Skills subagent-driven-development

📦

subagent-driven-development

Name: subagent-driven-development
Author: obra

Content revision r1 Safe ⚙️ External commands📁 Filesystem access

Execute Plans with Subagent Reviews

Complex implementation plans lose quality when one context handles every task. This skill coordinates fresh subagents for implementation, spec checks, and code quality reviews.

Supports: Claude Codex Code(CC)

🥉 78 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "subagent-driven-development" from https://skillstore.io/skills/obra-subagent-driven-development.md and its manifest at https://skillstore.io/api/skills/obra-subagent-driven-development/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/obra-subagent-driven-development.md Signed manifest GET /api/skills/obra-subagent-driven-development/manifest Signed lockfile GET /api/skills/obra-subagent-driven-development/lockfile

Test it

Using "subagent-driven-development". A user asks to execute task one from a prepared implementation plan.

Expected outcome:

The skill creates a task handoff, requests implementation, runs spec review, runs quality review, and marks the task complete.

Using "subagent-driven-development". A reviewer finds an extra feature that was not requested.

Expected outcome:

The implementer removes the extra work.
The spec reviewer checks the corrected task again.
The workflow continues only after approval.

Using "subagent-driven-development". All plan tasks are complete.

Expected outcome:

The workflow sends the whole branch for final review and then moves to the finishing branch process.

Security Audit

Safe

v9 • 7/6/2026 Open versioned report

The static findings are false positives caused by Markdown fences, inline prompt-template filenames, review checklist wording, and an example config path. No malicious prompt injection, data exfiltration intent, shell execution instructions, or unsafe filesystem behavior was found.

Files scanned

403

Lines analyzed

Review items

False positives ignored

Risk Factors

⚙️ External commands (8)

SKILL.md:14-30 SKILL.md:30-40 SKILL.md:40-83 SKILL.md:83-87 SKILL.md:87-88 SKILL.md:88-89 SKILL.md:89-93 SKILL.md:93-165

📁 Filesystem access (2)

SKILL.md:107 SKILL.md:107

No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.

Audited by: codex View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

https://skillstore.io/skills/obra-subagent-driven-development/audits/9?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/obra-subagent-driven-development/security.svg)](https://skillstore.io/skills/obra-subagent-driven-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/obra-subagent-driven-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/obra-subagent-driven-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/obra-subagent-driven-development.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

obra. (2026). subagent-driven-development security audit report (audit version 9) [Author version unspecified]. Skillstore. https://skillstore.io/skills/obra-subagent-driven-development/audits/9

BibTeX citation

@techreport{obra-obra-subagent-driven-development-2026,
  author = {obra},
  title = {subagent-driven-development security audit report (audit version 9)},
  institution = {Skillstore},
  year = {2026},
  number = {9},
  url = {https://skillstore.io/skills/obra-subagent-driven-development/audits/9},
  note = {Author version unspecified}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "subagent-driven-development security audit report (audit version 9)"
version: "unspecified"
type: report
authors:
  - name: "obra"
date-released: "2026-07-06"
url: "https://skillstore.io/skills/obra-subagent-driven-development/audits/9"
identifiers:
  - type: other
    value: "skillstore:obra-subagent-driven-development:audit:9"
    description: "Skillstore immutable audit report identifier"

Compare variants

9 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Higher Skillstore usage

Author / source Skillstore Score Evidence Confidence Skillstore usage Updated

ZhanlinCui Recommended

zhanlincui-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 55

Updated

2026-08-21

obra Current

obra-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

sickn33

sickn33-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 12

Updated

2026-08-21

Cygnusfear

cygnusfear-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 7

Updated

2026-08-21

Doyajin174

doyajin174-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 6

Updated

2026-08-21

Cycleaddict

cycleaddict-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 6

Updated

2026-08-21

DYAI2025

dyai2025-subagent-driven-development

Skillstore Score 75

Evidence Confidence Medium

Skillstore usage 18

Updated

2026-08-21

CodingCossack

codingcossack-subagent-driven-development

Skillstore Score 74

Evidence Confidence High

Skillstore usage 8

Updated

2026-08-21

davila7

davila7-subagent-driven-development

Skillstore Score 70

Evidence Confidence High

Skillstore usage 9

Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Coordinate a Feature Plan

Break a planned feature into reviewed implementation tasks inside one AI session.

Control AI Coding Work

Use fresh subagents to reduce context drift while preserving review checkpoints.

Verify Contract Compliance

Compare each delivered task against its requirements before quality review begins.

Try These Prompts

Run One Task

Use subagent-driven development for the next task in my plan. Dispatch an implementer, then run spec and quality reviews.

Execute a Small Plan

Execute this three-task plan with fresh subagents. Give each subagent full task text, required context, and acceptance criteria.

Handle Review Failures

When a reviewer finds issues, return to the same implementer for fixes. Re-review until both reviewers approve.

Coordinate a Release Branch

Execute all independent tasks in this branch plan. Track status, collect commit SHAs, and finish with a final code review.

Best Practices

Paste full task text into each subagent prompt instead of making the subagent read the plan.
Resolve spec compliance issues before starting code quality review.
Keep one implementer responsible for fixing issues found in its task.

Avoid

Starting several implementation subagents for overlapping tasks in parallel.
Accepting an implementer report without reading the actual changed code.
Moving to the next task while review issues remain open.

Frequently Asked Questions

What does this skill do?

It guides a same-session workflow for implementing planned tasks with fresh subagents and two review stages.

Does it write code by itself?

No. It provides instructions and prompt templates; your AI tool performs the actual work.

When should I avoid it?

Avoid it when the work is exploratory, tightly coupled, or lacks a written implementation plan.

Why use fresh subagents?

Fresh subagents reduce context carryover and keep each task focused on its own requirements.

What reviews are required?

Each task gets spec compliance review first, then code quality review after spec approval.

Which tools does it support?

The report lists Claude, Codex, and Claude Code as supported tools.

Developer Details

Author

obra

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/obra/superpowers/tree/main/skills/subagent-driven-development

Ref

e397ce5a135369cd6def89cb6400d013e2f68f2f

Maintenance freshness

7/18/2026

Usage

11 downloads · 224 views

File structure

📄 code-quality-reviewer-prompt.md

📄 implementer-prompt.md

📄 SKILL.md

📄 spec-reviewer-prompt.md