New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Claude Devfleet

by affaan-m in affaan-m/ECC

通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。

MITAuto-check passed

Install Claude Devfleet

skills CLI
$ npx skills add affaan-m/ECC --skill claude-devfleet -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install affaan-m/ECC claude-devfleet --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/zh-CN/skills/claude-devfleet .claude/skills/claude-devfleet && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
claude-devfleet
GitHub stars
276k
Used in
1 other repo
Token cost
~909 tokens
SKILL.md length
214 words
Files
1
Skills in repo
673
Repo updated
First seen
Licence
MIT

At a glance

通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。

  • Works in 5 steps: 规划：调用 plan_project(prompt="...") → 返回… → 展示计划：向用户呈现任务标题、类型和依赖链。 → 调度：对根任务（depends_on 为空）调用… → …
  • SKILL.md covers 使用时机, 工作原理, 示例 and 指南
  • Calls claude

What it does

Claude Devfleet is an agent skill from affaan-m/ECC. 通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。

Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.

Example prompts

  • “/claude-devfleet”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 规划：调用 plan_project(prompt="...") → 返回 project_id 以及带有 depends_on 链和 auto_dispatch=true 的任务列表。
  2. 展示计划：向用户呈现任务标题、类型和依赖链。
  3. 调度：对根任务（depends_on 为空）调用 dispatch_mission(mission_id=)。剩余任务在其依赖项完成时自动调度（因为 plan_project 为它们设置了 auto_dispatch=true）。
  4. 监控：调用 get_mission_status(mission_id=...) 或 get_dashboard() 检查进度。
  5. 报告：任务完成后调用 get_report(mission_id=...)。与用户分享亮点。

What it can do on your machine

Read from SKILL.md and the folder at commit ef648e0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • claude

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Claude Devfleet loads about 909 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~20
When it runs · the whole SKILL.md, loaded when a task matches
~909

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from affaan-m/ECC at commit ef648e0, republished under its MIT licence (© affaan-m). 214 words, ~909 tokens.

Download SKILL.mdSave it as .claude/skills/claude-devfleet/SKILL.md (or your agent's skills folder).
name
claude-devfleet
description
通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。
origin
community

Claude DevFleet 多智能体编排

使用时机

当需要调度多个 Claude Code 智能体并行处理编码任务时使用此技能。每个智能体在独立的 git worktree 中运行，并配备全套工具。

需要连接一个通过 MCP 运行的 Claude DevFleet 实例：

bash
claude mcp add devfleet --transport http http://localhost:18801/mcp

工作原理

用户 → "构建一个带有身份验证和测试的 REST API"
  ↓
plan_project(prompt) → 项目ID + 任务DAG
  ↓
向用户展示计划 → 获取批准
  ↓
dispatch_mission(M1) → 代理1在工作树中生成
  ↓
M1完成 → 自动合并 → 自动分发M2 (依赖于M1)
  ↓
M2完成 → 自动合并
  ↓
get_report(M2) → 更改的文件、完成的工作、错误、后续步骤
  ↓
向用户报告
工具
工具用途
plan_project(prompt)AI 将描述分解为包含链式任务的项目
create_project(name, path?, description?)手动创建项目，返回 project_id
create_mission(project_id, title, prompt, depends_on?, auto_dispatch?)添加任务。depends_on 是任务 ID 字符串列表（例如 ["abc-123"]）。设置 auto_dispatch=true 可在依赖满足时自动启动。
dispatch_mission(mission_id, model?, max_turns?)启动智能体执行任务
cancel_mission(mission_id)停止正在运行的智能体
wait_for_mission(mission_id, timeout_seconds?)阻塞直到任务完成（见下方说明）
get_mission_status(mission_id)检查任务进度而不阻塞
get_report(mission_id)读取结构化报告（更改的文件、测试情况、错误、后续步骤）
get_dashboard()系统概览：运行中的智能体、统计信息、近期活动
list_projects()浏览所有项目
list_missions(project_id, status?)列出项目中的任务

关于 wait_for_mission 的说明： 此操作会阻塞对话，最长 timeout_seconds 秒（默认 600 秒）。对于长时间运行的任务，建议改为每 30-60 秒使用 get_mission_status 轮询，以便用户能看到进度更新。

工作流：规划 → 调度 → 监控 → 报告
  1. 规划：调用 plan_project(prompt="...") → 返回 project_id 以及带有 depends_on 链和 auto_dispatch=true 的任务列表。
  2. 展示计划：向用户呈现任务标题、类型和依赖链。
  3. 调度：对根任务（depends_on 为空）调用 dispatch_mission(mission_id=<first_mission_id>)。剩余任务在其依赖项完成时自动调度（因为 plan_project 为它们设置了 auto_dispatch=true）。
  4. 监控：调用 get_mission_status(mission_id=...) 或 get_dashboard() 检查进度。
  5. 报告：任务完成后调用 get_report(mission_id=...)。与用户分享亮点。
并发性

DevFleet 默认最多同时运行 3 个智能体（可通过 DEVFLEET_MAX_AGENTS 配置）。当所有槽位都占满时，设置了 auto_dispatch=true 的任务会在任务监视器中排队，并在槽位空闲时自动调度。检查 get_dashboard() 了解当前槽位使用情况。

示例

全自动：规划并启动
  1. plan_project(prompt="...") → 显示包含任务和依赖关系的计划。
  2. 调度第一个任务（depends_on 为空的那个）。
  3. 剩余任务在依赖关系解决时自动调度（它们具有 auto_dispatch=true）。
  4. 报告项目 ID 和任务数量，让用户知道启动了哪些内容。
  5. 定期使用 get_mission_status 或 get_dashboard() 轮询，直到所有任务达到终止状态（completed、failed 或 cancelled）。
  6. 对每个终止任务执行 get_report(mission_id=...)——总结成功之处，并指出失败任务及其错误和后续步骤。
手动：逐步控制
  1. create_project(name="My Project") → 返回 project_id。
  2. 为第一个（根）任务执行 create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true) → 捕获 root_mission_id。 为每个后续任务执行 create_mission(project_id=project_id, title="...", prompt="...", auto_dispatch=true, depends_on=["<root_mission_id>"])。
  3. 在第一个任务上执行 dispatch_mission(mission_id=...) 以启动链。
  4. 完成后执行 get_report(mission_id=...)。
带审查的串行执行
  1. create_project(name="...") → 获取 project_id。
  2. create_mission(project_id=project_id, title="Implement feature", prompt="...") → 获取 impl_mission_id。
  3. dispatch_mission(mission_id=impl_mission_id)，然后使用 get_mission_status 轮询直到完成。
  4. get_report(mission_id=impl_mission_id) 以审查结果。
  5. create_mission(project_id=project_id, title="Review", prompt="...", depends_on=[impl_mission_id], auto_dispatch=true) —— 由于依赖已满足，自动启动。

指南

  • 在调度前始终与用户确认计划，除非用户已明确指示继续。
  • 报告状态时包含任务标题和 ID。
  • 如果任务失败，在重试前读取其报告。
  • 批量调度前检查 get_dashboard() 了解智能体槽位可用性。
  • 任务依赖关系构成一个有向无环图（DAG）——不要创建循环依赖。
  • 每个智能体在独立的 git worktree 中运行，并在完成时自动合并。如果发生合并冲突，更改将保留在智能体的 worktree 分支上，以便手动解决。
  • 手动创建任务时，如果希望它们在依赖项完成时自动触发，请始终设置 auto_dispatch=true。没有此标志，任务将保持 draft 状态。

© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in docs/zh-CN/skills/claude-devfleet of affaan-m/ECC.

Open the folder on GitHubat commit ef648e0

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in affaan-m/ECC, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Claude Devfleet next to the 3 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Claude Devfleet compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Claude Devfleet this skillaffaan-m/ECC276k1 repos~909Automated safety check: PassMIT
Claude Devfleetloulanyue/awesome-claude-notes2722 repos~1.4kAutomated safety check: PassMIT
Claude Devfleetaffaan-m/ECC276k1 repos~1.5kAutomated safety check: PassMIT
Claude Devfleetaffaan-m/ECC276k—~468Automated safety check: PassMIT

Similar skills

  • Claude Devfleet

    loulanyue/awesome-claude-notes

    Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

    272 GitHub starsUsed in 2 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Devfleet

    affaan-m/ECC

    Orchestrate multi-agent coding tasks via Claude DevFleet — plan projects, dispatch parallel agents in isolated worktrees, monitor progress, and read structured reports.

    276k GitHub starsUsed in 1 repo~1.5k tokens
    Agent WorkflowsAuto-check passed

  • Claude Devfleet

    affaan-m/ECC

    Claude DevFleet経由でマルチエージェントコーディングタスクをオーケストレーション — プロジェクトを計画し、分離された作業ツリー内で平行エージェントを派遣し、進捗を監視し、構造化レポートを読む。

    276k GitHub stars~468 tokensUpdated 4 days ago
    Auto-check passed

More from affaan-m/ECC

All 673 skills in this repo

  • Skill Stocktake

    affaan-m/ECC

    Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.

    276k GitHub starsUsed in 5 repos~1.9k tokens
    Auto-check passed

  • VideoDB Video Search and Editing

    affaan-m/ECC

    Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.

    276k GitHub starsUsed in 3 repos~3.5k tokens
    Auto-check: notes

  • Rules Distillation

    affaan-m/ECC

    Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.

    276k GitHub starsUsed in 2 repos~2.3k tokens
    Auto-check passed

  • Master Agreement Generator

    affaan-m/ECC

    Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.

    276k GitHub stars~2.9k tokensUpdated 4 days ago
    Auto-check passed

  • Skill Compliance Checker

    affaan-m/ECC

    Measures whether agents actually follow a skill, rule or agent definition by generating scenarios at three strictness levels and scoring tool-call traces.

    276k GitHub starsUsed in 1 repo~623 tokens
    Auto-check passed

  • Continuous Learning V2

    affaan-m/ECC

    Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

    276k GitHub stars~3.5k tokensUpdated 4 days ago
    Auto-check passed

Questions about Claude Devfleet

What does Claude Devfleet do?

通过Claude DevFleet协调多智能体编码任务——规划项目、在隔离的工作树中并行调度智能体、监控进度并读取结构化报告。. Claude Devfleet is an agent skill from affaan-m/ECC.

How do I install Claude Devfleet in Claude Code?

Run `npx skills add affaan-m/ECC --skill claude-devfleet -a claude-code`. Or copy the skill folder (docs/zh-CN/skills/claude-devfleet in affaan-m/ECC) into .claude/skills/claude-devfleet in your project. Claude Code loads it when a task matches its description.

How do I install Claude Devfleet in Codex?

Run `npx skills add affaan-m/ECC --skill claude-devfleet -a codex`. Or copy the skill folder (docs/zh-CN/skills/claude-devfleet in affaan-m/ECC) into .agents/skills/claude-devfleet in your project. Codex loads it when a task matches its description.

Can I use Claude Devfleet in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill claude-devfleet -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/claude-devfleet, .gemini/skills/claude-devfleet, .github/skills/claude-devfleet and .opencode/skills/claude-devfleet in your project.

What does Claude Devfleet need to run?

Going by SKILL.md and its folder, Claude Devfleet needs the command-line tools its instructions call (claude).

Does Claude Devfleet access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Claude Devfleet safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Claude Devfleet use?

Claude Devfleet is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Claude Devfleet use?

About 909 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Claude Devfleet?

Skills that share tags, products or a category with Claude Devfleet: Claude Devfleet (loulanyue/awesome-claude-notes, 272 stars), Claude Devfleet (affaan-m/ECC, 276k stars) and Claude Devfleet (affaan-m/ECC, 276k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Claude Devfleet?

affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 275,546 GitHub stars. The repository holds 673 skills in this directory. The repository was last updated on October 5, 2026.

Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.