subagent-driven-development

subagent-driven-development is a skill for Claude Code, Codex from coctostan/pi-superpowers-plus. It costs 17 tokens per session (2,662 once invoked), scanned A, original, MIT.

A way to carry out an approved implementation plan by assigning each independent task to a fresh coding agent. Each task receives a requirements review and then a code-quality review.

In plain words
What is it for?
It helps implement multi-task plans, review each task for matching requirements, check code quality, and coordinate work that can be done independently.
Why use it?
It separates tasks and review responsibilities, making mistakes easier to spot before moving on. It also provides a structured path from an approved plan to completed code.

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/coctostan/pi-superpowers-plus/subagent-driven-development
Any agent
npx skills add coctostan/pi-superpowers-plus --skill subagent-driven-development
Clone the repo
git clone --depth 1 https://github.com/coctostan/pi-superpowers-plus

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/coctostan/pi-superpowers-plus/subagent-driven-development.svg)](https://agentmods.dev/skills/coctostan/pi-superpowers-plus/subagent-driven-development)
Your own site
<a href="https://agentmods.dev/skills/coctostan/pi-superpowers-plus/subagent-driven-development"><img src="https://agentmods.dev/badge/skills/coctostan/pi-superpowers-plus/subagent-driven-development.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,662 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 $0.00017 $0.02662
Opus 5 $0.00009 $0.01331
Sonnet 5 $0.00003 $0.00532
Haiku 4.5 $0.00002 $0.00266

Measured 4d ago against content hash 81b8c032bc00, 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.

skills/subagent-driven-development/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Related skills: Need an isolated workspace? /skill:using-git-worktrees. Need a plan first? /skill:writing-plans. Done? /skill:finishing-a-development-branch.

Subagent-Driven Development

Execute plan by dispatching fresh subagent per task, with two-stage review after each: spec compliance review first, then code quality review.

Core principle: Fresh subagent per task + two-stage review (spec then quality) = high quality, fast iteration

If a tool result contains a ⚠️ workflow warning, stop immediately and address it before continuing.

Prerequisites

  • Active branch (not main) or user-confirmed intent to work on main
  • Approved plan or clear task scope

When to Use

digraph when_to_use {
    "Have implementation plan?" [shape=diamond];
    "Tasks mostly independent?" [shape=diamond];
    "Stay in this session?" [shape=diamond];
    "subagent-driven-development" [shape=box];
    "executing-plans" [shape=box];
    "Manual execution or brainstorm first" [shape=box];

    "Have implementation plan?" -> "Tasks mostly independent?" [label="yes"];
    "Have implementation plan?" -> "Manual execution or brainstorm first" [label="no"];
    "Tasks mostly independent?" -> "Stay in this session?" [label="yes"];
    "Tasks mostly independent?" -> "Manual execution or brainstorm first" [label="no - tightly coupled"];
    "Stay in this session?" -> "subagent-driven-development" [label="yes"];
    "Stay in this session?" -> "executing-plans" [label="no - parallel session"];
}

vs. Executing Plans (parallel session):

  • Same session (no context switch)
  • Fresh subagent per task (no context pollution)
  • Two-stage review after each task: spec compliance first, then code quality
  • Faster iteration (no human-in-loop between tasks)

Dependent tasks: Most real plans have some dependencies. For dependent tasks, include the previous task's implementation summary and relevant file paths in the next subagent's context. Track what each completed task produced so you can pass it forward.

Read the full file on GitHub · 262 lines

Files

What ships with it

3 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. 4d ago First seen · 262 lines · 17 tokens per session scan A 81b8c032bc00

Subscribe to this mod's changes

subagent-driven-development is a skill published in the GitHub repository coctostan/pi-superpowers-plus (104 stars, last pushed 6mo ago), licensed MIT. It adds 17 tokens to every session and 2,662 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 2026-08-30.

Related

Other skills, from other repositories

surf

Control Chrome browser via CLI for testing, automation, and debugging. Use when the user needs browser automation, screenshots, form filling, page inspection, network/CPU emulation, DevTools streaming, or AI queries via ChatGPT/Gemini/Perplexity/Grok/AI Studio.

w-winter/dot314 · 60 tokens

prose-review

Review prose written for others -- user-facing docs, prompts for other LLMs, inline comments, docstrings, and other-facing messages -- for local jargon leakage, orphaned references, missing grounding, and audience or genre misfit.

w-winter/dot314 · 50 tokens

text-search

Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.

w-winter/dot314 · 22 tokens

repoprompt-tool-guidance-refresh

Refresh RepoPrompt tool guidance when the CLI/MCP surface changes. Tracks RepoPrompt CE (rpce-cli, the maintained target) across versions, and can diff the frozen Classic CLI (rp-cli) against CE. Uses /.pi/agent/skills/repoprompt-tool-guidance-refresh/scripts/track-rp-version.sh to capture/diff --help and -l (tool…

w-winter/dot314 · 115 tokens

pi-commandcode-release

Use when preparing, validating, publishing, or documenting a pi-commandcode-provider release/deployment, including version bumps, changelog entries, npm publish, GitHub releases, tags, and release follow-up comments.

patlux/pi-commandcode-provider · 47 tokens

operate-pi-dispatch

How to operate a pi-dispatch deployment through its tools, and how to use the operator-confirm gates on the write tools (changing limits, adding/editing/deleting triggers).

edgehero/pi-dispatch · 41 tokens