codex-vscode

codex-vscode is a skill for Claude Code, Codex from JunMystery/Agent-Guidance-Python. It costs 60 tokens per session (477 once invoked), scanned A, original, MIT.

A guide for configuring OpenAI Codex, an AI coding assistant, in VS Code and similar editors. It explains which project instruction files Codex reads and how to connect those instructions to repository standards.

In plain words
What is it for?
Use it to add or update AGENTS.md instructions, support nested workspaces, and align Codex with project standards when working in VS Code, Cursor, or Windsurf.
Why use it?
It prevents Codex from missing project rules or using the wrong instruction file. It also helps diagnose why guidance works in one workspace but not another.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions AGENTS.md; mentions Codex.

Good fit Use it to add or update AGENTS.md instructions, support nested workspaces, and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/junmystery/agent-guidance-python/codex-vscode
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 JunMystery/Agent-Guidance-Python --skill codex-vscode
Clone the repo
git clone --depth 1 https://github.com/JunMystery/Agent-Guidance-Python

Made for: Claude Code, Codex.

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-vscode

README.md
[![agentmods](https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/codex-vscode.svg)](https://agentmods.dev/skills/junmystery/agent-guidance-python/codex-vscode)
Your own site
<a href="https://agentmods.dev/skills/junmystery/agent-guidance-python/codex-vscode"><img src="https://agentmods.dev/badge/skills/junmystery/agent-guidance-python/codex-vscode.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 477 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.
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 $0.00060 $0.00477
Opus 5 $0.00030 $0.00238
Sonnet 5 $0.00012 $0.00095
Haiku 4.5 $0.00006 $0.00048

Measured 6d ago against content hash dd614d4bc1f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

codex-vscode 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 6d 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.

skills/codex-vscode/SKILL.md · 38 lines

What it actually says

Codex VS Code

Use this skill to make OpenAI Codex follow the repository standards when it runs from VS Code, Cursor, Windsurf, or another VS Code-compatible IDE.

What to Apply

  • Prefer AGENTS.md as the Codex project instruction file.
  • Keep Codex instructions short and link to standards files instead of duplicating the whole framework.
  • Put AGENTS.md at the project root so Codex can auto-discover it for the workspace.
  • For nested workspaces, check for closer AGENTS.md files before editing files in subdirectories.
  • Keep task-specific guidance on-demand through SKILL-REFERENCE.md and skills/.
  • When installing this framework into another project, copy AGENTS.md together with the other root instruction files and rewrite links with scripts/setup.py.

VS Code Notes

  • Treat Codex in VS Code as the same coding agent workflow as Codex CLI: it can inspect the repo, edit files, and run checks subject to approvals and sandbox settings.
  • Do not use .instructions.md for Codex-specific guidance; that file is for VS Code Copilot.
  • Use AGENTS.md for shared Codex behavior and PROJECT-STANDARDS.md for project-local rules that all agents should honor.
  • If the user is configuring a VS Code fork, keep the guidance Codex-specific and avoid changing Cursor or Windsurf rules unless the request also affects those tools.

Reference Files

Output Expectation

State which instruction file Codex will load, what changed, and how to verify by asking Codex "What coding standards are you following?"

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. 6d ago First seen · 38 lines · 60 tokens per session scan A dd614d4bc1f0

Subscribe to this mod's changes

codex-vscode is a skill published in the GitHub repository JunMystery/Agent-Guidance-Python (2 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 477 once invoked, about $0.0003 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

frontmcp-setup

Use when starting, scaffolding, or organizing a FrontMCP project. Covers creating a new project (CLI scaffold or manual) for Node, Vercel, and other targets; standalone versus Nx-monorepo layout, naming conventions, generators, and dependency rules; composing multiple @App classes, ESM packages, and remote MCP servers…

agentfront/frontmcp · 176 tokens

apitap

ApiTap gives AI agents cheap access to web data through three layers.

n1byn1kt/apitap · 0 tokens

you-finance

Route finance questions to an existing local script, a new You.com Finance Research API call, or an MCP payment-aware fallback.

youdotcom-oss/agent-skills · 29 tokens

zia-look-up-rule-targets

Look up the shared 'who/where/when/what-device' fields that every ZIA rule resource scopes by — users, groups, departments, locations, locationgroups, urlcategories, devices, devicegroups, workloadgroups, labels, and timewindows — and return the IDs (or canonical strings) the rule API expects. Use this skill from…

zscaler/zscaler-mcp-server · 188 tokens

powerpoint-mcp

PowerPoint MCP Server skill for Windows presentation automation via a live PowerPoint desktop instance (COM/PIA). Use when an assistant needs rich MCP tools to create, open, build, format, and export PowerPoint (.pptx/.pptm) presentations — slides, shapes, text boxes, tables, native charts, images, audio, video…

sbroenne/mcp-server-powerpoint · 112 tokens