subagent-driven-development

subagent-driven-development is a skill for Claude Code, Codex from PedroMosquera/squadai. It costs 18 tokens per session (681 once invoked), scanned A, original, MIT.

A workflow for coordinating several specialised agents while building a complex feature. It uses TDD, or test-driven development, where tests are written before the code and guide the implementation.

In plain words
What is it for?
Use it to turn a feature request into test scenarios, an implementation plan, tested code, code review, and follow-up debugging when needed.
Why use it?
It divides planning, coding, review, and debugging into clear responsibilities instead of leaving one agent to manage every stage.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/pedromosquera/squadai/subagent-driven-development
Any agent
npx skills add PedroMosquera/squadai --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/PedroMosquera/squadai

Made for: Claude Code, Codex.

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/pedromosquera/squadai/subagent-driven-development.svg)](https://agentmods.dev/skills/pedromosquera/squadai/subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/pedromosquera/squadai/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/pedromosquera/squadai/subagent-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00018 $0.00681
Opus 5 $0.00009 $0.00341
Sonnet 5 $0.00004 $0.00136
Haiku 4.5 $0.00002 $0.00068

Measured 4d ago against content hash d953f2d5093d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

internal/assets/skills/tdd/subagent-driven-development/SKILL.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sub-Agent Driven Development Skill

Coordinate a team of specialized sub-agents through the full TDD lifecycle for a complex feature. This skill is used by the TDD Orchestrator.

Overview

Sub-agent driven development applies TDD at the team level. Rather than one agent doing all phases, each phase is handled by a specialist:

Feature Request
  → Brainstormer: scenarios and edge cases
  → Planner: ordered test plan + implementation dependencies
  → Implementer: red-green-refactor cycles
  → Reviewer: two-stage code review
  → Debugger: (if tests fail after implementation)

Orchestration Steps

1. Receive and clarify the feature request

Before delegating, gather:

  • Clear success criteria
  • Acceptance tests (user-visible behavior)
  • Non-functional requirements (performance, security)
  • Constraints (deadline, API compatibility)

If any are missing, ask before starting delegation.

2. Delegate to Brainstormer

Provide: the feature description + success criteria. Expect back: numbered list of test scenarios grouped by category. Validate: covers happy paths, edge cases, and error scenarios.

3. Delegate to Planner

Provide: the brainstorming output + feature description. Expect back: ordered test plan + implementation dependencies. Validate: tests are ordered simple → complex, dependencies listed.

4. Delegate to Implementer

Provide: the full test plan. Expect back: passing test suite + minimal implementation. Validate: all tests pass, no skipped tests, no TODO comments.

5. Delegate to Reviewer

Provide: the diff (all changed files). Expect back: Critical/Warning/Suggestion review findings. Validate: no Critical findings before accepting. Address Warnings.

6. Handle failures via Debugger

If Implementer reports failing tests, delegate to Debugger. Provide: exact failure output + relevant code. Expect back: root cause analysis + fix. Then re-delegate to Implementer or apply fix directly.

Sub-Agent Isolation Rules

  • Each sub-agent starts with a fresh context
  • Pass ONLY what the sub-agent needs — no irrelevant history
  • Summarize results after each phase (do not carry full sub-agent output)
  • If a sub-agent exceeds its scope, correct and redirect

Read the full file on GitHub · 104 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. 4d ago First seen · 104 lines · 18 tokens per session scan A d953f2d5093d

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository PedroMosquera/squadai (8 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 681 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

red-green-refactor

Guides the red-green-refactor TDD workflow: write a failing test first, implement the minimum code to make it pass, then refactor while keeping tests green. Use when a user asks to practice TDD, write tests first, follow red-green-refactor, do test-driven development, write failing tests before code, or phrases like…

rohitg00/skillkit · 90 tokens

kiro-impl

Implement approved tasks using TDD with subagent dispatch. Runs all pending tasks autonomously or selected tasks manually.

gotalab/cc-sdd · 27 tokens

testing-strategy

Design test strategies and test plans with coverage targets. Complements /draft:coverage which measures what this skill plans. Auto-loaded by /draft:implement before TDD.

drafthq/draft · 38 tokens

hotfix

Fixes an observed defect with reproducible evidence in one call: writes a short trace doc before touching code, implements the fix, and backs it with a regression test written before the fix. Production incidents are the motivating case, not a gate. When blocked, it halts by name and saves the doc for a later call to…

pe-menezes/vibeflow · 102 tokens

testing

Applies repository-aware TDD, observable test design, and applicable quality checks. Use when changing behavior, writing tests, or reviewing test quality.

shinpr/agentic-code · 31 tokens

write-plan

Write a bite-sized TDD implementation plan from a spec before touching code. Saves under docs/plans/ / (gitignored WIP); promote to docs/features/ / when stable. Use when the user invokes write-plan, or when interview-plan hands off an assembled spec. Do not use to implement.

ayberkcansever/ai-skills · 70 tokens