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 xiaojiou176-open/multi-ai-panel --skill agentganggang-compare-workflowsgit clone --depth 1 https://github.com/xiaojiou176-open/multi-ai-panelWrote 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/xiaojiou176-open/multi-ai-panel/agentganggang-compare-workflows)<a href="https://agentmods.dev/skills/xiaojiou176-open/multi-ai-panel/agentganggang-compare-workflows"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/multi-ai-panel/agentganggang-compare-workflows/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/xiaojiou176-open/multi-ai-panel/agentganggang-compare-workflows"><img src="https://agentmods.dev/badge/skills/xiaojiou176-open/multi-ai-panel/agentganggang-compare-workflows.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 | $0.00036 | $0.00583 |
| Opus 5 | $0.00018 | $0.00292 |
| Sonnet 5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
multi-ai-panel-compare-workflows 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 12d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MultiAiPanel Compare Workflows
Teach the agent how to install, connect, and use MultiAiPanel as a compare-first browser workspace.
Use this skill when
- the user wants to compare the same prompt across multiple already-open AI chat tabs
- the host can run a local MCP server
- the user wants one inspectable compare artifact before broader automation
What this package teaches
- how to wire the local MultiAiPanel MCP sidecar into a host
- which MCP tools are safe and useful first
- how to move from readiness checks to a real compare turn
- how to keep the workflow grounded in a browser-native compare product
Start here
- Read references/INSTALL.md
- Load the right host config from:
- Skim the tool surface in references/CAPABILITIES.md
- Run the demo from references/DEMO.md
Recommended workflow
multi-ai-panel.bridge_statusmulti-ai-panel.check_readinessmulti-ai-panel.comparemulti-ai-panel.analyze_comparemulti-ai-panel.run_workflow
Suggested first prompt
Use MultiAiPanel to compare the prompt below across the ready ChatGPT and
Gemini tabs. Start with multi-ai-panel.bridge_status and
multi-ai-panel.check_readiness. If fewer than two model tabs are ready,
stop and tell me exactly which login or tab-prep step is missing. If two or
more tabs are ready, run multi-ai-panel.compare and summarize the most
important wording differences.
Success checks
- the host can launch the MCP server from the provided config
bridge_statusconfirms the local bridge is reachablecheck_readinessidentifies which tabs are readycompareproduces a real session/turn artifact the agent can inspect
Boundaries
- MultiAiPanel stays a local browser workflow, not a hosted service
- the MCP sidecar supports compare workflows; it does not replace the extension
- keep claims grounded in the actual tool surface documented in this package
What ships with it
9 files 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.
- 12d ago First seen · 69 lines · 36 tokens per session scan A 360b02606d9a
multi-ai-panel-compare-workflows is a skill published in the GitHub repository xiaojiou176-open/multi-ai-panel (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 583 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 2026-08-31.
Other skills, from other repositories
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
extension-dev
Detect Chrome extension framework/stack, find proper docs, implement features, and debug across service worker, content script, and popup contexts.
extension-analyze
Audit Chrome extensions for security issues, best practice violations, performance problems, and CWS compliance. Scans manifest, code, CSP, message handlers, storage, and dependencies.
extension-create
Auto-scaffold Chrome extensions with WXT or CRXJS. Ask user for name/features, scaffold, configure entrypoints. Use when: create extension, scaffold, new extension.
extension-payment
Integrate payment gateways into Chrome extensions. Stripe, Paddle, Lemon Squeezy, Polar, PayPal, and more. Licensing, subscriptions, freemium. Use when: payment, monetize, subscribe, billing, premium.
extension-ui
Build polished Chrome extension UIs (popup/sidepanel/options). Analyze existing UI, suggest improvements, set up design systems, enforce a11y and UX best practices.