codexbox

A way to run the OpenAI Codex command-line tool inside a networked container called aicodebox. It provides an interactive shell, one-off commands, file operations, prompt runs, and an OpenAI-compatible chat API.

In plain words
What is it for?
Opening a shell, executing single commands, reading or syncing workspace files, starting synchronous or asynchronous prompt runs, polling runs by ID, and connecting through the compatible chat-completions endpoint.
Why use it?
It makes Codex available through several interfaces, including remote HTTP requests and workspace file synchronization.

Skill for Claude CodeCodex

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 skills/psyb0t/docker-codexbox/codexbox
Any agent
npx skills add psyb0t/docker-codexbox --skill codexbox
Clone the repo
git clone --depth 1 https://github.com/psyb0t/docker-codexbox

Made for: Claude Code, Codex.

Per session 203 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin unknown 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 $0.00203 $0.04786
Opus 5 $0.00102 $0.02393
Sonnet 5 $0.00041 $0.00957
Haiku 4.5 $0.00020 $0.00479

Measured today against content hash 988937d6113a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codexbox scanned grade A 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 today.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

{ "openclaw": { "emoji": "🧑‍💻", "primaryEnv": "CODEXBOX_URL", "requires": { "bins": ["docker", "curl"] } } }
.agents/skills/codexbox/SKILL.md · 313 lines

The source is not reproduced here

Licensed WTFPL

The repository is licensed WTFPL, which this catalogue does not treat as permission to reproduce the file. Read it at the source.

Read it on GitHub

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. today First seen · 313 lines · 203 tokens per session scan A 988937d6113a

Subscribe to this mod's changes

codexbox is a skill published in the GitHub repository psyb0t/docker-codexbox (0 stars, last pushed 18d ago), licensed WTFPL. It adds 203 tokens to every session and 4,786 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.