Geo Fundamentals
wasp-lang/wasp
Generative Engine Optimization for AI search engines (ChatGPT, Claude, Perplexity).
A skill your agent uses when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture…
MITAuto-check passed
Install Chatgpt Delegate
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegate --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .claude/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .claude/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegateType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .agents/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .agents/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .cursor/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .cursor/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/adamallcock/codex-chatgpt-control.git --path plugins/codex-chatgpt-control/skills/chatgpt-delegate--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .gemini/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .gemini/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegateInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .github/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .github/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install adamallcock/codex-chatgpt-control chatgpt-delegate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/adamallcock/codex-chatgpt-control.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/codex-chatgpt-control/skills/chatgpt-delegate .opencode/skills/chatgpt-delegate && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "chatgpt-delegate" agent skill from https://github.com/adamallcock/codex-chatgpt-control/tree/main/plugins/codex-chatgpt-control/skills/chatgpt-delegate into .opencode/skills/chatgpt-delegate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "chatgpt-delegate", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
chatgpt-delegate- GitHub stars
- 406
- Token cost
- ~1.7k tokens
- SKILL.md length
- 547 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture…
- Codex should delegate a visible
- SKILL.md covers Runtime Loader, Choose The Experience, Chat Delegation and Work Delegation, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- User-directed task to ChatGPT Chat
What it does
Chatgpt Delegate is an agent skill from adamallcock/codex-chatgpt-control. Use when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture, files, and artifacts.
Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It works with OpenAI. The repository describes itself as: Unofficial SDK for Codex agents controlling visible ChatGPT web sessions. The licence is MIT.
When your agent uses it
- Codex should delegate a visible
- User-directed task to ChatGPT Chat
- Including configuration discovery
- Long-running Work progress
Example prompts
- “/chatgpt-delegate”
What it can do on your machine
Read from SKILL.md and the folder at commit 1e50539. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are javascript).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Chatgpt Delegate loads about 1.7k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 547 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from adamallcock/codex-chatgpt-control at commit 1e50539, republished under its MIT licence (© adamallcock). 547 words, ~1,695 tokens.
Download SKILL.mdSave it as
.claude/skills/chatgpt-delegate/SKILL.md (or your agent's skills folder).- name
- chatgpt-delegate
- description
- Use when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture, files, and artifacts.
ChatGPT Delegate
Use this skill for outcome-oriented delegation to the visible ChatGPT product. Choose Chat for a conversational answer or review. Choose Work for a longer task with progress, steering, files, or deliverable artifacts. Use the official Codex SDK or CLI—not this skill—for repository editing, terminal execution, sandboxing, and code deployment.
This is a workflow over the codex-chatgpt-control plugin. It operates visible UI only and must not call private ChatGPT endpoints, inspect credentials or browser storage, bypass login or confirmation, or submit sensitive material without the user's approval.
Runtime Loader
Resolve relative paths from this SKILL.md. Load the plugin-bundled runtime:
const loaderUrl = new URL(
"../../runtime/import-chatgpt-control.mjs",
"file:///absolute/path/to/plugins/codex-chatgpt-control/skills/chatgpt-delegate/SKILL.md"
);
const { importChatGPTControl } = await import(`${loaderUrl.href}?t=${Date.now()}`);
const { createChatGPT } = await importChatGPTControl();
const chatgpt = createChatGPT({
agent: globalThis.agent,
reporting: { enabled: true, includeContent: false }
});If globalThis.agent is absent, use the bridge-bootstrap instructions in the broad codex-chatgpt-control skill. An ordinary-shell browser_bridge_unavailable result is expected and should be reported, not worked around.
Choose The Experience
chat: reviews, questions, synthesis, brainstorming, search-oriented answers, or continuing an existing conversation.work: longer research or production tasks that benefit from progress checks, steering, files, or artifacts.- official Codex: local code changes, commands, tests, branches, deployments, or repository-native agents.
Do not choose a surface solely from a model name. Availability varies by account, workspace, locale, and rollout. Inspect the visible capability graph and apply only controls that are actually present.
When the user requests Chat or Work, call experience.open for that surface
before inspecting configuration or submitting. Do not assume the currently
visible pane is the requested one. The SDK handles the current Chat/Work radio
selector and returning from an active Work task to the home selector, while
retaining compatibility fallbacks for older UI shapes.
const detected = await chatgpt.experience.detect();
const configuration = await chatgpt.configuration.inspect({
experience: detected.data?.experience === "unknown"
? undefined
: detected.data?.experience
});Chat Delegation
Use the runner for a visible Chat review:
const reviewer = chatgpt.agent({
name: "chatgpt-reviewer",
instructions: [
"Be critical, constructive, specific, and evidence-aware.",
"Call out assumptions, risks, and concrete next steps.",
"Return clear Markdown."
].join("\n"),
defaults: {
experience: "chat",
wait: false,
read: false,
report: { enabled: true, includeContent: false }
}
});
const submitted = await chatgpt.runner.run(reviewer, {
input: "Review this plan:\n\n...",
thread: { type: "new" },
experience: "chat",
configuration: { intelligence: "Pro" }
});The configuration is a visible preference, not a guaranteed underlying model identifier. Inspect the configuration sequence step and require verified: true before claiming that the requested setting was active. If the account does not expose that option, report the structured blocker and visible candidates.
For long answers, submit once and poll the same thread:
const progress = await chatgpt.messages.status({ maxPreviewChars: 500 });
const read = await chatgpt.messages.waitAndRead({
timeoutMs: 25_000,
stableMs: 1_500,
pollMs: 750,
role: "assistant",
format: "markdown"
});partial, completionState: "generating", or generationActive: true means the prompt may already be running. Never resubmit it blindly.
Show full SKILL.md (212 more words)Show less
Work Delegation
Start a fresh Work task with explicit, strictly verified configuration:
const started = await chatgpt.work.start({
prompt: "Research the options and produce a decision-ready implementation brief.",
newTask: true,
configuration: {
model: "GPT-5.6 Sol",
effort: "High",
speed: "Standard"
},
wait: false,
read: false
});newTask defaults to true. If an existing task is loaded and no unique new-task control can be verified, the SDK blocks rather than appending the prompt accidentally. Pass newTask: false only when intentionally continuing the currently visible Work task.
Poll without resubmission:
const status = await chatgpt.work.status({ includeArtifacts: true });
const waited = await chatgpt.work.wait({
timeoutMs: 25_000,
stableMs: 1_500,
pollMs: 750,
responseContent: "metadata"
});Steer the same task:
await chatgpt.work.steer({
prompt: "Prioritize the migration risks and add a two-week execution sequence.",
wait: false,
read: false
});Read the latest response and enumerate artifacts:
const latest = await chatgpt.work.readLatest({ format: "markdown" });
const artifacts = await chatgpt.work.artifacts.listLatest({});Use chatgpt.work.artifacts.wait(...) and downloadLatest(...) for visible downloadable deliverables. Attach only user-approved absolute host-local paths.
When the deliverable has a known filename, use the file workflow with an exact case-insensitive regular expression:
await chatgpt.files.downloadLatest({
destDir: "/absolute/output/dir",
filenamePattern: "^report\\.csv$"
});This supports direct file links and filename-labelled artifact previews. A filename mismatch is a blocker, not permission to accept another visible image or older file.
Compatibility
The legacy mode runner input, chatgpt.modes.set/get, and chatgpt-pro-consult skill still work for existing callers. New work should use experience plus configuration, because Chat and Work expose different nested axes and strict postcondition verification.
Blockers And Reporting
Stop and report:
browser_bridge_unavailablelogin_requiredcaptcharate_limitpermissionneeds_confirmationselector_drift
Preserve the SDK's real ok, status, warnings, blocker, error, steps, and task/thread reference. Do not wrap a failed result as success. Reports remain redacted by default.
Treat delegated output as another model's judgment, not verified truth. Verify current or high-stakes claims with primary sources.
© adamallcock, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/codex-chatgpt-control/skills/chatgpt-delegate of adamallcock/codex-chatgpt-control.
Open the folder on GitHubat commit 1e50539
Compare with similar skills
Chatgpt Delegate next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Chatgpt Delegate this skilladamallcock/codex-chatgpt-control | 406 | — | ~1.7k | Automated safety check: Pass | MIT | |
| Geo Fundamentalswasp-lang/wasp | 19k | 9 repos | ~861 | Automated safety check: Pass | MIT | |
| AI SDKvercel-labs/ai-facts | 168 | 20 repos | ~1.2k | Automated safety check: Pass | None | |
| AI Image Generation and Editingzhayujie/CowAgent | 47k | — | ~1.3k | Automated safety check: Pass | MIT | |
| PR Design DocOpenHands/OpenHands | 90k | — | ~2.4k | Automated safety check: Pass | MIT | |
| SEO GeoReScienceLab/opc-skills | 1.8k | 4 repos | ~2.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
AI SDK
vercel-labs/ai-facts
Answer questions about the AI SDK and help build AI-powered features.
AI Image Generation and Editing
zhayujie/CowAgent
Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.
PR Design Doc
OpenHands/OpenHands
For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…
SEO Geo
ReScienceLab/opc-skills
SEO & GEO (Generative Engine Optimization) for websites. An agent skill from ReScienceLab/opc-skills.
Open Code Review CLI
alibaba/open-code-review
Runs the ocr command-line tool to review Git changes, a commit or a branch comparison with an AI model, returning line-level comments and optionally applying fixes.
More from adamallcock/codex-chatgpt-control
Codex Chatgpt Control
adamallcock/codex-chatgpt-control
A skill your agent uses when Codex agents need to operate visible ChatGPT Chat or Work through the codex-chatgpt-control plugin, including verified configuration, prompts, tasks, progress, steering…
Codex Chatgpt Control
adamallcock/codex-chatgpt-control
A skill your agent uses when Codex agents need to operate visible ChatGPT Chat or Work through the codex-chatgpt-control SDK, including verified configuration, prompts, tasks, progress, steering…
Chatgpt Pro Consult
adamallcock/codex-chatgpt-control
Backward-compatible alias for a visible Chat consultation with the Pro intelligence setting; prefer chatgpt-delegate for new Chat or Work delegation workflows.
Related
Works with
Questions about Chatgpt Delegate
What does Chatgpt Delegate do?
A skill your agent uses when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture…. Chatgpt Delegate is an agent skill from adamallcock/codex-chatgpt-control. Use when Codex should delegate a visible, user-directed task to ChatGPT Chat or Work, including configuration discovery, long-running Work progress, steering, response capture, files, and artifacts.
When should I use Chatgpt Delegate?
Chatgpt Delegate fits situations like: Codex should delegate a visible; user-directed task to ChatGPT Chat; including configuration discovery; long-running Work progress.
How do I install Chatgpt Delegate in Claude Code?
Run `npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a claude-code`. Or copy the skill folder (plugins/codex-chatgpt-control/skills/chatgpt-delegate in adamallcock/codex-chatgpt-control) into .claude/skills/chatgpt-delegate in your project. Claude Code loads it when a task matches its description.
How do I install Chatgpt Delegate in Codex?
Run `npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a codex`. Or copy the skill folder (plugins/codex-chatgpt-control/skills/chatgpt-delegate in adamallcock/codex-chatgpt-control) into .agents/skills/chatgpt-delegate in your project. Codex loads it when a task matches its description.
Can I use Chatgpt Delegate in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add adamallcock/codex-chatgpt-control --skill chatgpt-delegate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/chatgpt-delegate, .gemini/skills/chatgpt-delegate, .github/skills/chatgpt-delegate and .opencode/skills/chatgpt-delegate in your project.
What does Chatgpt Delegate need to run?
SKILL.md names no scripts, command-line tools or credentials: Chatgpt Delegate is instructions for the agent only.
Does Chatgpt Delegate access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Chatgpt Delegate safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Chatgpt Delegate use?
Chatgpt Delegate is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Chatgpt Delegate use?
About 1.7k tokens (SKILL.md is roughly 6.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Chatgpt Delegate?
Skills that share tags, products or a category with Chatgpt Delegate: Geo Fundamentals (wasp-lang/wasp, 19k stars), AI SDK (vercel-labs/ai-facts, 168 stars), AI Image Generation and Editing (zhayujie/CowAgent, 47k stars) and PR Design Doc (OpenHands/OpenHands, 90k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Chatgpt Delegate?
adamallcock (a GitHub user) maintains it in adamallcock/codex-chatgpt-control, which has 406 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 4, 2026.
Source: adamallcock/codex-chatgpt-control on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.