agentleFS
Sign inStart free
agentspace-soagentspace-so/agent-skills/gpt-image-2/SKILL.md

gpt-image-2

Skill15 starsChanged 6 months agoMITView on GitHub

Generate images with GPT Image 2 (ChatGPT Images 2.0) inside Claude Code, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no per-image billing. Supports text-to-image, image-to-image editing, style transfer, and multi-reference composition via the local Codex CLI. Triggers on "gpt image 2", "gpt-image-2", "ChatGPT Images 2.0", "image 2", or any explicit ask to generate or edit an image through the user's ChatGPT plan.

  • Installs packages

We split this skill into the rules it gives an agent

10 rules. 0 are common, 6 are distinctive, and 4 are very specific to this project.

  • 0

    Common

    Most of the 15 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 4

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not auto-trigger for a plain "generate an image" request if the user didn't specify this route.

    line 44
  2. Distinctive:

    Pass the user's prompt through raw: Do not translate, polish, or add style modifiers unless the user asked for it.

    line 71
  3. Very specific:

    Choose the output path: Default to ./image-<YYYYMMDD-HHMMSS>.png in the current working directory if the user didn't specify.

    line 72
  4. Distinctive:

    Deliver the image: After the script succeeds, display / attach the output file.

    line 73
  5. Distinctive:

    Do not switch routes without permission.

    line 78
  6. Distinctive:

    Do not rewrite the prompt unless asked.

    line 79
  7. Very specific:

    Do not imply this skill works without a local codex login and a valid ChatGPT subscription with image-generation entitlement.

    line 80
  8. Very specific:

    No environment variables are read.

    line 124
  9. Very specific:

    No network calls leave this skill.

    line 125
  10. Distinctive:

    Not a direct OpenAI API client.

    line 129

“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🪞 GPT Image 2 — Image Generation via Your ChatGPT Subscription

agentspace.so · GitHub

Generate images with GPT Image 2 (ChatGPT Images 2.0) inside your agent, using your existing ChatGPT Plus or Pro subscription — no separate OpenAI access, no Fal or Replicate tokens, no per-image billing.

Text-to-image, image-to-image editing, style transfer, and multi-reference composition. Runs entirely through the local codex CLI you're already logged into.

Heads up — this skill requires a ChatGPT Plus or Pro subscription plus the Codex CLI installed locally. If you have neither, you can use GPT Image 2 in the browser via RunComfy instead — hosted, no ChatGPT subscription or local install needed (RunComfy account required):

The rest of this document covers the local Codex CLI flow for agents whose user has a ChatGPT subscription.

Image: GPT Image 2 example — flat-color lobster repainted as a 1950s ukiyo-e woodblock print

Example output: a plain flat-color icon repainted via --ref in ukiyo-e style — composition preserved, rendering swapped, period-appropriate red seal added by the model unprompted.

When to trigger

Trigger when the user explicitly asks for GPT Image 2 via their ChatGPT subscription, for example:

  • "use GPT Image 2" / "use gpt-image-2" / "use ChatGPT Images 2.0"
  • "use Image 2" / "image 2 this"
  • attached a reference image and asked to remix / edit / restyle it

Do not auto-trigger for a plain "generate an image" request if the user didn't specify this route. If they did specify it, do not silently fall back to HTML mockups, screenshots, or a different image model.

How to invoke

A single bash script handles everything: runs codex exec with the right flags, then decodes the generated image from the persisted session rollout.

Text-to-image:

bash scripts/gen.sh \
  --prompt "<user's raw prompt>" \
  --out <absolute/path/to/output.png>

Image-to-image (reference flag is repeatable for multi-reference composition):

bash scripts/gen.sh \
  --prompt "<user's raw prompt, e.g. 'repaint in watercolor'>" \
  --ref /absolute/path/to/reference.png \
  --out <absolute/path/to/output.png>

Optional: --timeout-sec 300 (default 300).

Default behavior

  • Pass the user's prompt through raw. Do not translate, polish, or add style modifiers unless the user asked for it.
  • Choose the output path. Default to ./image-<YYYYMMDD-HHMMSS>.png in the current working directory if the user didn't specify.
  • Deliver the image. After the script succeeds, display / attach the output file. Do not stop at "done, see path X".
  • Text-heavy layouts are fine. Image 2 handles infographics and timeline prompts well. Do not preemptively warn just because a prompt has a lot of text.

Hard constraints

  • Do not switch routes without permission. If the user said "use GPT Image 2", do not substitute DALL·E, Midjourney, an HTML mockup, or a manual screenshot workflow.
  • Do not rewrite the prompt unless asked.
  • Do not imply this skill works without a local codex login and a valid ChatGPT subscription with image-generation entitlement.

Prerequisites

  1. codex CLI installed — brew install codex or see openai/codex.
  2. Logged in with a ChatGPT plan that includes Image 2 — codex login.
  3. python3 on PATH (ships with macOS; apt install python3 on Linux).

This skill does not grant image-generation capability on its own. It exposes the capability the user already has through their ChatGPT subscription.

Exit codes

codemeaning
0success — output path printed on stdout
2bad args
3codex or python3 CLI missing
4--ref file does not exist
5codex exec failed (auth? network? model?)
6no new session file detected
7imagegen did not produce an image payload (feature not enabled, quota, or capability refused)

On failure, name the layer in one sentence instead of dumping the full stderr at the user.

How it works

The codex CLI reuses the logged-in ChatGPT session and exposes an imagegen tool (gated behind the image_generation feature flag). The script:

  1. snapshots ~/.codex/sessions/ before the run
  2. runs codex exec --enable image_generation --sandbox read-only ... (with -i <file> for each reference image)
  3. diffs the sessions directory, then invokes scripts/extract_image.py to scan every new rollout JSONL for a base64 image payload (PNG / JPEG / WebP magic-header match)
  4. decodes the largest matching blob and writes it to --out

Two non-obvious flags other wrappers get wrong on codex-cli 0.111.0+:

  • --enable image_generation is required; the feature is still under-development and off by default.
  • --ephemeral must not be used — ephemeral sessions aren't persisted, so the image payload has nowhere to live.

Data handling

The script is narrowly scoped on purpose:

  • It reads only session rollout files created by its own codex exec invocation. The sessions directory is snapshotted before the call and diffed after, so any prior ~/.codex/sessions/* files (which may contain unrelated Codex conversations) are never touched, read, or transmitted.
  • It writes only two kinds of file: the output PNG at the caller's --out path, and short-lived mktemp logs that are auto-deleted on exit via a trap.
  • No environment variables are read. No credentials are requested. No other paths under ~/.codex/ are accessed.
  • No network calls leave this skill. The only outbound traffic is the one made by the codex CLI itself (to OpenAI, using the user's existing ChatGPT login) — this skill does not add endpoints, telemetry, or callbacks.

What this skill is not

Not a direct OpenAI API client. Not a capability grant — it depends on the user's working Codex CLI login. Not a multi-tenant service (one call per invocation; concurrent calls are serialized by the filesystem-snapshot diff).

Download now (ZIP)

  • Other versions26 projects use a version of this.

    Word for word · 2

    1. Bitslix/BLXCode★ 15100% same
    2. squarerf/claude-skills★ 1100% same

    Edited · 1

    1. cskwork/skills★ 257% same

    Wrote their own version · 23

    1. ConardLi/garden-skills★ 13ksame name
    2. ConardLi/web-design-skill★ 13ksame name
    3. glebis/claude-skills★ 404same name
    4. jiangmuran/claude-image★ 88same name
    5. robonuggets/gpt-image-2-skill★ 69same name
    6. pilioai/skills★ 43same name
    7. prime-skills/runcomfy-agent-skills★ 41same name
    8. genmedia-labs/skills★ 26same name
    9. JustinPerea/nebula-nodes★ 20same name
    10. AceDataCloud/Skills★ 17same name

    13 more not listed

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • Used alongsideProjects with it also use image-inpainting, flux-2-klein and 10 more.

    Other files people use alongside this one.

    Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
    • prime-skillsSkill

      image-inpainting

      Mask-driven image inpainting on RunComfy via the `runcomfy` CLI. Routes to Tongyi MAI Z-Image Turbo Inpainting (the dedicated inpainting endpoint with mask, strength, and control-scale) and to identity-preserving edit models (Nano Banana 2 Edit, GPT Image 2 Edit, FLUX Kontext Pro) when a mask isn't available and the region must be described instead. Use for object removal, watermark removal, region replacement, blemish cleanup, and any controlled local edit where a binary mask defines the target area. Triggers on "inpaint", "inpainting", "image inpaint", "remove from image", "fill region", "mask-driven edit", "remove watermark", "remove object", "patch the photo", "fill the hole", or any explicit ask to edit a specific masked region of a still.

      Also in 4 projects that use this

    • agentspace-soSkill

      flux-2-klein

      Generate images with Flux 2 Klein (Black Forest Labs' distilled fast variant of Flux 2) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux 2 Klein's strengths (sub-second latency, multi-reference brand styling, declarative subject-first prompts), the step-count strategy (4–8 for fast iteration, ~25 for polish), the 9B vs 4B variant trade-off, and when to route to Flux 2 Pro / Seedream 5 / GPT Image 2 instead. Calls `runcomfy run blackforestlabs/flux-2-klein/9b/text-to-image` (or `/4b/`) through the local RunComfy CLI. Triggers on "flux 2 klein", "flux-2-klein", "flux klein", "BFL flux 2", or any explicit ask to generate with this model.

      Also in 4 projects that use this

    • agentspace-soSkill

      flux-kontext

      Edit images with Flux 1 Kontext Pro (Black Forest Labs' precise local image-edit model) on RunComfy — bundled with the model's documented prompting patterns so the skill gets sharper output than naive prompting against the same model. Documents Flux Kontext's strengths (single-reference precise local edits, strong prompt control, consistent high-fidelity outputs), the schema (single image + prompt), and when to route to Nano Banana Edit / GPT Image 2 edit / Flux 2 Klein instead. Calls `runcomfy run blackforestlabs/flux-1-kontext/pro/edit` through the local RunComfy CLI. Triggers on "flux kontext", "flux-kontext", "flux 1 kontext", "kontext", "BFL kontext", or any explicit ask to edit with this model.

      Also in 4 projects that use this

    • prime-skillsSkill

      ace-step

      Generate, inpaint, and outpaint music with ACE Step on RunComfy via the `runcomfy` CLI. ACE Step is StepFun-AI's open-weights music foundation model — tag-driven composition (genre, mood, instruments), multilingual lyrics with section markers, 5 s to 4 min stereo output, $0.0002–0.0003 per second (≈ 27× cheaper than ElevenLabs Music). Four endpoints: ACE Step text-to-audio (the default), ACE Step 1.5 text-to-audio (50+ language lyrics, refined structured-lyric handling), ACE Step audio-inpaint (regenerate a time range inside an existing track), ACE Step audio-outpaint (extend an existing track before or after). Triggers on "ace step", "ace-step", "acestep", "ACE music", "open music model", "cheap AI music", "inpaint audio", "audio inpaint", "extend music", "audio outpaint", "lengthen track", "music with tags", or any explicit ask to generate or edit music with ACE Step.

      Also in 3 projects that use this

    • ConardLiSkill

      beautiful-article

      把用户提供的素材（网页 URL / PDF / DOCX / Markdown / 纯文本 / 截图 / 粘贴材料）编辑、设计成一篇美丽的、可离线打开和分享的**单文件 HTML 网页文章**。基于 reacticle 组件协议：不手写裸 HTML/CSS，而用语义组件 + 受主题约束的 Raw 自由层；按 source→规划→双确认→生成→终审→修复的小型 harness 流程推进，默认 100% 信息保留的长文。触发场景：把 URL/PDF/DOCX/文章做成网页文章 / 长文 / briefing / 解释文 / 视觉文章 / 教程 / 审阅复盘 / 方案分析，'render this as a beautiful web article / 把这篇做成网页文章 / 生成一篇可分享的 HTML 长文 / reacticle 文章'。只生成文章，不生成后台、表单、dashboard、产品原型或通用 Web App。

      Also in 3 projects that use this

    • +3 more from agentspace-so
    • +4 more from prime-skills

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free