Skills subagent-driven-development
📦

subagent-driven-development

Content revision r1 Safe ⚙️ External commands📁 Filesystem access

Coordinate Subagent Development Reviews

Plan execution can lose quality when one agent keeps too much context. This skill coordinates fresh implementer and reviewer subagents for each task.

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/cycleaddict-subagent-driven-development.md and its manifest at https://skillstore.io/api/skills/cycleaddict-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/cycleaddict-subagent-driven-development.md Signed manifest GET /api/skills/cycleaddict-subagent-driven-development/manifest Signed lockfile GET /api/skills/cycleaddict-subagent-driven-development/lockfile

Test it

Using "subagent-driven-development". A five-task implementation plan with mostly independent tasks.

Expected outcome:

  • A task list with all plan tasks captured before work starts.
  • A separate implementer assignment for the first task.
  • A spec review result followed by code quality review.

Using "subagent-driven-development". A reviewer finds that a task added an unrequested option.

Expected outcome:

  • The implementer receives the specific reviewer issue.
  • The unrequested option is removed or justified by the user.
  • The same reviewer gate runs again before the task is marked complete.

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

Expected outcome:

  • A final whole-branch review is requested.
  • The workflow moves to finishing the development branch.

Security Audit

Safe
v8 • 7/6/2026 Open versioned report

Static analysis flagged Markdown fences, inline prompt-template filenames, checklist questions, and one example hidden config path. Review found no command execution, system or network reconnaissance, hidden file access, data exfiltration, or prompt injection intent in the cited files.

4
Files scanned
403
Lines analyzed
0
Review items
0
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
Security Assessment

Copy report link

https://skillstore.io/skills/cycleaddict-subagent-driven-development/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

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

Cycleaddict. (2026). subagent-driven-development security audit report (audit version 8) [Author version unspecified]. Skillstore. https://skillstore.io/skills/cycleaddict-subagent-driven-development/audits/8

BibTeX citation

@techreport{cycleaddict-cycleaddict-subagent-driven-development-2026, author = {Cycleaddict}, title = {subagent-driven-development security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/cycleaddict-subagent-driven-development/audits/8}, 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 8)" version: "unspecified" type: report authors: - name: "Cycleaddict" date-released: "2026-07-06" url: "https://skillstore.io/skills/cycleaddict-subagent-driven-development/audits/8" identifiers: - type: other value: "skillstore:cycleaddict-subagent-driven-development:audit:8" 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 Current

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
55
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Execute Feature Plans

Run independent plan tasks through implementer, spec reviewer, and quality reviewer roles.

Enforce Review Gates

Require every task to pass spec compliance before code quality review begins.

Reduce Context Drift

Use fresh subagents for each task while the main session coordinates progress.

Try These Prompts

Start a Plan Run 
Use subagent-driven development for this plan. Extract each task, create a task list, and start with Task 1.
Dispatch an Implementer 
Dispatch an implementer subagent for Task N. Include the full task text, context, working directory, test expectations, and reporting format.
Run Spec Review 
Dispatch a spec compliance reviewer. Compare the requested task with the actual changed files and report missing or extra work.
Complete a Review Loop 
Send the reviewer findings back to the implementer. Require fixes, rerun the same review gate, and move forward only after approval.

Best Practices

  • Give each subagent the full task text and only the context it needs.
  • Run spec compliance review before code quality review for every task.
  • Answer subagent questions before allowing implementation to continue.

Avoid

  • Do not ask subagents to rediscover the plan from files when you can provide task text.
  • Do not mark tasks complete while reviewer issues remain open.
  • Do not use this workflow for tightly coupled tasks that need one shared context.

Frequently Asked Questions

What does this skill help coordinate?
It coordinates implementer, spec reviewer, and code quality reviewer subagents for plan-based coding work.
Does it write code by itself?
No. It provides workflow instructions and prompt templates for AI tools that can run subagents.
Why use fresh subagents for each task?
Fresh subagents reduce context drift and keep each implementation focused on one task.
Why review spec compliance before code quality?
A clean implementation still fails if it builds the wrong thing or adds unrequested behavior.
Can it be used with Claude Code or Codex?
Yes. The workflow is written for AI coding sessions that support delegated agent work.
What is the main safety consideration?
The workflow is intended to modify repositories, so users should run it only in trusted workspaces.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

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

Ref

d11af420e07cd866fe39cfa937efef3223896c06

Maintenance freshness

7/18/2026

Usage

4 downloads · 257 views

File structure

📄 code-quality-reviewer-prompt.md

📄 implementer-prompt.md

📄 SKILL.md

📄 spec-reviewer-prompt.md