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/adamallcock/codex-chatgpt-controlnpx agentmods add skills/adamallcock/codex-chatgpt-control/chatgpt-delegateWrote 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/adamallcock/codex-chatgpt-control/chatgpt-delegate)<a href="https://agentmods.dev/skills/adamallcock/codex-chatgpt-control/chatgpt-delegate"><img src="https://agentmods.dev/badge/skills/adamallcock/codex-chatgpt-control/chatgpt-delegate/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/adamallcock/codex-chatgpt-control/chatgpt-delegate"><img src="https://agentmods.dev/badge/skills/adamallcock/codex-chatgpt-control/chatgpt-delegate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 19 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00044 | $0.01523 |
| Opus 5 | $0.00022 | $0.00762 |
| Sonnet 5 | $0.00009 | $0.00305 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
chatgpt-delegate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ChatGPT Delegate
Use this skill for outcome-oriented delegation to the visible ChatGPT product. Choose Chat for a conversational answer or review. Choose Work for a longer task with progress, steering, files, or deliverable artifacts. Use the official Codex SDK or CLI—not this skill—for repository editing, terminal execution, sandboxing, and code deployment.
This is a workflow over the codex-chatgpt-control plugin. It operates visible UI only and must not call private ChatGPT endpoints, inspect credentials or browser storage, bypass login or confirmation, or submit sensitive material without the user's approval.
Runtime Loader
Resolve relative paths from this SKILL.md. Load the plugin-bundled runtime:
const loaderUrl = new URL(
"../../runtime/import-chatgpt-control.mjs",
"file:///absolute/path/to/plugins/codex-chatgpt-control/skills/chatgpt-delegate/SKILL.md"
);
const { importChatGPTControl } = await import(`${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.
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.
- 9d ago First seen · 184 lines · 44 tokens per session scan A fd2405cca051
chatgpt-delegate is a skill published in the GitHub repository adamallcock/codex-chatgpt-control (396 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,523 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…