subagent-driven-development
Use when executing implementation plans with independent tasks in the current session
- License 许可
- MIT
- 最近更新
- 2026-11-05
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- subagent-driven-development
- version
- 1.0.0
- description
- Use when executing implementation plans with independent tasks in the current session
02 资源文件 12
- 参考文档implementer-prompt.md6.2 KB
- 参考文档re-review-prompt.md4.6 KB
- 参考文档sections/common-rationalizations.md1.4 KB
- 参考文档sections/example-workflow.md2.3 KB
- 参考文档sections/final-review.md1.4 KB
- 参考文档sections/finish.md833 B
- 参考文档sections/model-selection.md1.9 KB
- 参考文档sections/setup.md3.3 KB
- 参考文档sections/the-process.md4.7 KB
- 参考文档sections/the-task-loop.md12.6 KB
- 参考文档sections/when-to-use.md1.1 KB
- 参考文档task-reviewer-prompt.md8.8 KB
03 SKILL.md 正文
Subagent-Driven Development
Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.
Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.
Core principle: Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration
Narration: between tool calls, narrate at most one short line — the ledger and the tool results carry the record.
Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.
Rulings, not stalls. A running plan does not wait on a human. Conflicts,
ambiguities, plan defects, a cap you would have asked to exceed — decide
them. The spec is the binding authority, the plan is its argument, and your
judgment settles what neither answers. Record every decision in the ledger as
Ruling: <what you decided> — <why> — <what it costs if wrong>, and keep
going. A wrong ruling costs rework your human partner can see and undo; a
session parked on a question costs their whole day and buys nothing.
Four things stop you, and only these: an irreversible or destructive operation; a security-sensitive action; a side effect outside this worktree that norms say you ask about first (a merge, a push to a shared branch, a publish); and a plan so broken that every path forward is a guess. For those, stop and ask.
04 同仓库更多 Skills
writing-waterfall-requirements-documents
Write a waterfall requirements document: elicit, structure and review testable, traceable requirements, then baseline the specification before design.
writing-vision-and-values-statements
Write a V2MOM vision a reader can test and a ranked list of values that settles real tradeoffs, so the rest of the document has a clear anchor.
writing-system-prompts-for-claude
Write Claude prompts and CLAUDE.md files that supply exact inputs, scope the task, and define done so the first attempt can be checked.
writing-page-specific-website-copy
Website copywriting by page type: write homepage, landing page, pricing page and feature page copy that fits each page's visitor and single job.
writing-internal-press-releases
How to write an internal press release: the one-page working backwards press release that opens a PR/FAQ document before anything is built.
writing-email-sequences-that-sell
Email sequence copywriting for nurture and sales: give each email one job, write clear subject lines, and close with one specific call to action.