subagent-driven-development

subagent-driven-development is a skill for Claude Code, Codex from a5c-ai/babysitter. It costs 26 tokens per session (293 once invoked), scanned A, original, MIT.

A workflow for implementing a software plan by assigning each independent task to a fresh coding agent. Each result goes through a requirements check and then a code-quality check.

In plain words
What is it for?
Use it to execute independent tasks one at a time, verify that each matches the specification, review its code quality, and perform a final review of the whole change.
Why use it?
It prevents an implementation from moving on while it still misses the requested behaviour or has unresolved quality problems. Separate reviews provide checkpoints without relying on the implementer to review its own work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it to execute independent tasks one at a time, verify that each matches the specification, review its code quality, and perform a final review of the whole change.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/subagent-driven-development
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,783 stars · on GitHub · a5c.ai

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 a5c-ai/babysitter --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

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/a5c-ai/babysitter/subagent-driven-development/github.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/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/a5c-ai/babysitter/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/subagent-driven-development.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 293 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00026 $0.00293
Opus 5 $0.00013 $0.00147
Sonnet 5 $0.00005 $0.00059
Haiku 4.5 $0.00003 $0.00029

Measured 4d ago against content hash adfafbb965bc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, 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.

library/methodologies/superpowers/skills/subagent-driven-development/SKILL.md · 39 lines

What it actually says

  • Want to stay in current session
  • Want automatic review checkpoints

Two-Stage Review

  1. Spec Compliance - Did they build what was requested? (nothing more, nothing less)
  2. Code Quality - Is it well-built? (clean, tested, maintainable)

Spec MUST pass before quality review begins.

Red Flags

  • Never skip either review stage
  • Never proceed with unfixed issues
  • Never dispatch multiple implementation subagents in parallel
  • Never let implementer self-review replace actual review

Agents Used

  • agents/implementer/ - Fresh subagent per task
  • agents/spec-reviewer/ - Verifies spec compliance
  • agents/code-quality-reviewer/ - Verifies code quality
  • agents/code-reviewer/ - Final review of entire implementation

Tool Use

Invoke via babysitter process: methodologies/superpowers/subagent-driven-development

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 39 lines · 26 tokens per session scan A adfafbb965bc

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository a5c-ai/babysitter (1,783 stars, last pushed 4d ago), licensed MIT. It adds 26 tokens to every session and 293 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 2026-09-05.