codex-do

A command for sending a clearly defined implementation task to the OpenAI Codex coding agent, an AI tool that can make code changes.

In plain words
What is it for?
Boilerplate generation, writing tests for existing code, migration scripts, file-format conversions, and focused edits in one file or a small area.
Why use it?
It helps hand off repetitive or well-scoped work with a precise description of the files, requirements, constraints, and completion criteria.

Command

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 commands/arystos/skill-codex/codex-do
Clone the repo
git clone --depth 1 https://github.com/Arystos/skill-codex
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 549 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 $0.00549
Opus 5 $0.00000 $0.00275
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured 2d ago against content hash b4076627732e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-do 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.

commands/codex-do.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Delegate Task to Codex

Delegate a well-scoped implementation task to Codex.

Instructions

You are delegating an implementation task to Codex. Follow these steps:

  1. Parse the task from $ARGUMENTS. If the argument is vague or missing, ask the user to be more specific before proceeding.

  2. Evaluate if the task is suitable for delegation:

    • Good for Codex: repetitive bulk changes, boilerplate generation, test writing for existing code, migration scripts, file format conversions, well-defined single-file edits
    • Keep for yourself: architectural decisions, cross-module refactoring, tasks requiring deep conversation context, ambiguous requirements, and trivial edits you'd finish faster yourself than you can write a spec for
    • If the task is poorly scoped, explain why and suggest how to break it down.
  3. Prepare a precise, self-contained prompt for Codex. Include:

    • Exact file paths to create or modify
    • The specific change required with examples if helpful
    • Constraints (language, framework, coding style, naming conventions)
    • What "done" looks like
  4. Call the codex_exec MCP tool with:

    • prompt: the prepared prompt
    • mode: "full-auto"
    • requireGit: true
  5. Review Codex's output critically:

    • Run git status --short first to see ALL changes, including newly-created files (lines starting with ??). Codex in full-auto mode often creates new files, and git diff alone is blind to untracked files.
    • Run git diff for modifications to tracked files, and read any new untracked files directly to review their contents.
    • Check for introduced bugs, regressions, or style violations
    • Verify it matches the requested changes
    • Verify it doesn't modify files outside the requested scope
  6. Present the result with your assessment:

    • What was done correctly
    • What needs adjustment
    • Apply changes only if they pass your review
    • If issues found, offer to fix them yourself or re-delegate with refined instructions

Read the full file on GitHub · 46 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.

  1. 2d ago First seen · 46 lines · 0 tokens per session scan A b4076627732e

Subscribe to this mod's changes

codex-do is a command published in the GitHub repository Arystos/skill-codex (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 549 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.