scripts

A set of scripts that connects agents to the Codex command-line tool and manages task state and review scope.

In plain words
What is it for?
Use it to run Codex, detect the installed command, check supported capabilities, save task state, and determine which Git changes a review should cover.
Why use it?
It keeps Codex calls consistent and avoids separate agents starting the command-line tool or storing state in the wrong place.

Cursor rule for Cursor

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 rules/mzored/superpowers-cc-to-codex/scripts
Clone the repo
git clone --depth 1 https://github.com/mzored/superpowers-cc-to-codex

Made for: Cursor.

Per session 0 Nothing until a file matches its globs; then the whole rule loads.
When invoked 276 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 $0.00000 $0.00276
Opus 5 $0.00000 $0.00138
Sonnet 5 $0.00000 $0.00055
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash 8ace176b0cfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scripts 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 2d 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.

.cursor/rules/scripts.mdc · 32 lines

What it actually says

Scripts

Core runtime adapter and utilities for Codex CLI integration.

Key Files

File Role
codex-run.mjs Single adapter for ALL Codex CLI invocations
detect-codex.mjs Locates codex binary at runtime
lib/codex-state.mjs Task state load/save with optional/required variants
lib/codex-cli-contract.mjs CLI version and capability checks
lib/review-scope.mjs Git diff scope extraction for reviews

Conventions

  • codex-run.mjs is the ONLY file that spawns the codex process — all agents delegate through it
  • CLI entry detection: import.meta.url === \file://${process.argv[1]}``
  • Functions accept runner parameter for testability (dependency injection, no mocking library)
  • State files stored as .claude/state/codex/{taskId}.json — outside plugin root

Anti-Patterns

  • Calling codex CLI directly from agents or skills — always go through codex-run.mjs
  • Storing state inside the plugin directory tree
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. 2d ago First seen · 32 lines · 0 tokens per session scan A 8ace176b0cfa

Subscribe to this mod's changes

scripts is a cursor rule published in the GitHub repository mzored/superpowers-cc-to-codex (7 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 276 tokens. 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.