mirror of https://github.com/affaan-m/everything-claude-code.git synced 2026-03-30 21:53:28 +08:00

Files

Avdhesh Singh Chouhan ac53fbcd0e Add Claude DevFleet multi-agent orchestration skill (#505 )

* Add Claude DevFleet multi-agent orchestration skill

Adds a skill for Claude DevFleet — a multi-agent coding platform that dispatches
Claude Code agents to work on missions in parallel, each in an isolated git worktree.

The skill teaches Claude Code how to use DevFleet's 11 MCP tools to plan projects,
dispatch agents, monitor progress, and read structured reports.

Setup: claude mcp add devfleet --transport sse http://localhost:18801/mcp/sse
Repo: https://github.com/LEC-AI/claude-devfleet

* Add DevFleet MCP config and /devfleet command

- Add devfleet entry to mcp-configs/mcp-servers.json for discovery
- Add /devfleet slash command for multi-agent orchestration workflow

* Add orchestration flow diagrams to skill and command

- Add visual flow to SKILL.md showing plan → dispatch → auto-chain → report
- Add flow to /devfleet command showing the trigger sequence

* Fix review feedback: frontmatter, workflow docs, HTTP transport

- Add YAML description frontmatter to commands/devfleet.md
- Fix manual workflow in SKILL.md to capture project_id from create_project
- Change mcp-servers.json from deprecated SSE to Streamable HTTP transport

* Address all review comments

* Add monitoring/reporting steps to full auto pattern

Addresses review feedback: the full auto example now includes polling
for completion and retrieving reports, matching the other patterns.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Update skills/claude-devfleet/SKILL.md

Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>

* Update skills/claude-devfleet/SKILL.md

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Update commands/devfleet.md

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Fix review feedback

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Avdhesh Singh Chouhan <avdhesh.acro@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

2026-03-16 13:35:50 -07:00

3.7 KiB

Raw Blame History

description

description
Orchestrate parallel Claude Code agents via Claude DevFleet — plan projects from natural language, dispatch agents in isolated worktrees, monitor progress, and read structured reports.

DevFleet — Multi-Agent Orchestration

Orchestrate parallel Claude Code agents via Claude DevFleet. Each agent runs in an isolated git worktree with full tooling.

Requires the DevFleet MCP server: claude mcp add devfleet --transport http http://localhost:18801/mcp

Flow

User describes project
  → plan_project(prompt) → mission DAG with dependencies
  → Show plan, get approval
  → dispatch_mission(M1) → Agent spawns in worktree
  → M1 completes → auto-merge → M2 auto-dispatches (depends_on M1)
  → M2 completes → auto-merge
  → get_report(M2) → files_changed, what_done, errors, next_steps
  → Report summary to user

Workflow

Plan the project from the user's description:

mcp__devfleet__plan_project(prompt="<user's description>")

This returns a project with chained missions. Show the user:

Project name and ID
Each mission: title, type, dependencies
The dependency DAG (which missions block which)

Wait for user approval before dispatching. Show the plan clearly.
Dispatch the first mission (the one with empty depends_on):

mcp__devfleet__dispatch_mission(mission_id="<first_mission_id>")

The remaining missions auto-dispatch as their dependencies complete (because plan_project creates them with auto_dispatch=true). When manually creating missions with create_mission, you must explicitly set auto_dispatch=true for this behavior.

Monitor progress — check what's running:

mcp__devfleet__get_dashboard()

Or check a specific mission:

mcp__devfleet__get_mission_status(mission_id="<id>")

Prefer polling with get_mission_status over wait_for_mission for long-running missions, so the user sees progress updates.

Read the report for each completed mission:

mcp__devfleet__get_report(mission_id="<mission_id>")

Call this for every mission that reached a terminal state. Reports contain: files_changed, what_done, what_open, what_tested, what_untested, next_steps, errors_encountered.

All Available Tools

Tool	Purpose
`plan_project(prompt)`	AI breaks description into chained missions with `auto_dispatch=true`
`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.
`dispatch_mission(mission_id, model?, max_turns?)`	Start an agent
`cancel_mission(mission_id)`	Stop a running agent
`wait_for_mission(mission_id, timeout_seconds?)`	Block until done (prefer polling for long tasks)
`get_mission_status(mission_id)`	Check progress without blocking
`get_report(mission_id)`	Read structured report
`get_dashboard()`	System overview
`list_projects()`	Browse projects
`list_missions(project_id, status?)`	List missions

Guidelines

Always confirm the plan before dispatching unless the user said "go ahead"
Include mission titles and IDs when reporting status
If a mission fails, read its report to understand errors before retrying
Agent concurrency is configurable (default: 3). Excess missions queue and auto-dispatch as slots free up. Check get_dashboard() for slot availability.
Dependencies form a DAG — never create circular dependencies
Each agent auto-merges its worktree on completion. If a merge conflict occurs, the changes remain on the worktree branch for manual resolution.

3.7 KiB Raw Blame History