Instructions for using the Codex command-line tool to have OpenAI Codex analyze, refactor, or edit code automatically.

Use them when running Codex from a terminal with commands such as codex exec or codex resume.

They define how to choose a model and reasoning level, select safe sandbox settings, and assemble commands for coding tasks.

codex — Skill for Claude Code and Codex by ondrej-svec

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.

Any agent

npx skills add ondrej-svec/heart-of-gold-toolkit --skill codex

Clone the repo

git clone --depth 1 https://github.com/ondrej-svec/heart-of-gold-toolkit

Made for: Claude Code, Codex.

Or install guide, the plugin that ships this one along with the rest of its 7 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/codex/github.svg)](https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/codex)

Your own site

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/codex"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/codex/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/ondrej-svec/heart-of-gold-toolkit/codex"><img src="https://agentmods.dev/badge/skills/ondrej-svec/heart-of-gold-toolkit/codex.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,691 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Excessive Agency · line 85
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00038	$0.01691
Opus 5.5	$0.00015	$0.00676
Sonnet 5.5	$0.00008	$0.00338
Haiku 4.5	$0.00004	$0.00169

Measured 2mo ago against content hash 3bce8ba4446f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 2mo 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.

plugins/guide/skills/codex/SKILL.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex CLI Skill Guide

Available Models

Model	Best for
`gpt-5.5`	Flagship (released 2026-04-23) — complex coding, computer use, knowledge work, research workflows. ChatGPT sign-in only — not available with API-key auth. Fall back to `gpt-5.4` if not in the user's model picker yet.
`gpt-5.4`	Professional coding with strong reasoning + tool use. Default fallback when `gpt-5.5` is unavailable.
`gpt-5.4-mini`	Faster/cheaper for lighter coding tasks and subagents
`gpt-5.3-codex`	Complex software engineering with industry-leading coding capabilities
`gpt-5.3-codex-spark`	Near-instant real-time coding iteration (ChatGPT Pro research preview)

Default recommendation: gpt-5.5 for complex tasks (with gpt-5.4 fallback), gpt-5.4-mini for speed.

Running a Task

Ask the user (via AskUserQuestion) which model to use (default: gpt-5.5, fallback gpt-5.4) AND which reasoning effort (xhigh, high, medium, or low) in a single prompt with two questions.
Select the sandbox mode required for the task; default to --sandbox read-only unless edits or network access are necessary.
Assemble the command with the appropriate options:
- -m, --model <MODEL>
- --config model_reasoning_effort="<xhigh|high|medium|low>"
- --sandbox <read-only|workspace-write|danger-full-access>
- --full-auto
- -C, --cd <DIR>
- --skip-git-repo-check
- "your prompt here" (as final positional argument)
Always use --skip-git-repo-check.
IMPORTANT: By default, append 2>/dev/null to all codex exec commands to suppress thinking tokens (stderr). Only show stderr if the user explicitly requests to see thinking tokens or if debugging is needed.
Run the command, capture stdout/stderr (filtered as appropriate), and summarize the outcome for the user.
After Codex completes, inform the user: "You can resume this Codex session at any time by saying 'codex resume' or asking me to continue."

Read the full file on GitHub · 94 lines

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.

2mo ago First seen · 94 lines · 38 tokens per session scan A 3bce8ba4446f

Subscribe to this mod's changes

codex is a skill published in the GitHub repository ondrej-svec/heart-of-gold-toolkit (19 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 1,691 once invoked, about $0.0002 per session on Opus 5.5. 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.

Building agents

codex next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
codexondrej-svec/heart-of-gold-toolkit	Skill	19	1mo ago	MIT	A	38	Claude Code, Codex
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code