agentmods.dev

codex-studio AGENTS.md

Repository-specific guidance for agents working on Codex Studio, a local application for creating and managing generated content.

In plain words
What is it for?
Use it when setting up the project, understanding its structure, or deciding how settings, providers, recipes, and diagnostics should be handled.
Why use it?
It gives agents the project's terminology, architecture, setup rules, and required checks so their changes fit the repository.

Instructions file for CodexOpenCode

12 3d ago A scan 1,173 tokens original MIT
View the source file gvastethecreator/codex-studio
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 instructions/gvastethecreator/codex-studio/agents-md
Clone the repo
git clone --depth 1 https://github.com/gvastethecreator/codex-studio

Made for: Codex, OpenCode.

Per session 1,173 This file is loaded in full into every session.
When invoked 1,173 The same file — it is already loaded in full.
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 $0.01173 $0.01173
Opus 5 $0.00587 $0.00587
Sonnet 5 $0.00235 $0.00235
Haiku 4.5 $0.00117 $0.00117

Measured 2d ago against content hash 8ba194b0ad6e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-studio AGENTS.md 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.

AGENTS.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Studio Agent Guide

This file is for agents that work in this repo. Vocabulary lives in CONTEXT.md. System shape lives in docs/ARCHITECTURE.md. Specialized workflows live in SKILLS.md.

Current direction

  • Codex Studio is Codex-first, local-first, and library-backed.
  • codex app-server is the interactive Codex Product Runtime.
  • Codex SDK or scripts are Codex Automation Surface only: audits, migrations, tests, and maintenance.
  • Generation Task and Generation Provider are separate concepts.
  • Recipe Modules must produce Generation Task Specs.
  • Providers compile specs into compact provider inputs.
  • Studio Settings are editable app preferences. Bootstrap Configuration and Provider Secrets stay outside SQLite-backed settings.
  • The top toolbar is the Command Center.
  • Heavy diagnostics, settings, provider internals, and visual effects must be Demand-Mounted Surfaces.

Setup / first run

If the user asks for setup, getting started, first run, or onboarding, or if the checkout is not initialized, use skills/codex-studio-setup/SKILL.md before ad hoc commands.

Setup agent flow:

  1. Read this guide, README.md, SKILLS.md, and skills/codex-studio-setup/SKILL.md.
  2. Inspect repo and app-owned runtime state without printing secrets:
    • git status --short
    • Bun can run repo scripts. Record tool metadata only when it helps diagnosis.
    • Codex Runtime Doctor status, app-server support, and selected executable. Record CLI metadata only when it helps diagnosis.
    • .env.local presence
    • Studio Library path and initialization state
    • /api/health and /api/codex/session when the server is reachable
  3. Run bun install only when dependencies are missing or stale enough to block setup.
  4. Run bun run studio:init when .env.local, the Studio Library, SQLite state, the default library, or the default workspace is missing.
  5. Start or make sure that the local runtime works with bun run dev when needed. Then make sure that the UI and backend are healthy.
  6. If ChatGPT auth is missing, stop. Ask the user to run codex login and choose ChatGPT. Do not claim setup is complete until that user-only step is done and you make sure that it works.
  7. Do not block setup on an exact Bun or Codex release when readiness, supported scripts, app-server support, and Local Codex Session are healthy.
  8. Close with one validation pass and a short readiness summary.

Read the full file on GitHub · 121 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 · 121 lines · 1,173 tokens per session scan A 8ba194b0ad6e

Subscribe to this mod's changes

codex-studio AGENTS.md is an instructions file published in the GitHub repository gvastethecreator/codex-studio (12 stars, last pushed 3d ago), licensed MIT. It adds 1,173 tokens to every session, about $0.0059 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 2026-08-30.

Creative and mediaDebuggingWriting and docsbuncodexcodex-clidesktopimage-genimage-generation
Related

Other instructions, from other repositories

atet AGENTS.md

Instructions for hraness/atet, a project described as: Local-first AI media generation and video editing toolkit for coding agents, with a Bun CLI, TypeScript SDK, MCP server, and Agent Skill.

hraness/atet · 1,949 tokens

codex-image-context-runtime AGENTS.md

Instructions for shixinnt/codex-image-context-runtime, covering agents.md, public boundary, runtime contract and changes.

shixinnt/codex-image-context-runtime · 286 tokens

openai-compatible-imagegen AGENTS.md

Instructions for Syh1906/openai-compatible-imagegen, covering agent instructions, project scope, package management, checks and module boundaries.

Syh1906/openai-compatible-imagegen · 1,225 tokens

pixeltamer-gpt-image-skill CLAUDE.md

Instructions for gabelul/pixeltamer-gpt-image-skill, covering claude.md — pixeltamer, what this is, architecture, how the skill works and the two backends.

gabelul/pixeltamer-gpt-image-skill · 1,899 tokens

comfyui_mcp AGENTS.md

Instructions for hybridindie/comfyui_mcp, covering agents.md, independent & harness-agnostic, project overview, tech stack and project structure.

hybridindie/comfyui_mcp · 4,166 tokens

open-nuyoah-skill AGENTS.md

Instructions for nuyoah-ai-works/open-nuyoah-skill, covering open-nuyoah-skill 仓库规则, 定位, 目录, skill 约束 and 修改与验证.

nuyoah-ai-works/open-nuyoah-skill · 536 tokens