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.
npx skills add Syysean/web-ai-skills --skill chatgpt-workergit clone --depth 1 https://github.com/Syysean/web-ai-skillsWrote 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/syysean/web-ai-skills/chatgpt-worker)<a href="https://agentmods.dev/skills/syysean/web-ai-skills/chatgpt-worker"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/chatgpt-worker/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/syysean/web-ai-skills/chatgpt-worker"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/chatgpt-worker.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 | $0.01568 |
| Opus 5.5 | $0.00030 | $0.00627 |
| Sonnet 5.5 | $0.00015 | $0.00314 |
| Haiku 4.5 | $0.00008 | $0.00157 |
Grade A, and why
chatgpt-worker 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 2mo 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 — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatGPT Worker
Send a prompt to ChatGPT via browser and return the response.
Environment
- URL: https://chatgpt.com
- Browser: Chrome on localhost:9222 (managed by local-browser-tools)
- Login: Required — session persisted in ~/.cache/browser-tools profile
- Tools:
browser-start.js,browser-nav.js,browser-eval.js,browser-screenshot.js
Input
prompt: string # The text to send to ChatGPT
task_type: string # qa | summary | translation | rewrite | extraction | comparison | brainstorming | analysis
Output
Always output this JSON block first:
{
"site": "chatgpt",
"task_type": "<task_type>",
"status": "success | partial | error",
"answer": "<extracted response text>",
"retry_count": 0,
"elapsed_ms": 0,
"error_reason": null
}
Then follow with a short human-readable summary (2–3 sentences max).
Critical Architecture Note
ChatGPT uses ProseMirror as its rich text editor. The real input element is a div.ProseMirror, NOT the <textarea> on the page. The textarea (wcDTda_fallbackTextarea) is a hidden accessibility fallback that React does not monitor for input. Writing to the textarea will never trigger the send button — it will always launch voice mode instead.
Workflow
Step 1 — Start browser
node ~/.pi/agent/skills/local-browser-tools/browser-start.js
Expected: ✓ Chrome already running on :9222 or ✓ Chrome started on :9222
If fails: return error status, stop.
Step 2 — Navigate to ChatGPT
node ~/.pi/agent/skills/local-browser-tools/browser-nav.js https://chatgpt.com
Take a screenshot and verify:
- Input area is visible
- Not showing a login wall
If login page appears: return error_reason: "login_required", stop.
Step 3 — Locate input box
ChatGPT's real input is a ProseMirror div, NOT a textarea.
Check:
!!document.querySelector('div.ProseMirror[contenteditable="true"]')
Fallback selectors in order:
div.ProseMirror[contenteditable="true"]div[role="textbox"][aria-label="Chat with ChatGPT"]div[contenteditable="true"][role="textbox"]
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.
- 2mo ago First seen · 226 lines · 76 tokens per session scan A a59190df03a3
chatgpt-worker is a skill published in the GitHub repository Syysean/web-ai-skills (16 stars, last pushed 5mo ago), licensed MIT. It adds 76 tokens to every session and 1,568 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 2026-08-31.
chatgpt-worker compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| chatgpt-workerSyysean/web-ai-skills | Skill | 16 | 5mo ago | MIT | A | 76 | Claude Code, Codex |
| patent-maphandsomestWei/patent-disclosure-skill | Skill | 13k | 2d ago | MIT | A | 48 | Claude Code |
| sandbaseiflytek/skillhub | Skill | 5.4k | yesterday | Apache-2.0 | A | 67 | Claude Code |
| convex-insightsopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 45 | Claude Code, Codex |
| openclaw-design-systemopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 37 | Claude Code, Codex |
| convex-addopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 81 | Claude Code, Codex |
| convex-seedopenclaw/clawhub | Skill | 9.5k | yesterday | MIT | A | 15 | Claude Code, Codex |