subagent-driven-development-codex

subagent-driven-development-codex is a skill for Claude Code, Codex from mzored/superpowers-cc-to-codex. It costs 36 tokens per session (1,155 once invoked), scanned A, original, MIT.

A workflow for carrying out an implementation plan by sending each task to a coding agent and reviewing the result in two stages: specification compliance and code quality.

In plain words
What is it for?
Use it when implementing a plan with separate coding and review agents, while tracking each task and checking only the changes made for that task.
Why use it?
It breaks a large plan into ordered tasks and adds a review after each one, making omissions and quality problems easier to catch.

Skill for Claude CodeCodex

Part of the superpowers-cc-to-codex plugin — 15 skills, 2 commands shipped together

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/mzored/superpowers-cc-to-codex/subagent-driven-development-codex
Any agent
npx skills add mzored/superpowers-cc-to-codex --skill subagent-driven-development-codex
Clone the repo
git clone --depth 1 https://github.com/mzored/superpowers-cc-to-codex

Made for: Claude Code, Codex.

Or install superpowers-cc-to-codex, the plugin that ships this one along with the rest of its 15 skills, 2 commands.

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-codex

README.md
[![agentmods](https://agentmods.dev/badge/skills/mzored/superpowers-cc-to-codex/subagent-driven-development-codex.svg)](https://agentmods.dev/skills/mzored/superpowers-cc-to-codex/subagent-driven-development-codex)
Your own site
<a href="https://agentmods.dev/skills/mzored/superpowers-cc-to-codex/subagent-driven-development-codex"><img src="https://agentmods.dev/badge/skills/mzored/superpowers-cc-to-codex/subagent-driven-development-codex.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,155 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 $0.00036 $0.01155
Opus 5 $0.00018 $0.00577
Sonnet 5 $0.00007 $0.00231
Haiku 4.5 $0.00004 $0.00115

Measured 5d ago against content hash 6733efe751ec, 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-codex 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 5d 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-codex/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent-Driven Development

Execute plan by calling codex_implement per task via the MCP tool, with two-stage review after each: Claude-side spec compliance first, then codex_review for code quality.

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

Checklist

You MUST create a task for each plan task and complete them in order.

Setup:

  1. Read plan — read the plan file once, extract all tasks with full text and context
  2. Create TodoWrite — one entry per plan task

Per task:

  1. Capture task base — before dispatching the implementer, record the current revision:
TASK_BASE_SHA="$(git rev-parse HEAD)"

Substitute the captured TASK_BASE_SHA value as the structured review base for this task, so the reviewer inspects only the task's delta rather than all prior tasks.

  1. Dispatch implementer — call the codex_implement MCP tool. Pass the task description as the prompt:
{
  "tool": "codex_implement",
  "arguments": {
    "taskId": "task-17",
    "prompt": "Implement Task 3 from docs/superpowers/plans/2026-04-03-agent-forwarding.md. Keep the work scoped to agents/codex-implementer.md and tests/prompt-contracts/execution-workflows.test.mjs.",
    "workspaceRoot": "/absolute/path/to/your/repo"
  }
}
  1. Handle status — see Status Handling below
  2. Spec compliance review — Claude reads the actual code and verifies against spec using spec-review-template.md; if issues remain, resume the same implementer thread with codex_resume:

Read the full file on GitHub · 124 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. 5d ago First seen · 124 lines · 36 tokens per session scan A 6733efe751ec

Subscribe to this mod's changes

subagent-driven-development-codex is a skill published in the GitHub repository mzored/superpowers-cc-to-codex (7 stars, last pushed 4mo ago), licensed MIT. It adds 36 tokens to every session and 1,155 once invoked, about $0.0002 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

claude-code-session-broker

Use when running Arcgentic V2 in Claude Code and fixed Planner, Developer, and Auditor role sessions must be coordinated through a broker.

Arch1eSUN/Arcgentic · 35 tokens

arcgentic

Use when the user says Arcgentic, asks to use Arcgentic, or wants an idea taken through a complete plan → development → self-audit → external audit workflow in Codex.

Arch1eSUN/Arcgentic · 43 tokens

espalier-migrate

Migrate an existing harness/espalier install to the current Espalier version — auto-detects which of v0.1→v0.2, v0.3→v0.4, v0.4→v0.5, the v0.5.3 coder-agent patch, v0.5→v0.6 (Stage 1 grill), v0.6→v0.7 (read-only /espalier-ask lane), v0.7→v0.8 (requirements approval gate), the v0.8.1 impact-analysis agent patch, the…

Junhanliu-dev/espalier-engineering · 0 tokens

verify-gates

Runs the mechanical quality gates that the arcgentic state machine requires for state transitions. Invoked indirectly by transition.sh OR directly by orchestrator agent before declaring a state transition. Use when about to call transition.sh OR when manually verifying that a round artifact meets the gate criteria.…

Arch1eSUN/Arcgentic · 75 tokens

session-mode

Use when a project has not yet stored session mode, when a user asks for complete arcgentic workflow execution, or when role identity handoff prompts are needed.

Arch1eSUN/Arcgentic · 36 tokens

cross-session-handoff

Read, write, snapshot, and lock .arcgentic/state.yaml across planner, dev, audit, and optional test sessions.

Arch1eSUN/Arcgentic · 31 tokens