agentleFS
Sign inStart free
RBraga01RBraga01/a-team/skills/subagent-driven-development/SKILL.md

subagent-driven-development

Skill24 starsChanged 24 days agoMITView on GitHub

Use when executing implementation plans with independent tasks in the current session. Dispatches a fresh subagent per task with two-stage review (spec compliance, then code quality).

189 other projects use a version of this, 1 of them edited.

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

9 rules. 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 179 edited versions we read keep these.

  • 9

    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:

    Continuous execution: Do not pause to check in between tasks.

    line 12
  2. Distinctive:

    Read plan file once; extract ALL tasks with full text and context

    line 18
  3. Distinctive:

    Create TodoWrite with all tasks

    line 19
  4. Distinctive:

    Verify git worktree isolation is configured

    line 20
  5. Distinctive:

    If implementer asks questions → answer, re-dispatch

    line 24
  6. Distinctive:

    If spec issues → implementer fixes, reviewer re-reviews (loop)

    line 27
  7. Distinctive:

    If quality issues → implementer fixes, reviewer re-reviews (loop)

    line 29
  8. Distinctive:

    Never skip either review stage.

    line 58
  9. Distinctive:

    Start on main/master branch without explicit user consent

    line 62

“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

Execute a plan by dispatching fresh subagents per task, with two-stage review after each.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration.

Continuous execution: Do not pause to check in between tasks. Execute all tasks without stopping. The only reasons to stop: BLOCKED status you cannot resolve, genuine ambiguity, or all tasks complete.

Process

Step 0: Setup

  • Read plan file once; extract ALL tasks with full text and context
  • Create TodoWrite with all tasks
  • Verify git worktree isolation is configured

Per Task:

  1. Dispatch implementer subagent with full task text + relevant context
  2. If implementer asks questions → answer, re-dispatch
  3. Implementer implements, tests, commits, self-reviews
  4. Dispatch spec compliance reviewer — confirms code matches spec
  5. If spec issues → implementer fixes, reviewer re-reviews (loop)
  6. Dispatch code quality reviewer — confirms quality standards met
  7. If quality issues → implementer fixes, reviewer re-reviews (loop)
  8. Mark task complete in TodoWrite

After All Tasks:

  • Dispatch final code reviewer for entire implementation
  • Use finishing-a-development-branch skill

Implementer Status Handling

StatusAction
DONEProceed to spec compliance review
DONE_WITH_CONCERNSRead concerns, address if correctness/scope issues
NEEDS_CONTEXTProvide missing context, re-dispatch
BLOCKEDAssess: context problem → more context; reasoning → higher model; too large → break up; wrong plan → escalate

Model Selection

Select the lowest tier that can handle the task:

ScopeClaude CodeOpenAIGoogle
1-2 files, clear specclaude-haiku-4-5gpt-4.1-minigemini-2.0-flash-lite
Multi-file, integration concernsclaude-sonnet-4-6gpt-4.1gemini-2.5-flash
Design judgment, broad codebaseclaude-opus-4-8o3 / gpt-5.5gemini-2.5-pro

Review Order (Critical)

Spec compliance MUST be ✅ before starting code quality review. Never skip either review stage.

Red Flags — Never Do

  • Start on main/master branch without explicit user consent
  • Skip either review stage
  • Dispatch multiple implementation subagents in parallel (file conflicts)
  • Make subagent read plan file (provide full text instead)
  • Accept "close enough" on spec compliance
  • Ignore subagent questions before they start work

Integration

Uses: writing-plans (creates the plan), finishing-a-development-branch (completes work) Subagents use: test-driven-development, code-review patterns

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