agentleFS
iadr-deviadr-dev/colab/skills/subagent-driven-development/SKILL.md

subagent-driven-development

Skill2 starsChanged 7 months agoMITView on GitHub

Dispatch multiple specialized subagents to work in parallel on independent tasks using git worktrees to prevent conflicts. Use when a plan has 3+ independent tasks or total work >2h. Triggers when BUILD workflow runs a multi-task plan.

189 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use chinese-code-review, chinese-commit-conventions and 10 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.
  • Leodorareluctant259Skill

    chinese-code-review

    中文代码审查规范——在保持专业严谨的同时,用符合国内团队文化的方式给出有效反馈

    Also in 8 projects that use this

  • Leodorareluctant259Skill

    chinese-commit-conventions

    中文 Git 提交规范 — 适配国内团队的 commit message 规范和 changelog 自动化

    Also in 8 projects that use this

  • obraSkill

    diagnosing-superpowers

    Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

    Also in 19 projects that use this

  • Tommy-ywSkill

    webhook-subscriptions

    Create and manage webhook subscriptions for event-driven agent activation, or for direct push notifications (zero LLM cost). Use when the user wants external services to trigger agent runs OR push notifications to chats.

    Also in 5 projects that use this

  • math-incSkill

    minecraft-modpack-server

    Set up a modded Minecraft server from a CurseForge/Modrinth server pack zip. Covers NeoForge/Forge install, Java version, JVM tuning, firewall, LAN config, backups, and launch scripts.

    Also in 5 projects that use this

  • math-incSkill

    pokemon-player

    Play Pokemon games autonomously via headless emulation. Starts a game server, reads structured game state from RAM, makes strategic decisions, and sends button inputs — all from the terminal.

    Also in 5 projects that use this

  • +3 more from Leodorareluctant259
  • +2 more from math-inc

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when: plan has multiple independent tasks that can be parallelized.

    line 12
  2. Distinctive:

    Run verifier on merged result.

    line 59

“Common” is measured: kept by at least 6 in 10 of the 179 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

Subagent-Driven Development

Use when: plan has multiple independent tasks that can be parallelized.

When to Dispatch vs Do Inline

Dispatch when:

  • Tasks touch different files (no conflicts possible)
  • Tasks are independent (B doesn't depend on A's output)
  • Each task is >30min
  • 3+ tasks total in the plan

Do inline when:

  • Tasks are sequential (B needs A's output)
  • Tasks are <30min each
  • Tasks share files (git conflicts)
  • Only 1-2 tasks total

Dispatch Protocol

1. Prepare worktrees

git worktree add .git/worktrees/ohc-task-1 -b ohc/task-1
git worktree add .git/worktrees/ohc-task-2 -b ohc/task-2

2. Write task spec per subagent

Save to .ohc/state/dispatch-{id}.json:

{
  "task": "Task name from plan",
  "agent": "executor",
  "worktree": ".git/worktrees/ohc-task-1",
  "files": ["src/auth.ts", "tests/auth.test.ts"],
  "success_criterion": "All auth tests pass",
  "plan_ref": ".ohc/plans/auth-feature.md#task-1"
}

3. Launch

ohc team 3:claude "implement tasks from .ohc/state/dispatch-*.json"

Or: /ohc-team 3:executor in Claude Code with task specs attached.

4. Merge results

git merge ohc/task-1 ohc/task-2 ohc/task-3

Run verifier on merged result.

5. Cleanup

git worktree remove .git/worktrees/ohc-task-1
git branch -d ohc/task-1

See references/dispatch-patterns.md for when to dispatch. See references/worktree-coordination.md for conflict prevention.

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.