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.
npx agentmods add instructions/mzored/superpowers-cc-to-codex/agents-mdgit clone --depth 1 https://github.com/mzored/superpowers-cc-to-codexWrote 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.
[](https://agentmods.dev/instructions/mzored/superpowers-cc-to-codex/agents-md)<a href="https://agentmods.dev/instructions/mzored/superpowers-cc-to-codex/agents-md"><img src="https://agentmods.dev/badge/instructions/mzored/superpowers-cc-to-codex/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.01234 | $0.01234 |
| Opus 5 | $0.00617 | $0.00617 |
| Sonnet 5 | $0.00247 | $0.00247 |
| Haiku 4.5 | $0.00123 | $0.00123 |
Grade A, and why
superpowers-cc-to-codex AGENTS.md 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- superpowers-cc-to-codex GEMINI.md — 92% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Overview
Claude Code plugin that forks seven Superpowers workflows for Codex-backed execution. Claude stays in control of the main thread; bounded work is delegated to the public codex CLI.
Setup
# Plugin users
/plugin marketplace add mzored/superpowers-cc-to-codex
/plugin install superpowers-cc-to-codex@superpowers-cc-to-codex
# Development
git clone https://github.com/mzored/superpowers-cc-to-codex
npm test
npm run doctor
Requirements
- Node.js 22+
codexCLI installed and authenticated (minimum version 0.111.0)git- Claude Code with plugin marketplace support
Commands
npm test # Node.js native test runner (node --test)
npm run doctor # Validate plugin installation and required CLIs
npm run check:upstream # Check upstream Superpowers fork drift
npm run validate:plugin # Validate Claude Code plugin structure
Architecture
Claude is the controller. Codex is a bounded worker.
User ↔ Claude (controller)
├─ skills/ → SKILL.md workflow + prompts/ sent to Codex
├─ scripts/mcp-server.mjs → MCP server (only transport, registered in plugin.json)
├─ scripts/ → codex-run.mjs is the ONLY Codex CLI adapter
├─ schemas/ → JSON schemas for Codex I/O contracts
└─ .claude/state/ → Task resume state (survives plugin updates)
Key Files
| File | Role |
|---|---|
scripts/mcp-server.mjs |
MCP server — only transport for Codex delegation |
scripts/codex-run.mjs |
Single adapter for all Codex CLI invocations |
scripts/lib/mcp-runtime.mjs |
Timeout, progress ticker, and cancellation for MCP requests |
scripts/lib/mcp-tool-definitions.mjs |
Typed schemas for the 7 MCP workflow tools |
scripts/lib/mcp-workspace.mjs |
Roots-aware workspace resolver |
scripts/lib/codex-jsonl.mjs |
Codex JSONL parser and implementer-result validators |
scripts/lib/codex-state.mjs |
Task state persistence (load/save) |
scripts/detect-codex.mjs |
Runtime detection of codex CLI binary |
.claude-plugin/plugin.json |
Plugin metadata, MCP server registration |
.claude-plugin/marketplace.json |
Marketplace configuration |
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.
- 5d ago First seen · 114 lines · 1,234 tokens per session scan A 98f10bc10296
superpowers-cc-to-codex AGENTS.md is an instructions file published in the GitHub repository mzored/superpowers-cc-to-codex (7 stars, last pushed 4mo ago), licensed MIT. It adds 1,234 tokens to every session, about $0.0062 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.
Other instructions, from other repositories
cc-multi-cli-plugin AGENTS.md
Instructions for greenpolo/cc-multi-cli-plugin, covering agents.md, what this is, the golden rule, the request chain and build & test.
agent-toolkit AGENTS.md
AGENTS.md instructions for DiUS/agent-toolkit, covering agents.md, what this repo is, repo map, principles and how to add each component type.
agentic-tech-debt AGENTS.md
AGENTS.md instructions for bcanfield/agentic-tech-debt: The agent instructions for this repo live in CLAUDE.md — one source of truth for every coding agent. Read it and follow it as written; it applies to Codex exactly as it does to Claude Code.
zuvo CLAUDE.md
Claude Code instructions for greglas75/zuvo, covering zuvo plugin — project guide, what this repo is, tech stack, how to update after making changes and for yourself (dev testing, no marketplace push).
ultrapowers AGENTS.md
Instructions for 7xuanlu/ultrapowers, covering what this repo is, the discipline bar (eat our own dog food), verification commands, things that are load-bearing, do not casually change and editing the engine, footguns.
ultrapowers CLAUDE.md
Instructions for 7xuanlu/ultrapowers, covering workflow, the engine and command are the product, treat them as such, after any edit and distribution.