agentleFS
loganware05loganware05/captains-compass-cursor/.cursor/skills/subagent-driven-development/SKILL.md

subagent-driven-development

Skill2 starsChanged 36 days agoMITView on GitHub

Use when executing an APPROVED implementation plan with independent tasks — dispatch a fresh implementer per task, review after each, keep going with recorded Rulings

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

11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 8

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Playbook only: Does not expand Captain authority or bypass NorthStar stop rules.

    line 11
  2. Very specific:

    Prefer Skill worktree-orchestration when file boundaries need isolation.

    line 19
  3. Distinctive:

    After the task, run a focused review (spec compliance + obvious defects).

    line 33
  4. Very specific:

    Continuous execution: do not pause for “should I continue?” between tasks once the Captain approved the plan.

    line 35
  5. Distinctive:

    Stop and ask: only for:

    line 38
  6. Very specific:

    When all tasks complete, load verification-before-completion, then finishing-a-development-branch / pull-request-preparation.

    line 44
  7. Distinctive:

    Do not start without an APPROVED plan

    line 53
  8. Distinctive:

    Do not override NorthStar approval, security, or protected-branch rules

    line 54
  9. Distinctive:

    Do not auto-merge or deploy

    line 55
  10. Distinctive:

    Do not install third-party Superpowers plugins

    line 56
  11. Distinctive:

    Do not silently expand scope past the plan (return to approval gate instead)

    line 57

“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

Patterns inspired by obra/superpowers subagent-driven-development (DISCOVERED inspiration — not a plugin install).

Playbook only. Does not expand Captain authority or bypass NorthStar stop rules.

Use this Skill when

  • IMPLEMENTATION_PLAN.md is APPROVED
  • Tasks are mostly independent
  • Subagent / worktree tools are available and the Captain did not require inline-only

Prefer Skill worktree-orchestration when file boundaries need isolation.

Core principle

Fresh implementer context per task + task review (spec + quality) + final branch review. The coordinator preserves context; children do not inherit the full chat history — give them exactly what they need.

Procedure

  1. Confirm plan APPROVED and rollback/branch exist.
  2. For each plan task (in dependency order):
    • Dispatch a fresh implementer with task brief, file boundaries, acceptance checks, and pointers to Skills — not the entire session.
    • After the task, run a focused review (spec compliance + obvious defects).
    • Fix small findings yourself; re-dispatch only for material gaps.
  3. Continuous execution: do not pause for “should I continue?” between tasks once the Captain approved the plan. Record mid-flight decisions as: Ruling: <what> — <why> — <cost if wrong> and proceed.
  4. Stop and ask only for:
    • irreversible / destructive operations
    • security-sensitive actions
    • side effects outside this worktree that norms require asking (merge, push to shared branch, publish)
    • a plan so broken every path forward is a guess
  5. When all tasks complete, load verification-before-completion, then finishing-a-development-branch / pull-request-preparation.

Output

Task ledger with reviews/Rulings, validation evidence, PR-ready branch.

Prohibited actions

  • Do not start without an APPROVED plan
  • Do not override NorthStar approval, security, or protected-branch rules
  • Do not auto-merge or deploy
  • Do not install third-party Superpowers plugins
  • Do not silently expand scope past the plan (return to approval gate instead)

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.