subagent-driven-development

A development method that assigns each independent implementation task to a fresh helper agent, then reviews the result after each task and reviews the whole branch at the end.

In plain words
What is it for?
Carrying out multi-task implementation plans with task-by-task implementation reviews, code-quality checks, and a final review. It is intended for the Superpowers workflow mode.
Why use it?
It separates tasks and review work so mistakes or missed requirements can be caught throughout implementation.

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

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin 91% copy Near-identical to another mod 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 $0.00017 $0.07577
Opus 5 $0.00009 $0.03789
Sonnet 5 $0.00003 $0.01515
Haiku 4.5 $0.00002 $0.00758

Measured yesterday against content hash c8f8b3325785, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

subagent-driven-development scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

delete this plan's workspace (`rm -rf <workspace>`) — the git history is
Origin

This is a copy

91% identical to subagent-driven-development — 10 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/skills/subagent-driven-development/SKILL.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Workflow Mode Guard

Use this skill only when the active local workflow mode is superpowers.

Before proceeding:

  • Run ./scripts/hooks/workflow-mode.sh status.
  • If the active mode is speckit, stop and tell the user to switch with make workflow-use mode=superpowers or continue with the Spec Kit lifecycle instead.
  • Do not mix Superpowers workflow skills with speckit-* commands in the same session or worktree.

Subagent-Driven Development

Execute plan by dispatching a fresh implementer subagent per task, a task review (spec compliance + code quality) after each, and a broad whole-branch review at the end.

Why subagents: You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

Core principle: Fresh subagent per task + task review (spec + quality) + broad final review = high quality, fast iteration

Narration: between tool calls, narrate at most one short line — the ledger and the tool results carry the record.

Continuous execution: Do not pause to check in with your human partner between tasks. Execute all tasks from the plan without stopping. The only reasons to stop are the four named below, or all tasks complete. "Should I continue?" prompts and progress summaries waste their time — they asked you to execute the plan, so execute it.

Rulings, not stalls. A running plan does not wait on a human. Conflicts, ambiguities, plan defects, a cap you would have asked to exceed — decide them. The spec is the binding authority, the plan is its argument, and your judgment settles what neither answers. Record every decision in the ledger as Ruling: <what you decided> — <why> — <what it costs if wrong>, and keep going. A wrong ruling costs rework your human partner can see and undo; a session parked on a question costs their whole day and buys nothing.

Read the full file on GitHub · 579 lines

Files

What ships with it

6 files 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. yesterday First seen · 579 lines · 17 tokens per session scan C c8f8b3325785

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository stefaniuk/loadout (1 stars, last pushed 3d ago), licensed MIT. It adds 17 tokens to every session and 7,577 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). It is 91% identical to subagent-driven-development, differing in 10 lines, and is treated as a copy.