subagent-driven-development

subagent-driven-development is a plugin for Claude Code from jasonm4130/claude-skills. Its manifest loads nothing; the 1 skill it bundles cost 102 tokens per session together, scanned A, original, MIT.

A fixed workflow for building software through planned tasks, separate coding agents, reviews, fixes, and final branch checks. It can run independent tasks in parallel while keeping dependencies and merge points controlled.

In plain words
What is it for?
Use it to plan a feature, divide it into dependent tasks, run implementation and review work in separate worktrees, merge completed waves, and perform a final whole-branch review.
Why use it?
Multi-agent coding can become inconsistent when tasks, reviews, and merges are handled ad hoc. This provides a repeatable process for coordinating the work and escalating blocked tasks.

Plugin for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code
/plugin marketplace add jasonm4130/claude-skills
agentmods
npx agentmods add plugins/jasonm4130/claude-skills/subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/jasonm4130/claude-skills

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 1 skill cost 102 tokens a session between them.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

The scan reads plugin.json. This mod also ships 1 executable file (manifest.test.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/subagent-driven-development/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "subagent-driven-development",
  "description": "Deterministic, workflow-driven subagent development loop: plan -> confirm -> background Workflow runs per-task implement/review/fix with tiered models in deps-driven parallel waves (per-task worktrees + per-wave merge gate), ponytail anti-over-engineering discipline, deterministic BLOCKED escalation and oscillation halt, then an Opus whole-branch final review. Replaces the model-driven superpowers post-plan suite.",
  "version": "0.12.0",
  "author": {
    "name": "Jason Matthew",
    "email": "[email protected]"
  },
  "homepage": "https://github.com/jasonm4130/claude-skills",
  "repository": "https://github.com/jasonm4130/claude-skills",
  "license": "MIT",
  "keywords": [
    "subagent-driven-development",
    "sdd",
    "workflow",
    "tdd",
    "code-review",
    "ponytail",
    "model-tiering"
  ]
}
Contents

What it installs

The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 102 tokens a session between them. Each is measured on its own page, and each can be installed alone.

Files

What ships with it

1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 22 lines scan A 99b23287f178

Subscribe to this mod's changes

subagent-driven-development is a plugin published in the GitHub repository jasonm4130/claude-skills (5 stars, last pushed 3d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other plugins, from other repositories

moai-accountant

재무·세무 전담 AI 코워커 — 재무제표 분석·결산 관리·차이 분석·IR, 개인 세금 절약·가계 예산·투자 입문·보험 적합성 스킬 11종. OpenDART 전자공시 MCP 연동. 이런 분께 추천: 사업자·재무 담당자·개인 재테크 입문자. ※ 세무사·회계사 자문 대체가 아닌 참고 자료입니다.

modu-ai/moai-cowork · not measured

moai-analyst

데이터·공공데이터 분석 전담 AI 코워커 — 데이터 프로파일링·시각화, 공공데이터 조회(부동산·경매·주식·KOSIS·건축물대장) 스킬 7종. KOSIS 통계·건축HUB·DART 전자공시 MCP 연동. 자연어 요청 시 매칭 스킬이 자동 호출됩니다. 이런 분께 추천: 데이터 애널리스트·사무직·기획자·자영업 운영자.

modu-ai/moai-cowork · not measured

moai-career

구직자 편 커리어 코칭 전담 AI 코워커 — 이력서·포트폴리오 첨삭, 면접 준비, 이직 전략까지 커리어 전환 실무 스킬. 인사채용(고용주 편)과 구분되는 구직자 관점입니다. 이런 분께 추천: 이직 준비자·취업 준비생·주니어 직장인.

modu-ai/moai-cowork · not measured

moai-consultant

경영·창업 컨설팅 전담 AI 코워커 — 사업계획서·비즈니스 모델·시장 분석(TAM/SAM/SOM)·경영 진단 브리프·정부 지원사업 매칭·상권분석 보고서까지 전략 실무 스킬 6종. 이런 분께 추천: 예비 창업자·소상공인·스타트업 운영자.

modu-ai/moai-cowork · not measured

axiom-git

Composes Conventional Commits messages with gitmoji from the staged diff, deciding type, scope, emoji, subject, and body, and gating on protected branches, staged secrets, and pre-commit hooks.

netopsengineer/axiom · not measured

osv-scanner

Scans project dependencies for known vulnerabilities using OSV Scanner and the OSV database.

alejandrosaenz117/bonfires-marketplace · not measured