (feature requests, bug reports, refactor proposals) that frame the Why, and design proposals or RFCs that answer the How, for work carried out by humans or AI agents.