subagent-driven-development

subagent-driven-development is a skill for Claude Code from tranhieutt/software_development_department. It costs 55 tokens per session (2,063 once invoked), scanned A, original, MIT.

A workflow for carrying out an approved implementation plan one task at a time with a new coding helper for each task. Each task passes checks for following the plan and for code quality before the next begins.

In plain words
What is it for?
Use it to implement multi-task plans, verify acceptance criteria, and review each task before progressing.
Why use it?
It adds review checkpoints and keeps separate tasks focused, especially when several tasks must be completed in sequence.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions subagents; names the TodoWrite tool.

Good fit Use it to implement multi-task plans, verify acceptance criteria, and review each task before progressing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tranhieutt/software_development_department/subagent-driven-development
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add tranhieutt/software_development_department --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for subagent-driven-development

README.md
[![agentmods](https://agentmods.dev/badge/skills/tranhieutt/software_development_department/subagent-driven-development/github.svg)](https://agentmods.dev/skills/tranhieutt/software_development_department/subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/subagent-driven-development/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for subagent-driven-development

Your own site · 80×15
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,063 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.02063
Opus 5 $0.00028 $0.01032
Sonnet 5 $0.00011 $0.00413
Haiku 4.5 $0.00006 $0.00206

Measured 9d ago against content hash da68bbac2782, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

subagent-driven-development scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/subagent-driven-development/SKILL.md · 302 lines

How it starts

The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development

Purpose

Execute an approved implementation plan by dispatching one fresh implementer subagent per task, then running two review gates before moving to the next task:

  1. Spec compliance review: did the task implement exactly the plan?
  2. Code quality review: is the implementation maintainable, tested, and safe?

The controller does not implement code directly. The controller curates context, dispatches focused subagents, verifies outputs, and blocks progression when a review gate fails.

Position in SDD

Use this workflow after:

spec-driven-development -> planning-and-task-breakdown -> user approval

Use it instead of:

  • test-driven-development inline when the plan has multiple tasks and review checkpoints would reduce risk
  • orchestrate when the work does not need multiple specialist domain waves
  • fork-join when tasks are not safe to run in parallel or share files

Preconditions

All must be true:

  • A concrete implementation plan exists.
  • The user explicitly approved executing the plan.
  • Tasks list exact files, acceptance criteria, and verification commands.
  • The current branch/worktree is appropriate for implementation.
  • Existing unrelated worktree changes are understood and will not be overwritten.

If any precondition is missing, stop and route back to planning-and-task-breakdown, using-sdd, or the user.

Before the first implementation subagent, state:

Pre-code gate: Plan satisfied by user approval; execution mode: subagent-driven-development; Task 1 owner: fresh implementer subagent.

When Not to Use

  • Single tiny task: use inline test-driven-development.
  • Multiple independent branches: use fork-join.
  • Cross-domain specialist sequencing: use orchestrate.
  • Vague requirements: use deep-interview or spec-driven-development.
  • Missing tests or verification strategy: update the plan first.

Controller Workflow

1. Load the Plan Once

Read the approved plan once. Extract:

Read the full file on GitHub · 302 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 302 lines · 55 tokens per session scan A da68bbac2782

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 2,063 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.