subagent-driven-development
Skill1 starsChanged 6 months agoMITView on GitHub
Use when executing implementation plans with many tasks or large file impact. Also invoked automatically when executing-plans detects the plan exceeds its threshold (>8 tasks or any task touches >5 files).
189 other projects use a version of this.
Adopted by
Most recently taken up by
- DemonDamon/AgenticXtheir own version, first seen Nov 9, 2026
- roundpilot/superpowers-antigravitytheir own version, first seen Nov 8, 2026
- REPOZY/superpowers-optimizedtheir own version, first seen Nov 8, 2026
- lingyired/status-triotheir own version, first seen Nov 8, 2026
- DJtx001/ai-coding-playbooktheir own version, first seen Nov 8, 2026
- namlxuit056/social-forextheir own version, first seen Nov 8, 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 versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 189
- obra/superpowers★ 314ksame name
- jnMetaCode/superpowers-zh★ 8.4ksame name
- openai/plugins★ 7.8ksame name
- farm-fe/farm★ 5.6ksame name
- lingyired/status-trio★ 1.8ksame name
- GanyuanRan/Aegis★ 1.4ksame name
- pcvelz/superpowers★ 1.3ksame name
- math-inc/OpenGauss★ 1.3ksame name
- DemonDamon/AgenticX★ 1ksame name
- coco-research/coco★ 797same name
179 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 repository20 other files it gives its agents.
- finishing-a-development-branchSkill
- receiving-code-reviewSkill
- requesting-code-reviewSkill
- systematic-debuggingSkill
- verification-before-completionSkill
- api-designSkill
- database-migrationsSkill
- fastapi-patternsSkill
- logging-standardsSkill
- python-patternsSkill
- redis-patternsSkill
- springboot-patternsSkill
- security-reviewSkill
- using-superpowersSkill
- java-testingSkill
- python-testingSkill
- test-driven-developmentSkill
- brainstormingSkill
- executing-plansSkill
- writing-plansSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
18 rules. 0 are common, 11 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 179 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
If 03-implementation-plan.md already has tasks with status other than pending, a prior session was interrupted.
- Distinctive: line 18
Read all task statuses.
- Distinctive: line 44
Before dispatching any implementer, scan the full task list for parallelism opportunities:
- Distinctive: line 55
When not to parallelize: if you cannot confidently determine the file/table overlap from the plan, default to sequential.
- Very specific: line 59
Check Depends on — all listed tasks must be completed before dispatching.
- Distinctive: line 61
If questions are raised, answer before implementation.
- Distinctive: line 74
If spec issues exist, implementer fixes and spec review repeats.
- Distinctive: line 76
If quality issues exist:
- Very specific: line 81
Update 04-verification.md evidence for task REQ/CR/DR mapping.
- Distinctive: line 86
If a new requirement or optimization appears mid-run:
- Very specific: line 89
If scope change: add CR-### in 05-change-log.md, update 01-requirements.md.
- Very specific: line 90
If design change only: add DR-### in 05-change-log.md, update 02-design.md.
- Very specific: line 91
Update 03-implementation-plan.md tasks/status (pending/in_progress/completed/superseded/cancelled).
- Very specific: line 92
Update impacted verification entries in 04-verification.md.
- Distinctive: line 95
No task implementation is allowed for unmapped requests.
- Distinctive: line 99
Before final reviewer and branch-finishing:
- Distinctive: line 112
Start code quality review before spec compliance passes
- Distinctive: line 115
Start work on main/master without explicit user consent
“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.
Files
Subagent-Driven Development
Execute one planned task at a time with a fresh implementer subagent, then two reviews: spec compliance first, code quality second.
Core Principle
Fresh subagent per task + strict traceability + two-stage review.
RESUME Mode (when session was interrupted)
If 03-implementation-plan.md already has tasks with status other than pending, a prior session was interrupted. Do not start from scratch.
- Read all task statuses.
completed→ skip entirely, do not re-implement.in_progress→ check whether the implementer produced any code output (look for commits or file changes since the task was markedin_progress):- Code exists → interrupted mid-review. Do not re-implement. Run spec review and quality review on the existing output. If reviews pass, mark
completed. If reviews fail, dispatch implementer to fix only the flagged issues. - No code exists → interrupted before implementer finished. Treat as
pendingand dispatch implementer normally.
- Code exists → interrupted mid-review. Do not re-implement. Run spec review and quality review on the existing output. If reviews pass, mark
pending→ enter normal dispatch flow.- Announce:
"Resuming plan. Completed: N | In-progress (review-only): M | In-progress (re-dispatch): L | Pending: K."
Preflight (MANDATORY)
Step 0: Load project rules: read all files matching rules/**/*.md. Apply them for the entire session.
Load artifacts from one feature folder before dispatching any subagent:
01-requirements.md02-design.md03-implementation-plan.md04-verification.md05-change-log.md99-mistake-log.md06-research-notes.md(if present)
Build a task list from 03-implementation-plan.md and include REQ-###/CR-###/DR-### mapping per task.
Parallel Task Identification (after Preflight)
Before dispatching any implementer, scan the full task list for parallelism opportunities:
- Find the ready set: tasks whose
Depends onlists are fullycompleted. - Within the ready set, group tasks that have no shared file targets and no shared DB table modifications.
- Tasks in the same group may be dispatched in parallel — send multiple implementer subagents in a single message.
- Tasks with shared files or tables must remain sequential even if dependencies are met.
Announce: "Ready set: [Task A, B, C]. Parallel groups: [[A, C], [B] (sequential — shared file XxxMapper.xml)]."
Parallel review: each parallel implementer completes its own spec review and quality review independently. If one implementer's review fails, the others continue uninterrupted. The failed task returns to in_progress for targeted fixes only.
When not to parallelize: if you cannot confidently determine the file/table overlap from the plan, default to sequential. Incorrect parallelism with overlapping writes causes merge conflicts and is harder to recover from than sequential slowness.
Per-Task Flow
- Check
Depends on— all listed tasks must becompletedbefore dispatching. If not, skip and report blocked. - Dispatch implementer subagent using
implementer-prompt.md. - If questions are raised, answer before implementation.
- Implementer runs tests and reports outputs.
- Implementer verifies every DoD item from
03-implementation-plan.mdbefore handing off:- All tests pass; coverage meets targets
- No TODO / debug / temporary code left
- Naming follows project rules
- Error handling complete
- All callers in
Impacthandled - Commit message:
type(scope): one-line English summary
[USER CHECKPOINT 1] Present implementer's concise report to user. Wait for explicit confirmation (e.g. "continue", "ok", "确认") before proceeding to review. Do NOT dispatch reviewers until confirmed.
- Dispatch spec reviewer (
spec-reviewer-prompt.md). - If spec issues exist, implementer fixes and spec review repeats.
- Dispatch code-quality reviewer (
code-quality-reviewer-prompt.md). - If quality issues exist:
[USER CHECKPOINT 2] Present review findings (MUST/SHOULD violations) to user. Wait for explicit confirmation before dispatching implementer to fix. User may choose to skip SHOULD fixes.
Implementer fixes confirmed issues and quality review repeats.
10. Update 04-verification.md evidence for task REQ/CR/DR mapping.
11. Mark task complete.
Plan Drift Gate (MANDATORY)
If a new requirement or optimization appears mid-run:
- Stop dispatching implementers.
- If scope change: add
CR-###in05-change-log.md, update01-requirements.md. If design change only: addDR-###in05-change-log.md, update02-design.md. - Update
03-implementation-plan.mdtasks/status (pending/in_progress/completed/superseded/cancelled). - Update impacted verification entries in
04-verification.md. - Re-extract tasks, then resume dispatch.
No task implementation is allowed for unmapped requests.
Completion Gate
Before final reviewer and branch-finishing:
unmapped_req = 0open_cr = 0pending_recheck = 0
Then invoke agent-workflow:finishing-a-development-branch.
Red Flags
Never:
- Skip either review stage
- Start code quality review before spec compliance passes
- Move to next task with unresolved reviewer issues
- Implement requirement changes without CR + plan updates
- Start work on main/master without explicit user consent
Integration
- REQUIRED:
agent-workflow:writing-plans - REQUIRED:
agent-workflow:requesting-code-review - REQUIRED:
agent-workflow:finishing-a-development-branch - Subagents should use:
agent-workflow:test-driven-development
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.

