Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add aurolabs-ai/claude-chatgpt-bridge/plugin install chatgpt-bridgeWrote 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/aurolabs-ai/claude-chatgpt-bridge/launch-bridge)<a href="https://agentmods.dev/skills/aurolabs-ai/claude-chatgpt-bridge/launch-bridge"><img src="https://agentmods.dev/badge/skills/aurolabs-ai/claude-chatgpt-bridge/launch-bridge/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/aurolabs-ai/claude-chatgpt-bridge/launch-bridge"><img src="https://agentmods.dev/badge/skills/aurolabs-ai/claude-chatgpt-bridge/launch-bridge.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 | $0.00061 | $0.01948 |
| Opus 5 | $0.00030 | $0.00974 |
| Sonnet 5 | $0.00012 | $0.00390 |
| Haiku 4.5 | $0.00006 | $0.00195 |
Grade A, and why
launch-bridge 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 11d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Launch ChatGPT bridge
You take over a dialogue in the macOS ChatGPT app and iterate with ChatGPT autonomously until there is a concrete deliverable — a decision committed, a file written, a plan with sourced numbers, a falsified hypothesis. The user does NOT want to be asked questions mid-loop. The user does NOT want a long summary of what was discussed. The user wants a finished thing.
User input: $ARGUMENTS
Parse it as either:
<share-url> <goal>— read existing thread from the share URL, then continue the dialogue in the app (user has the same thread open in ChatGPT)<goal>— no share URL; use the app's current thread as-is
If $ARGUMENTS is empty or unclear: do NOT ask. Read the existing thread (cgpt-read-app + optionally cgpt-read-share), infer the most plausible concrete goal from context, state it once for yourself in your reasoning, and proceed. Better to commit to a wrong-but-concrete goal and adjust mid-loop than to bounce control back to the user.
Tools
Plugin bin/ is on PATH:
| Command | Purpose |
|---|---|
cgpt-read-share <url> |
Pull a public share-link transcript as {role, text} messages. Use for user-side history (the app's Accessibility tree doesn't expose user messages). |
cgpt-read-app |
Read current ChatGPT window via Accessibility. Returns assistant-side messages + input field value. Use after every cgpt-wait-idle. |
cgpt-send "<msg>" |
Paste into ChatGPT input + click send. |
cgpt-attach <file> ["caption"] [--no-send] |
Attach a file to the input via pasteboard (drag-from-Finder behavior), with optional caption text and optional skip-send. Use for screenshots, PDFs, code files, images. |
cgpt-wait-idle [--timeout 120] |
Block until ChatGPT finishes generating. Call immediately after every cgpt-send or cgpt-attach (when sent). |
You also have all your normal Claude Code tools — Bash, Read, Grep, Glob, WebFetch, etc. Use them aggressively between turns. See "Verification" below.
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.
- 11d ago First seen · 117 lines · 61 tokens per session scan A 78cc6481558f
launch-bridge is a skill published in the GitHub repository aurolabs-ai/claude-chatgpt-bridge (5 stars, last pushed 3mo ago), licensed MIT. It adds 61 tokens to every session and 1,948 once invoked, about $0.0003 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 2026-08-31.
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…