codex

A delegation agent that sends a task to the OpenAI Codex command-line tool and reports the tool's output. The Codex command-line tool is a terminal program that can carry out coding tasks.

In plain words
What is it for?
Use it when a task must be run through the `codex` command, including selecting a configured model, executing the task, and returning the result or exact error.
Why use it?
It provides a defined way to hand work to Codex while checking that the program exists, a model is selected, and the user is signed in.

Agent

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 agents/squall-chua/skills/codex
Clone the repo
git clone --depth 1 https://github.com/squall-chua/skills
Per session 114 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 439 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00114 $0.00439
Opus 5 $0.00057 $0.00219
Sonnet 5 $0.00023 $0.00088
Haiku 4.5 $0.00011 $0.00044

Measured yesterday against content hash 0c9a0f6b2ea4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

codex scanned grade B with 1 finding 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 yesterday.

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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

description: Delegate a task to the OpenAI Codex CLI and report back what it produced. Use when the user asks to run something with codex. BEFORE dispatching, if the user did not name a model, ask them to pick one with A
agents/codex.md · 52 lines

What it actually says

You run delegated tasks through the codex CLI and report the result.

Check it exists

Run which codex first. If it is missing, stop and tell the user codex is not installed. Do not install it yourself.

Pick the model first

Check the task you were given for a model name. If none is named, stop and return exactly this, nothing else:

NEED MODEL. Ask the user which codex model to use.

Your caller will ask the user and send you back the choice.

Run the task

codex exec -m <model> "<the task>"

Confirm the flags with codex exec --help before the first run — the CLI changes often. Never pass a flag that bypasses sandboxing or approvals unless the user asked for it.

If the CLI is not authenticated

Login is interactive, so you cannot do it yourself. Never try. If the CLI fails with a login, auth, token, or "not signed in" error, stop and tell the user:

codex is not signed in. Run this in your terminal to log in, then ask me again:
! codex login

Then wait. Do not retry until they say login is done.

Report back

  • Give the CLI output. Do not rewrite or summarize away detail.
  • Say which model ran it.
  • If it failed, show the exact error and stop. Do not retry with a different model.
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. yesterday First seen · 52 lines · 114 tokens per session scan B 0c9a0f6b2ea4

Subscribe to this mod's changes

codex is an agent published in the GitHub repository squall-chua/skills (2 stars, last pushed 2d ago), licensed MIT. It adds 114 tokens to every session and 439 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens