Menü
Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
顽皮制造 — Fuse multiple external skill repos/sources into an existing skill to create a unified, more capable version. Use when the user says 'merge these skills', 'combine X into Y', 'absorb the best parts of A/B/C into Z', 'upgrade this skill with features from those repos', or provides multiple GitHub URLs and asks to integrate them into a single skill. Also triggers on 'audit these skills and see if they can enhance ours'.
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch.
Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, or when you need to organize work across multiple parallel streams.
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Drives development with tests. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality.
| name | claude-devfleet |
| description | Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports. |
| metadata | {"origin":"community"} |
Use this skill when you need to dispatch multiple Claude Code agents to work on coding tasks in parallel. Each agent runs in an isolated git worktree with full tooling.
The DevFleet server is a separate project, not bundled with HCP. Install and run it from its repository first: https://github.com/LEC-AI/claude-devfleet
Then connect the running instance via MCP:
claude mcp add devfleet --transport http http://localhost:18801/mcp
Before first use, verify the process listening on port 18801 is the DevFleet binary you installed (see SECURITY.md on localhost MCP servers).
User → "Build a REST API with auth and tests"
↓
plan_project(prompt) → project_id + mission DAG
↓
Show plan to user → get approval
↓
dispatch_mission(M1) → Agent 1 spawns in worktree
↓
M1 completes → auto-merge → auto-dispatch M2 (depends_on M1)
↓
M2 completes → auto-merge
↓
get_report(M2) → files_changed, what_done, errors, next_steps
↓
Report back to user
| Tool | Purpose |
|---|---|
plan_project(prompt) | AI breaks a description into a project with chained missions |
create_project(name, path?, description?) | Create a project manually, returns project_id |
create_mission(project_id, title, prompt, depends_on?, auto_dispatch?) | Add a mission. depends_on is a list of mission ID strings (e.g., ["abc-123"]). Set auto_dispatch=true to auto-start when deps are met. |
dispatch_mission(mission_id, model?, max_turns?) | Start an agent on a mission |
cancel_mission(mission_id) | Stop a running agent |
wait_for_mission(mission_id, timeout_seconds?) | Block until a mission completes (see note below) |
get_mission_status(mission_id) | Check mission progress without blocking |
get_report(mission_id) | Read structured report (files changed, tested, errors, next steps) |
get_dashboard() | System overview: running agents, stats, recent activity |
list_projects() | Browse all projects |
list_missions(project_id, status?) | List missions in a project |
Note on
wait_for_mission: This blocks the conversation for up totimeout_seconds(default 600). For long-running missions, prefer polling withget_mission_statusevery 30–60 seconds instead, so the user sees progress updates.
plan_project(prompt="...") → returns project_id + list of missions with depends_on chains and auto_dispatch=true.dispatch_mission(mission_id=<first_mission_id>) on the root mission (empty depends_on). Remaining missions auto-dispatch as their dependencies complete (because plan_project sets auto_dispatch=true on them).get_mission_status(mission_id=...) or get_dashboard() to check progress.get_report(mission_id=...) when missions complete. Share highlights with the user.DevFleet runs up to 3 concurrent agents by default (configurable via DEVFLEET_MAX_AGENTS). When all slots are full, missions with auto_dispatch=true queue in the mission watcher and dispatch automatically as slots free up. Check get_dashboard() for current slot usage.
plan_project(prompt="...") → shows plan with missions and dependencies.depends_on).auto_dispatch=true).get_mission_status or get_dashboard() periodically until all missions reach a terminal state (completed, failed, or cancelled).get_report(mission_id=...) for each terminal mission — summarize successes and call out failures with errors and next steps.create_project(name="My Project") → returns project_id.create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true) for the first (root) mission → capture root_mission_id.
create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true, depends_on=["<root_mission_id>"]) for each subsequent task.dispatch_mission(mission_id=...) on the first mission to start the chain.get_report(mission_id=...) when done.create_project(name="...") → get project_id.create_mission(project_id=project_id, title="Implement feature", prompt="...") → get impl_mission_id.dispatch_mission(mission_id=impl_mission_id), then poll with get_mission_status until complete.get_report(mission_id=impl_mission_id) to review results.create_mission(project_id=project_id, title="Review", prompt="...", depends_on=[impl_mission_id], auto_dispatch=true) — auto-starts since the dependency is already met.get_dashboard() for agent slot availability before bulk dispatching.auto_dispatch=true if you want them to trigger automatically when dependencies complete. Without this flag, missions stay in draft status.