adjutant

MCP tools for communicating with the Adjutant dashboard and other agents. Use when agents need to send messages, report status, manage beads, or query system state. Auto-connects to the Adjutant MCP server.

Spawn a full squad of worktree-isolated Claude Code agents to execute a spec or epic. Includes staff engineers, QA sentinel, optional Product/UIUX reviewer, and optional code reviewer. The invoking agent stays in coordinator mode. Use when the user says "spin up a team", "squad execute", "execute this epic with a team", "spawn engineers for this", "staff up", "build a team for this", "run this with agents", "deploy a squad", "get engineers on this", "execute with a crew", or wants parallel multi-agent execution of planned work. Also matches "launch team", "start squad", "kick off execution", and any request involving multiple agents working on an epic or spec simultaneously.

Create structured epic hierarchies for new features, major refactorings, and large tasks. Generates speckit-style artifacts (spec.md, plan.md, tasks.md, beads-import.md) in specs/ and creates real beads via `bd` CLI with wired dependencies. Use when the user says things like "Create a new epic for ...", "I want to do a major refactoring ...", "Time for a new plan", "Let's add a new feature", "New epic", or any request to plan and track a significant body of work.

Spawn a full squad of worktree-isolated Claude Code agents to execute a spec or epic. Includes staff engineers, QA sentinel, optional Product/UIUX reviewer, and optional code reviewer. The invoking agent stays in coordinator mode. Use when the user says "spin up a team", "squad execute", "execute this epic with a team", "spawn engineers for this", "staff up", "build a team for this", "run this with agents", "deploy a squad", "get engineers on this", "execute with a crew", or wants parallel multi-agent execution of planned work. Also matches "launch team", "start squad", "kick off execution", and any request involving multiple agents working on an epic or spec simultaneously.

Automated code review analyzing diffs for test coverage, code quality, architecture conformance, and security. Produces structured findings and optionally creates beads for issues found. Use when user says "review code", "code review", "review my changes", "check this branch", "/code-review", or wants automated quality analysis before merging.

Discuss and review an improvement proposal with the user. Analyzes strengths, weaknesses, feasibility, and cost estimate. Records the review as a persistent comment on the proposal, and optionally creates a revision if concrete improvements are identified. Use when the user says "discuss proposal", "review proposal", "what do you think about this proposal", or references a proposal ID for discussion and refinement rather than execution.

Set up automatic TestFlight deployment for iOS projects via Fastlane and GitHub Actions. Auto-detects project structure, generates CI/CD configuration files, and provides a step-by-step manual setup guide. Use when the user says "set up TestFlight", "configure CI/CD for iOS", "automate TestFlight builds", or wants to add TestFlight deployment to any iOS project.

Execute an accepted proposal by fetching it from the backend and orchestrating epic creation via the epic-planner skill. Use when the user says "execute proposal", "implement proposal", "start working on proposal X", or wants to turn a proposal into an actionable epic hierarchy with beads.

Broadcast a message into every active agent's Claude Code tmux session as a submitted prompt. Also sends persistent MCP messages as backup. Use when you need to inject a standing order, instruction, or announcement into all running agents at once.

Send a direct message to a specific agent via MCP messaging and tmux injection. Guarantees delivery by injecting the message as a submitted prompt into the agent's tmux session AND sending a persistent MCP message. Use when you need to message a specific agent and get a response, rather than broadcasting to everyone.