Skills subagent-driven-development

📦

subagent-driven-development

Name: subagent-driven-development
Author: sickn33

Content revision r1 Safe ⚙️ External commands📁 Filesystem access

Coordinate Subagent Development Tasks

Independent implementation tasks can lose quality when context and reviews are inconsistent. This skill defines a same-session workflow with fresh subagents, spec checks, and code quality review.

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/sickn33-subagent-driven-development.md and its manifest at https://skillstore.io/api/skills/sickn33-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/sickn33-subagent-driven-development.md Signed manifest GET /api/skills/sickn33-subagent-driven-development/manifest Signed lockfile GET /api/skills/sickn33-subagent-driven-development/lockfile

Test it

Using "subagent-driven-development". Run a three-task plan for a login feature.

Expected outcome:

A task list is created, Task 1 is implemented by a fresh subagent, then reviewed for spec compliance and code quality.

Using "subagent-driven-development". A spec reviewer finds a missing requirement.

Expected outcome:

The implementer fixes the gap, the spec reviewer checks again, and the workflow waits before starting quality review.

Using "subagent-driven-development". All planned tasks pass their review loops.

Expected outcome:

A final branch review is requested before development is considered ready to finish.

Security Audit

Safe

v4 • 7/7/2026 Open versioned report

All static findings are false positives caused by markdown code fences, inline file references, example text, and normal review checklist language. No evidence found of command execution, hidden file access, network reconnaissance, prompt injection, or malicious intent in the reviewed files.

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/sickn33-subagent-driven-development/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/sickn33-subagent-driven-development/security.svg)](https://skillstore.io/skills/sickn33-subagent-driven-development?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/sickn33-subagent-driven-development?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/sickn33-subagent-driven-development/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/sickn33-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

sickn33. (2026). subagent-driven-development security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/sickn33-subagent-driven-development/audits/4

BibTeX citation

@techreport{sickn33-sickn33-subagent-driven-development-2026,
  author = {sickn33},
  title = {subagent-driven-development security audit report (audit version 4)},
  institution = {Skillstore},
  year = {2026},
  number = {4},
  url = {https://skillstore.io/skills/sickn33-subagent-driven-development/audits/4},
  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 4)"
version: "unspecified"
type: report
authors:
  - name: "sickn33"
date-released: "2026-07-07"
url: "https://skillstore.io/skills/sickn33-subagent-driven-development/audits/4"
identifiers:
  - type: other
    value: "skillstore:sickn33-subagent-driven-development:audit:4"
    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

obra-subagent-driven-development

Skillstore Score 78

Evidence Confidence High

Skillstore usage 15

Updated

2026-08-21

sickn33 Current

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

Execute a Feature Plan

Break a prepared feature plan into independent tasks and route each task through implementation and review.

Improve Review Discipline

Use separate spec and quality reviewers so completed tasks are checked before the next task starts.

Reduce Context Drift

Give each subagent full task context upfront while keeping the controller session focused on coordination.

Try These Prompts

Start a Small Plan

Use subagent-driven-development for this plan. Extract each independent task, create a task list, and start with the first implementer subagent.

Dispatch One Implementer

Use the implementer prompt for Task 2. Include the full task text, required context, working directory, testing expectations, and report format.

Run the Review Loop

After the implementer reports back, dispatch a spec compliance reviewer. If approved, dispatch the code quality reviewer with base and head commit SHAs.

Coordinate a Full Branch

For this development branch, execute each independent task through fresh implementation, spec review, quality review, fixes, and final branch review.

Best Practices

Provide full task text and context so subagents do not need to read the plan file.
Run spec compliance review before code quality review for every task.
Repeat review loops until reported issues are fixed and approved.

Avoid

Dispatching multiple implementation subagents in parallel on the same codebase.
Accepting an implementer report without independent code inspection.
Moving to the next task while spec or quality issues remain open.

Frequently Asked Questions

When should I use this skill?

Use it when you have a written implementation plan with mostly independent tasks to execute in the current session.

Does it replace code review?

No. It requires code review after spec compliance passes and keeps review as a separate checkpoint.

Can subagents work in parallel?

The skill warns against parallel implementation subagents because concurrent edits can conflict.

Why use a fresh subagent for each task?

Fresh subagents reduce context drift and let each task start with focused instructions.

What happens when a reviewer finds issues?

The implementer fixes the issue, then the same review stage runs again before the workflow continues.

What other skills does it expect?

It references planning, code review, finishing a branch, and test-driven development workflow skills.

Developer Details

Author

sickn33

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/subagent-driven-development

Ref

9f814fc6a43fd99946f2da5e0df231c65a38bc76

Maintenance freshness

7/18/2026

Usage

10 downloads · 136 views

File structure

📄 code-quality-reviewer-prompt.md

📄 implementer-prompt.md

📄 SKILL.md

📄 spec-reviewer-prompt.md