Skills subagent-development

📦

subagent-development

Name: subagent-development
Author: DMJGilbert

Content revision r1 Safe ⚙️ External commands

Coordinate Subagent Development

Complex implementation plans can lose quality when tasks share stale context. This skill guides isolated subagent execution with review checkpoints after every 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-development" from https://skillstore.io/skills/dmjgilbert-subagent-development.md and its manifest at https://skillstore.io/api/skills/dmjgilbert-subagent-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/dmjgilbert-subagent-development.md Signed manifest GET /api/skills/dmjgilbert-subagent-development/manifest Signed lockfile GET /api/skills/dmjgilbert-subagent-development/lockfile

Test it

Using "subagent-development". A user provides a five-task refactor plan.

Expected outcome:

Creates a tracked task list from the plan.
Runs Task 1 in an isolated implementation context.
Sends the completed task to a reviewer before continuing.
Documents any deferred medium or low issues.

Using "subagent-development". A reviewer reports a high priority regression after Task 2.

Expected outcome:

The skill directs the assistant to fix the issue before starting Task 3 and request another review checkpoint.

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

Expected outcome:

Runs a final review against the original plan.
Checks for regressions and unresolved review items.
Transitions to merge or pull request workflow when ready.

Security Audit

Safe

v8 • 7/21/2026 Open versioned report

All 12 static detections are false positives. The nine external-command detections match Markdown code fences, and the three network-reconnaissance detections match ordinary implementation and review language. No prompt injection, data exfiltration, or unsafe operational intent was found in SKILL.md.

Files scanned

166

Lines analyzed

Review items

False positives ignored

Risk Factors

⚙️ External commands (9)

SKILL.md:27-31 SKILL.md:31-37 SKILL.md:37-54 SKILL.md:54-60 SKILL.md:60-74 SKILL.md:74-95 SKILL.md:95-108 SKILL.md:108-132 SKILL.md:132-158

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: claude 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/dmjgilbert-subagent-development/audits/8?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

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

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

BibTeX citation

@techreport{dmjgilbert-dmjgilbert-subagent-development-2026,
  author = {DMJGilbert},
  title = {subagent-development security audit report (audit version 8)},
  institution = {Skillstore},
  year = {2026},
  number = {8},
  url = {https://skillstore.io/skills/dmjgilbert-subagent-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-development security audit report (audit version 8)"
version: "unspecified"
type: report
authors:
  - name: "DMJGilbert"
date-released: "2026-07-21"
url: "https://skillstore.io/skills/dmjgilbert-subagent-development/audits/8"
identifiers:
  - type: other
    value: "skillstore:dmjgilbert-subagent-development:audit:8"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Execute a phased implementation plan

Run each plan task in a fresh context and review work before moving forward.

Add review gates to AI-assisted changes

Use reviewer checkpoints to catch regressions, missing tests, and requirement drift after each task.

Resume long-running work safely

Track task status and deferred issues so work can pause without losing context.

Try These Prompts

Run a plan step by step

Use subagent-development on this plan. Create the task list, dispatch one fresh subagent per task, review after each task, and stop for critical issues.

Implement with TDD gates

Use this skill to implement the plan with TDD. For each task, request a failing test, minimal implementation, passing tests, and review.

Coordinate dependent tasks

Use subagent-development, but identify dependencies before dispatch. Only start the next task after critical and high review findings are resolved.

Audit a completed task sequence

Apply the final review step to these commits. Check plan compliance, architecture, regressions, and unresolved review items before recommending merge readiness.

Best Practices

Start with a reviewed plan before using this skill.
Keep each subagent task small enough to test and review.
Resolve critical and high review findings before continuing.

Avoid

Do not use it for quick edits that do not need task isolation.
Do not run multiple implementation subagents in parallel.
Do not skip reviewer feedback because tests passed.

Frequently Asked Questions

Does this skill create the implementation plan?

No. It assumes a plan already exists and helps execute it with review checkpoints.

Can it run tasks in parallel?

No. The workflow requires one implementation subagent at a time to keep review order clear.

Does it require test-driven development?

Yes. The process asks each implementation subagent to write a failing test before code changes.

What happens when a critical issue is found?

The workflow stops forward progress until the issue is fixed and reviewed again.

Is it compatible with Claude, Codex, and Claude Code?

Yes. The report marks support for Claude, Codex, and Claude Code workflows.

When should I avoid this skill?

Avoid it for small edits, tightly dependent tasks, or plans that still need review.

Developer Details

Author

DMJGilbert

License

MIT

Skillstore revision

Version notice

The author did not declare a version.

Repository

https://github.com/DMJGilbert/.config/tree/main/users/darren/config/claude/skills/subagent-development

Ref

72d5025b022c77f7a51bdf5c1637c689c80e89d1

Maintenance freshness

7/24/2026

Usage

6 downloads · 203 views

File structure

📄 SKILL.md