Skills subagent-driven-development
📦

subagent-driven-development

v1.0 Content revision r1 Safe ⚙️ External commands

Orchestrate Subagent Implementation Reviews

Complex implementation plans can lose quality when tasks move forward without review. This skill coordinates subagent execution with spec and code quality checks.

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/doyajin174-subagent-driven-development.md and its manifest at https://skillstore.io/api/skills/doyajin174-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/doyajin174-subagent-driven-development.md Signed manifest GET /api/skills/doyajin174-subagent-driven-development/manifest Signed lockfile GET /api/skills/doyajin174-subagent-driven-development/lockfile

Test it

Using "subagent-driven-development". Completed plan for three independent interface tasks.

Expected outcome:

  • The first task is dispatched with context and acceptance criteria.
  • The implementer answers questions before editing starts.
  • Spec and quality reviews decide whether the task can complete.

Using "subagent-driven-development". Task passes implementation but fails spec review.

Expected outcome:

The same implementer receives the issues, fixes them, and repeats both reviews before progress continues.

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

Expected outcome:

The final review checks overall changes, integration tests, documentation, and merge readiness.

Security Audit

Safe
v8 • 7/6/2026 Open versioned report

All 15 static findings are false positives caused by fenced markdown blocks in SKILL.md. The matched backticks are delimiters for workflow notes and templates, not executable Ruby or shell syntax. No prompt injection, data exfiltration, network access, or malicious business logic was found.

1
Files scanned
153
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (15)
SKILL.md:19-23 SKILL.md:23-33 SKILL.md:33-53 SKILL.md:53-57 SKILL.md:57-79 SKILL.md:79-83 SKILL.md:83-88 SKILL.md:88-92 SKILL.md:92-107 SKILL.md:107-113 SKILL.md:113-125 SKILL.md:125-129 SKILL.md:129-141 SKILL.md:141-147 SKILL.md:147-152
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/doyajin174-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/doyajin174-subagent-driven-development/security.svg)](https://skillstore.io/skills/doyajin174-subagent-driven-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/doyajin174-subagent-driven-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/doyajin174-subagent-driven-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/doyajin174-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

Doyajin174. (2026). subagent-driven-development security audit report (audit version 8) [Author version 1.0]. Skillstore. https://skillstore.io/skills/doyajin174-subagent-driven-development/audits/8

BibTeX citation

@techreport{doyajin174-doyajin174-subagent-driven-development-2026, author = {Doyajin174}, title = {subagent-driven-development security audit report (audit version 8)}, institution = {Skillstore}, year = {2026}, number = {8}, url = {https://skillstore.io/skills/doyajin174-subagent-driven-development/audits/8}, note = {Author version 1.0} }

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: "1.0" type: report authors: - name: "Doyajin174" date-released: "2026-07-06" url: "https://skillstore.io/skills/doyajin174-subagent-driven-development/audits/8" identifiers: - type: other value: "skillstore:doyajin174-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 Current

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
55
Architecture
85
Maintainability
87
Content
70
Community
83
Spec Compliance

What You Can Build

Run a planned feature build

Split independent tasks across subagents while keeping review gates in the same session.

Enforce implementation review order

Require spec compliance review before code quality review for each completed task.

Manage multi-file cleanup work

Assign isolated refactors and verify changes before moving to the next item.

Try These Prompts

Start a simple subagent task 
Use subagent-driven-development for this completed plan. Dispatch one implementer for the first independent task, then run spec and quality reviews.
Coordinate independent tasks 
Use subagent-driven-development with this task list. Identify independent tasks, dispatch implementers one at a time, and stop when a review fails.
Run review-gated implementation 
Use subagent-driven-development for this plan. For each task, include context, acceptance criteria, test needs, spec review, and quality review.
Recover from review failures 
Use subagent-driven-development after a failed review. Send the issues back to the same implementer, request fixes, and repeat both reviews.

Best Practices

  • Prepare acceptance criteria before dispatching any implementer.
  • Answer subagent clarification questions before edits begin.
  • Complete spec review before code quality review.

Avoid

  • Skipping review steps when the implementation appears complete.
  • Starting code quality review before checking requirements.
  • Continuing to the next task with unresolved review issues.

Frequently Asked Questions

Does this skill write code itself?
No. It defines an orchestration workflow for assigning implementation tasks to subagents.
Should I use it without a plan?
No. The skill expects a completed implementation plan with clear tasks.
Can tasks run in parallel?
The skill is designed for current-session orchestration and sequential review gates.
Which reviews are required?
It requires spec compliance review and code quality review for each task.
Does it run tests automatically?
No. It asks the implementer to include testing, but project commands must come from the user or repository.
Is it suitable for urgent fixes?
It can help when the fix has clear acceptance criteria. Very small changes may be faster with direct implementation.

Developer Details

Author

Doyajin174

License

MIT

Author version

v1.0

Skillstore revision

r1

Version notice

The author-declared version is not valid SemVer.

Repository

https://github.com/Doyajin174/myskills/tree/main/.public/skills/subagent-driven-development

Ref

72d5025b022c77f7a51bdf5c1637c689c80e89d1

Maintenance freshness

7/18/2026

Usage

4 downloads · 232 views

File structure

📄 SKILL.md