Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/sologuy/chatgpt-web-handoffnpx agentmods add skills/sologuy/chatgpt-web-handoff/chatgpt-image-genWrote 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.
[](https://agentmods.dev/skills/sologuy/chatgpt-web-handoff/chatgpt-image-gen)<a href="https://agentmods.dev/skills/sologuy/chatgpt-web-handoff/chatgpt-image-gen"><img src="https://agentmods.dev/badge/skills/sologuy/chatgpt-web-handoff/chatgpt-image-gen/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sologuy/chatgpt-web-handoff/chatgpt-image-gen"><img src="https://agentmods.dev/badge/skills/sologuy/chatgpt-web-handoff/chatgpt-image-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00076 | $0.01650 |
| Opus 5.5 | $0.00030 | $0.00660 |
| Sonnet 5.5 | $0.00015 | $0.00330 |
| Haiku 4.5 | $0.00008 | $0.00165 |
Grade A, and why
chatgpt-image-gen scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 14d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatGPT 出图
驱动 Chrome 里已经登录的 ChatGPT Web 生成图片，并把图直接取回本地文件。 不走 API、不需要 key —— 用的就是你自己那个账号的网页版额度。
CGIMG=
for root in "$HOME/.claude" "$HOME/.agents" "$HOME/.codex" "$HOME/.hermes"; do
if [ -x "$root/skills/chatgpt-image-gen/cgimg" ]; then
CGIMG="$root/skills/chatgpt-image-gen/cgimg"
break
fi
done
[ -n "$CGIMG" ] || { echo "请先在项目仓库运行 ./scripts/install.sh --skills image" >&2; exit 1; }
"$CGIMG" "一只橘猫蹲在旧书店的木梯上，午后阳光斜射进来" \
--style "写实摄影，浅景深" --aspect 3:2 --out ~/Desktop
返回 JSON，images[].path 就是落盘路径，另有尺寸、文件格式、大小与 SHA-256。
这是前台等待命令，生成时间受网页和账号状态影响。要审查文字或代码，用同仓的
chatgpt-handoff；本 Skill 可独立安装，不依赖另一个 Skill 的入口。
参数
| 参数 | 说明 |
|---|---|
prompt（位置参数） |
要画什么。尽量具体——主体、场景、光线、氛围都写上，含糊的描述容易让它反问 |
--style |
风格：写实摄影，浅景深 / 水彩 / 等距像素 / 胶片颗粒 … |
--aspect |
画面比例：16:9 / 3:2 / 1:1 / 9:16 |
--ref |
参考图，可重复。会先上传再出图 |
--note |
追加一句自定义要求，原样拼进提示词 |
--out |
输出目录或文件名，默认当前目录；不覆盖已有文件 |
--max |
最多保存几张，默认 4 |
--timeout |
等待上限秒数，默认 600 |
--interval |
轮询间隔秒数，默认 6 |
--keep-tab |
跑完不关标签页（想继续在网页上追改图时用） |
--allow-model-drift |
明确接受实测模型不在预期列表；不要为绕过报错自行加上 |
档位固定极高，没有参数可调。 出图这件事没有省额度的必要，来回调档反而多一次 账号级写操作，还可能和别的自动化撞车。
提示词是自动包装过的
你给的描述会被包成一句明确的出图指令，末尾固定加上：
直接出图，不要向我提问、不要先描述你打算怎么画。只要图。
这句不是客套。ChatGPT 对含糊的描述习惯先追问风格或尺寸，一问就卡在那儿， 自动化这边只能干等到超时。所以宁可把要求写死。
即便如此，描述太抽象时它仍可能反问。超时返回里会带 assistant_text。
先检查保留的会话：已经发出的任务可能仍在生成，不能把超时当作未发送而直接重投。
会不会打扰你
会在已有 Chrome 会话里新开本次任务的标签页，不主动把 Chrome 窗口提到前台。
浏览器内的标签选择仍可能变化。成功时只关闭本次新页；加 --keep-tab 可保留。
失败时保留已经创建的本次页面，返回 page_id 和已知的 conversation_url，便于核查。
出错怎么办
| 情况 | 含义 | 怎么办 |
|---|---|---|
send_unknown |
已跨发送边界，未确认结果 | 检查保留页面，不要直接再执行 cgimg，避免重复生成 |
timeout |
已发送，尚未取得完整图片 | 读取 assistant_text 并检查保留会话；可能仍在生成，不能据此重投 |
image_download_failed |
部分或全部图片取回/写盘失败 | 保留 images 中已成功的文件，核对 failed_images，从现有会话取图，不能重新生成冒充重试下载 |
ref_not_found |
参考图路径不对 | 改路径。这一步在开浏览器之前就查，不浪费一轮 |
output_exists / output_type |
输出文件已存在或扩展名不支持 | 换输出路径，保留已有文件 |
auth_required |
ChatGPT 掉登录了 | 去原浏览器登录后再执行 |
model_changed / effort_not_found |
模型或档位不符 | 报出实测值，不静默降档；明确接受新模型后才可用 --allow-model-drift |
browser_busy / effort_drifted |
本次未发送，另一入口占锁或档位变化 | 核对未发送状态后可重试 |
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.
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.
- 14d ago First seen · 107 lines · 76 tokens per session scan A 19825064534d
chatgpt-image-gen is a skill published in the GitHub repository sologuy/chatgpt-web-handoff (2 stars, last pushed 2d ago), licensed MIT. It adds 76 tokens to every session and 1,650 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-23.
chatgpt-image-gen compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chatgpt-image-gensologuy/chatgpt-web-handoff | Skill | 2 | 2d ago | MIT | A | 76 | Claude Code, Codex |
| simplify-codeNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 14 | Claude Code, Codex |
| requesting-code-reviewNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 20 | Claude Code, Codex |
| pr-lensNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 15 | Claude Code, Codex |
| opencodeNousResearch/hermes-agent | Skill | 261k | today | MIT | A | 15 | Claude Code, Codex |
| security-reviewasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 15 | Claude Code |
| code-reviewasgeirtj/system_prompts_leaks | Skill | 71k | today | CC0-1.0 | A | 230 | Claude Code |