agentleFS
Sign inStart free
nathan-vmnathan-vm/subforge-mcp/.claude/skills/orchestrator/SKILL.md

orchestrator

Skill0 starsChanged 2 months agoMITView on GitHub

Entry point for agentic work in subforge-mcp. Breaks a request into planning, development, review, and QA instead of doing it all inline. Use for any non-trivial feature, fix, or refactor in this repo.

85 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use worker, reviewer and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • stotihvSkill

    worker

    Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

    Also in 3 projects that use this

  • MicrosoftSkill

    reviewer

    ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。

    Also in 4 projects that use this

  • yakatotechSkill

    advisor

    Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices

    Also in 3 projects that use this

  • AWSSkill

    planning

    Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

    Also in 3 projects that use this

  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 3 projects that use this

  • scott2bSkill

    obsidian

    PROACTIVELY use for Obsidian vault operations. Fast search using ripgrep, direct file operations (read/write/delete). Works with slipbox in _Slipbox directory. 4-7x faster than API. Use obsidian-api skill ONLY for Dataview queries, periodic notes, or patch operations.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 71 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    QA — conditional: If the change is user/tool-facing (new or changed MCP tool behavior, CLI-visible output), invoke qa (Agent tool, …

    line 13

“Common” is measured: kept by at least 6 in 10 of the 71 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

You are acting as the orchestrator for subforge-mcp. For anything beyond a genuinely trivial one-line change, delegate — don't write, review, or test code yourself. Your job is sequencing, context handoff between subagents, and integrating results.

Workflow

  1. Plan. Invoke planner (Agent tool, subagent_type: "planner") with the request. Skip only for a one-file, obviously-scoped change.
  2. Develop. For each planned subtask, invoke developer (Agent tool, subagent_type: "developer") with that subtask's scope and a branch/worktree name to use (e.g. feat/<slug>). It works in its own worktree under .worktrees/<branch>. Run subtasks sequentially if they touch the same files; in parallel (separate Agent calls in one message) only if they're independent.
  3. Review. Only once the developer subagent's call has returned and reported the change finished — never while it's still in flight — invoke code-review (Agent tool, subagent_type: "code-reviewer") with the same branch/worktree name, and nothing else from the developer's report or the planning conversation. It reviews that same worktree, not a separate one; the isolation is in the fresh context, not a second checkout.
  4. QA — conditional. If the change is user/tool-facing (new or changed MCP tool behavior, CLI-visible output), invoke qa (Agent tool, subagent_type: "qa") after review passes. Skip for pure refactors, internal-only changes, or doc/config edits.
  5. Integrate. Report the change, the reviewer's findings and how you addressed them, and QA results (if run) back to the user. To fix a reviewer-flagged issue, send the developer subagent another scoped task, then re-review before calling it done.

Model/effort policy

Each subagent's .claude/agents/*.md sets a default model and effort, both already inside the approved envelope (Sonnet or Haiku, effort medium or lower). Within that envelope you may judge freely per task — e.g. override a call to haiku for a trivial subtask, or to sonnet for a fiddly one, via the model param on the Agent call. Effort has no per-call override; it stays at each agent's declared default.

Going outside the envelope — Opus, or effort above medium — is never your call alone, no matter how necessary it seems. Stop and ask the user first, e.g.: "this task needs a developer with opus at high effort — approve?" Only proceed on an explicit yes.

Calling other skills

  • Calls: planner, developer, code-review, qa.
  • Called by: the repo's SessionStart hook (see .claude/settings.json), or directly via /orchestrator.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free