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
- 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
- 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
- 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
- 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
- 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
- When it triggers, read [references/fix-loop.md](references/fix-loop.md) and follow it. …dropped by 109 of 110
- 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
- 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
- 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
- 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
- Don't rush them into implementationadded by 77 of 110
- Don't skip the re-reviewadded by 77 of 110
- Don't try to fix manually (context pollution)added by 76 of 110
- superpowers:executing-plans - Use for parallel session instead of same-session executionadded by 76 of 110
- No file reading overhead (controller provides full text)added by 71 of 110
- A rule we can't quote: its licence doesn't allow itadded by 62 of 110
- A rule we can't quote: its licence doesn't allow itadded by 62 of 110
- 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.
Most recently taken up by
- Badhon-00/MDCPedited, first seen Nov 16, 2026
- b-mendoza/agent-skillsedited, first seen Nov 16, 2026
- dragoshont/architraveedited, first seen Nov 16, 2026
- wxxb789/hoatheir own version, first seen Nov 16, 2026
- mintunitish/tandemedited, first seen Nov 15, 2026
- auarunkumar1/mugil-ideedited, first seen Nov 15, 2026
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.
Leodorareluctant259Skillchinese-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
Leodorareluctant259Skillchinese-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
obraSkilldiagnosing-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-ywSkillwebhook-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-incSkillminecraft-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-incSkillpokemon-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
Other versions190 projects use a version of this.
Word for word · 5
- lingyired/status-trio★ 1.8k100% same
- damacus/agent-skills★ 2100% same
- AxlZero21/Skills★ 1100% same
- DJtx001/ai-coding-playbook★ 1100% same
- tlinedeep/claude-skills★ 0100% same
Edited · 121
- obra/superpowers★ 314k99% same
- openai/plugins★ 7.8k69% same
- farm-fe/farm★ 5.6k23% same
- pcvelz/superpowers★ 1.3k57% same
- DemonDamon/AgenticX★ 1k15% same
- mdiri-ai/SoduWork★ 93068% same
- coco-research/coco★ 79721% same
- koaning/wigglystuff★ 45546% same
- derHaken/SuperAntigravity★ 43914% same
- Ibrahim-3d/conductor-orchestrator-superpowers★ 38114% same
111 more not listed
Wrote their own version · 64
- jnMetaCode/superpowers-zh★ 8.5ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- math-inc/OpenGauss★ 1.3ksame name
- Tommy-yw/RunbookHermes★ 546same name
- KbWen/agentic-os★ 236same name
- RedWoodOG/Hermes-Desktop★ 177same name
- REPOZY/superpowers-optimized★ 146same name
- AtlasOmnia/donna-starter★ 136same name
- shibit-net/xuanji-community★ 90same name
- AtlasOmnia/hermes-custom-pack★ 75same name
54 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository171 other files it gives its agents.
- skills/05-ereuna/humanizer/AGENTS.mdAGENTS.md
- templates/CLAUDE.mdCLAUDE.md
- algorithmoi-polyplokotitaSkill
- anagnosi-paperSkill
- arxitektoniki-ypologistonSkill
- diktya-ypologistonSkill
- elegxos-vivliografiasSkill
- ellinika-texnika-keimenaSkill
- enswmatomena-systimataSkill
- ergasia-panepistimiouSkill
- fysiki-grafiSkill
- kathigitis-kodikaSkill
- latex-ellinikaSkill
- leitourgika-systimataSkill
- metaglottistesSkill
- omadiki-ergasia-gitSkill
- proetoimasia-exetaseonSkill
- ptyxiaki-diplomatikiSkill
- theoria-ypologismouSkill
- vaseis-dedomenonSkill
- discernment-nudgeSkill
- karpathy-guidelinesSkill
- mcp-builderSkill
- skill-creatorSkill
- using-superpowersSkill
- writing-skillsSkill
- brainstormingSkill
- dispatching-parallel-agentsSkill
- executing-plansSkill
- finishing-a-development-branchSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- systematic-debuggingSkill
- test-driven-developmentSkill
- using-git-worktreesSkill
- verification-before-completionSkill
- writing-plansSkill
- bash-defensive-patternsSkill
- cpp-proSkill
- c-reviewSkill
- debugging-strategiesSkill
- devcontainer-setupSkill
- frontend-designSkill
- gh-cliSkill
- go-concurrency-patternsSkill
- golang-proSkill
- java-architectSkill
- javascript-proSkill
- modern-cppSkill
- modern-pythonSkill
- mutation-testingSkill
- property-based-testingSkill
- python-proSkill
- rust-async-patternsSkill
- rust-engineerSkill
- rust-reviewSkill
- shellcheck-configurationSkill
- typescript-proSkill
- webapp-testingSkill
- web-artifacts-builderSkill
- The first 60 shown.
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
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.

