agentleFS
KPISTOLASKPISTOLAS/claude-skills/skills/02-roi-anaptyxis/subagent-driven-development/SKILL.md

subagent-driven-development

Skill0 starsChanged 21 days agoLicence not identifiedView on GitHub

Use when executing implementation plans with independent tasks in the current session

  • Deletes or force-pushes

190 other projects use a version of this, 121 of them edited; 110 of 120 edited versions we compared changed its rules; 8 new projects in the last 4 weeks, against 13 the 4 before.

How people change it

110 of 120 edited versions changed its rules, and some changes recur.

Of the 120 edited versions we compared: 9 keep every rule, 1 is an older text, 110 made changes of their own.

Not in older versions

  1. Waiting on dispatched subagents: never poll a wait interface with short timeouts, and never sit in one silent, open-ended wait either. While you have local work — ledger updates, packaging the next review, reading reports — keep working; …missing from 1 of 1
  2. When you are genuinely idle, wait in bounded stretches (five to ten minutes, where your platform allows), and between stretches post one line of status and reconcile your live children: list them, and chase any that finished without reporting. …missing from 1 of 1

Rules people drop

  1. Before dispatching Task 1, read [references/preflight.md](references/preflight.md) and run the conflict scan it describes. Its table and rulings go in the ledger.dropped by 109 of 110
  2. Small same-shape work: when the plan lists several small edits of the same kind across files, read [references/batching.md](references/batching.md) before dispatching them.dropped by 109 of 110
  3. If the reviewer reports "⚠️ Cannot verify from diff" items, read [references/cannot-verify.md](references/cannot-verify.md) before you mark the task complete.dropped by 109 of 110
  4. When it triggers, read [references/fix-loop.md](references/fix-loop.md) and follow it. …dropped by 109 of 110
  5. When every task is complete, read [references/final-review.md](references/final-review.md) and follow it. It covers the whole-branch review, its single fix wave, and how you finish.dropped by 109 of 110
  6. Waiting on dispatched subagents: never poll a wait interface with short timeouts, and never sit in one silent, open-ended wait either. While you have local work — ledger updates, packaging the next review, reading reports — keep working; …dropped by 87 of 110
  7. When you are genuinely idle, wait in bounded stretches (five to ten minutes, where your platform allows), and between stretches post one line of status and reconcile your live children: list them, and chase any that finished without reporting. …dropped by 87 of 110
  8. Read the plan once, note its context and Global Constraints, and create a todo per task. If the plan names a Spec, read that too: the spec is the authority the plan argues from, and conflicts inside the plan resolve against it. …dropped by 83 of 110

Rules people add

  1. Don't rush them into implementationadded by 77 of 110
  2. Don't skip the re-reviewadded by 77 of 110
  3. Don't try to fix manually (context pollution)added by 76 of 110
  4. superpowers:executing-plans - Use for parallel session instead of same-session executionadded by 76 of 110
  5. No file reading overhead (controller provides full text)added by 71 of 110
  6. A rule we can't quote: its licence doesn't allow itadded by 62 of 110
  7. A rule we can't quote: its licence doesn't allow itadded by 62 of 110
  8. A rule we can't quote: its licence doesn't allow itadded by 62 of 110

We split this file and each edited version into the rules they give an agent and match them by wording. A version that adds no rule of its own and has not changed since this file last did reads as an older text, so what it lacks is not counted as dropped. We keep no past texts of a file, so that is inferred, and an edited version that started from an older text still counts its gaps as drops.

Adopted by

Cooling: 8 new projects took it in the last 4 weeks, 0.6× the 4 weeks before.

Week of Sep 20: 3 new projectsWeek of Sep 27: 4 new projectsWeek of Oct 4: 4 new projectsWeek of Oct 11: 2 new projectsWeek of Oct 18: 0 new projectsWeek of Oct 25: 4 new projectsWeek of Nov 1: 1 new projectWeek of Nov 8: 3 new projects
Sep 2026Oct 2026Nov 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read.

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

Show its rules and text

We split this skill into the rules it gives an agent

24 rules. 0 are common, 21 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 175 edited versions we read keep these.

  • 21

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

The licence could not be identified — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 175 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.

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.