Skills subagent-driven-development
📦

subagent-driven-development

Content revision r1 Safe ⚙️ External commands

Execute Plans with Review Subagents

Complex implementation plans can lose quality when one agent keeps too much context. This skill assigns each task to a fresh subagent and adds review checkpoints before progress continues.

Supports: Claude Codex Code(CC)
📊 75 Adequate

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/dyai2025-subagent-driven-development.md and its manifest at https://skillstore.io/api/skills/dyai2025-subagent-driven-development/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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/dyai2025-subagent-driven-development.md Signed manifest GET /api/skills/dyai2025-subagent-driven-development/manifest Signed lockfile GET /api/skills/dyai2025-subagent-driven-development/lockfile

Test it

Using "subagent-driven-development". Execute a three-task feature plan with review after each task.

Expected outcome:

  • Task 1 completed with tests passing and no review blockers.
  • Task 2 required one important fix, which was applied and rechecked.
  • Task 3 passed review, and final review confirmed the plan requirements.

Using "subagent-driven-development". Review feedback reports a critical issue after Task 2.

Expected outcome:

The workflow stops normal progression, sends the issue to a fix subagent, and resumes only after the critical issue is resolved.

Using "subagent-driven-development". All implementation tasks are done.

Expected outcome:

The workflow dispatches a final code review, verifies the whole implementation, and then moves to branch completion steps.

Security Audit

Safe
v12 • 7/9/2026 Open versioned report

All seven external-command findings are false positives caused by Markdown code fences in workflow documentation. The ZIP file was manually reviewed and contains only the same SKILL.md content, so no hidden payload, prompt injection, or semantic abuse was found.

1
Files scanned
190
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (7)
SKILL.md:41-57 SKILL.md:57-64 SKILL.md:64-73 SKILL.md:73-85 SKILL.md:85-87 SKILL.md:87-111 SKILL.md:111-146
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
Security Assessment

Copy report link

https://skillstore.io/skills/dyai2025-subagent-driven-development/audits/12?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/dyai2025-subagent-driven-development/security.svg)](https://skillstore.io/skills/dyai2025-subagent-driven-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/dyai2025-subagent-driven-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/dyai2025-subagent-driven-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/dyai2025-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

DYAI2025. (2026). subagent-driven-development security audit report (audit version 12) [Author version unspecified]. Skillstore. https://skillstore.io/skills/dyai2025-subagent-driven-development/audits/12

BibTeX citation

@techreport{dyai2025-dyai2025-subagent-driven-development-2026, author = {DYAI2025}, title = {subagent-driven-development security audit report (audit version 12)}, institution = {Skillstore}, year = {2026}, number = {12}, url = {https://skillstore.io/skills/dyai2025-subagent-driven-development/audits/12}, 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 12)" version: "unspecified" type: report authors: - name: "DYAI2025" date-released: "2026-07-09" url: "https://skillstore.io/skills/dyai2025-subagent-driven-development/audits/12" identifiers: - type: other value: "skillstore:dyai2025-subagent-driven-development:audit:12" 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
ZhanlinCui Recommended

zhanlincui-subagent-driven-development

Skillstore Score 78
Evidence Confidence High
Skillstore usage 55
Updated

2026-08-21

obra

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 Current

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 9
Updated

2026-08-21

davila7

davila7-subagent-driven-development

Skillstore Score 70
Evidence Confidence High
Skillstore usage 10
Updated

2026-08-21

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Ship a Multi-Step Feature

Break a prepared implementation plan into reviewed task increments with fresh agent context for each step.

Maintain Review Discipline

Add a mandatory review gate after each subagent task so defects are caught before later work depends on them.

Coordinate AI Coding Workflows

Use a structured same-session process for implementation, review, fixes, final review, and branch completion.

Try These Prompts

Start Plan Execution 
Use subagent-driven-development to execute the plan in [plan file]. Work from [repository path] and start with the first independent task.
Run One Task with Review 
Use this workflow for Task [number] in [plan file]. Dispatch a fresh implementation subagent, request review, and report the review outcome before continuing.
Apply Review Feedback 
Use subagent-driven-development to fix the review findings for Task [number]. Treat critical and important issues as blockers before the next task.
Complete a Full Reviewed Run 
Execute every independent task in [plan file] with fresh subagents, review after each task, run final review, then use the finishing branch workflow.

Best Practices

  • Use this skill only after a clear implementation plan is available.
  • Keep task boundaries independent so each subagent can work with fresh context.
  • Resolve critical and important review issues before starting the next task.

Avoid

  • Do not use this workflow to invent or rewrite the plan during execution.
  • Do not dispatch multiple implementation subagents when they may edit the same files.
  • Do not skip intermediate reviews to save time on risky changes.

Frequently Asked Questions

What does this skill do?
It defines a same-session workflow for executing planned development tasks with fresh subagents and review gates.
Does it run commands automatically?
No. It is a process guide for agent coordination, review, and task sequencing.
When should I use it?
Use it when a plan has mostly independent implementation tasks and quality checks are important.
When should I avoid it?
Avoid it when tasks are tightly coupled, the plan is not ready, or one continuous context is required.
How does review fit into the workflow?
A code-reviewer subagent reviews each task before the next task starts, and a final review checks the complete result.
Which tools can use this skill?
The report lists compatibility with Claude, Codex, and Claude Code.

Developer Details

Author

DYAI2025

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/DYAI2025/Stoppclock-page/tree/main/stoppclock_speckit/.claude/commands/skills/subagent-driven-development

Ref

3e4b6c31a74a3bd1a291c98cf585d720cb9fbc88

Maintenance freshness

7/18/2026

Usage

15 downloads · 244 views

File structure

📄 SKILL.md

📄 SKILL.zip