codex-sandbox

codex-sandbox is a skill for Claude Code, Codex from Filip-Podstavec/claude-leverage. It costs 75 tokens per session (1,668 once invoked), scanned B, original, MIT.

A setup helper for Codex CLI that writes per-project sandbox and approval settings to .codex/config.toml. Sandbox settings control where the agent may read or write, while approval settings control when it must ask permission.

In plain words
What is it for?
Use it when setting up Codex in a project or tightening permissions for production and continuous-integration environments.
Why use it?
It avoids configuring the same project permissions manually and makes development, production, or custom access rules explicit. Re-running it updates its own settings while preserving unrelated configuration.

Skill for Claude CodeCodex

Written for Claude Code and Codex: allowed-tools in frontmatter, but also reads ~/.codex or $CODEX_HOME. Also seen: mentions Claude Code; mentions AGENTS.md; mentions Codex.

Part of the claude-leverage plugin — 16 skills, 5 commands, 14 agents, 4 hooks shipped together

Good fit Use it when setting up Codex in a project or tightening permissions for production and continuous-integration environments.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/filip-podstavec/claude-leverage/codex-sandbox
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 Filip-Podstavec/claude-leverage --skill codex-sandbox
Clone the repo
git clone --depth 1 https://github.com/Filip-Podstavec/claude-leverage

Made for: Claude Code, Codex.

Or install claude-leverage, the plugin that ships this one along with the rest of its 16 skills, 5 commands, 14 agents, 4 hooks.

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.

agentmods badge for codex-sandbox

README.md
[![agentmods](https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/codex-sandbox.svg)](https://agentmods.dev/skills/filip-podstavec/claude-leverage/codex-sandbox)
Your own site
<a href="https://agentmods.dev/skills/filip-podstavec/claude-leverage/codex-sandbox"><img src="https://agentmods.dev/badge/skills/filip-podstavec/claude-leverage/codex-sandbox.svg" alt="Measured on agentmods" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,668 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00075 $0.01668
Opus 5 $0.00037 $0.00834
Sonnet 5 $0.00015 $0.00334
Haiku 4.5 $0.00007 $0.00167

Measured 8d ago against content hash e21814f3cccd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

codex-sandbox 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 8d 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.

Reads agent configuration directoriesmediumAgent snooping

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

- **Configure `~/.codex/config.toml` (global).** Global Codex config
skills/codex-sandbox/SKILL.md · 166 lines

How it starts

The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/codex-sandbox

What it does

Codex CLI runs each agent inside a sandbox with a configurable permission model (filesystem, network, dangerous commands). The defaults are conservative; per-project overrides live in .codex/config.toml at the project root.

This skill asks 3–5 questions, recommends a profile, and writes the file. Re-running on an already-configured project detects the managed block (marker comments) and offers update-in-place.

What lives in .codex/config.toml

The skill writes only the policy-relevant sections (and leaves room for the user to add unrelated config below):

# <!-- claude-leverage:codex-sandbox START -->
# Managed by /codex-sandbox. Edit between markers and re-run the skill
# to update; do not delete the markers.

[project_doc]
max_bytes = 32768                # explicit; matches Codex default

[sandbox]
mode = "<workspace-write | read-only | full>"

[approval]
mode = "<on-request | on-failure | never>"
# <!-- claude-leverage:codex-sandbox END -->

The pre-baked profiles

Profile Sandbox Approval Use for
dev workspace-write on-request Local development. Agent can write inside the project but asks before risky actions (network, package install, shell commands outside cwd).
prod read-only never Production / CI runs. Agent can only read; any write requires running outside the sandbox.
custom (asks) (asks) Anything else; skill walks you through each field.

There is deliberately no staging profile: Codex config exposes no audit-log field, so a "staging" tier would differ from dev / prod in name only. For CI, use dev (keeps approvals) or prod (read-only sandbox); pipe Codex's stderr to your log aggregator if you need an audit trail.

Field names below are what Codex currently documents. If the spec evolves, this skill will need a refresh — /stack-check does not yet verify Codex spec freshness (v1.1 candidate).

Workflow

Read the full file on GitHub · 166 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. 8d ago First seen · 166 lines · 75 tokens per session scan B e21814f3cccd

Subscribe to this mod's changes

codex-sandbox is a skill published in the GitHub repository Filip-Podstavec/claude-leverage (68 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,668 once invoked, about $0.0004 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 2026-08-30.

Related

Other skills, from other repositories

OCR Review-to-Approval Loop

Drive a PR to an approved code review by looping OCR's multi-agent review and address steps. Runs /ocr:review then /ocr:address repeatedly until the review verdict is APPROVE, then one final /ocr:address for leftover suggestions, posting every review and every address round to the GitHub PR as comments. Use when the…

spencermarx/open-code-review · 178 tokens

repo-visuals

Create hero visuals — animated GIF, static PNG, or animated SVG — for GitHub repositories. Runs a structured discovery conversation (scan repo → recommend format → propose creative scenarios → agree on a brief), then designs bespoke HTML/SVG, previews it in the browser, and exports. Use when the user asks for a README…

livlign/claude-skills · 112 tokens

opik

This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…

comet-ml/opik-claude-code-plugin · 84 tokens

hyper-plan

Use when about to start a non-trivial implementation that needs decomposition before coding. Also when the user invokes /hyperclaude:hyper-plan. Produces an ordered, bite-sized plan in .hyperclaude/plans/ — the input for /hyperclaude:hyper-plan-review and /hyperclaude:hyper-implement.

zeikar/hyperclaude · 70 tokens

swarm

Run a multi-agent audit of a codebase by spawning specialized parallel subagents (security, performance, tests, architecture, dead-code), then synthesize their findings into a single prioritized action plan. Use this whenever the user runs /swarm, asks to "audit the repo," "review this codebase," "find issues across…

Zintellix/Claude-Skills · 138 tokens

mcp-builder

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

composio-community/awesome-claude-plugins · 61 tokens