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 web-ai-routergit 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/web-ai-router)<a href="https://agentmods.dev/skills/syysean/web-ai-skills/web-ai-router"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/web-ai-router/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/web-ai-router"><img src="https://agentmods.dev/badge/skills/syysean/web-ai-skills/web-ai-router.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 | $0.00071 | $0.01069 |
| Opus 5 | $0.00036 | $0.00535 |
| Sonnet 5 | $0.00014 | $0.00214 |
| Haiku 4.5 | $0.00007 | $0.00107 |
Grade A, and why
web-ai-router 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web AI Router
Select the best available web AI for a task and delegate to the appropriate worker.
Available Workers
| Worker | URL | Login Required | Best For |
|---|---|---|---|
| gemini-worker | gemini.google.com | ❌ No | General QA, summarization, translation, current events (has Google Search) |
| grok-worker | grok.com | ✅ Yes | Real-time web search, breaking news, current events, X/Twitter context |
| deepseek-worker | chat.deepseek.com | ✅ Yes | Deep reasoning, math, code analysis, complex multi-step problems |
| claude-worker | claude.ai | ✅ Yes | Writing, analysis, coding, nuanced long-form tasks |
| chatgpt-worker | chatgpt.com | ✅ Yes | General QA, writing, coding, creative tasks |
See worker-contract.md for the shared output schema.
Routing Logic
Step 1 — Identify task type
Read the user's request and classify:
| Task | Best Worker | Reason |
|---|---|---|
| Current news, real-time events | grok-worker | Live web search |
| Math, code, logic, deep analysis | deepseek-worker | Strong reasoning |
| Writing, editing, long-form tasks | claude-worker | Nuanced language |
| Creative tasks, general coding | chatgpt-worker | Broad capability |
| General QA, translation, summary | gemini-worker | Fast, no login needed |
| Ambiguous or mixed | gemini-worker | Default fallback |
Step 2 — Check worker availability
Before routing, verify the target worker is accessible:
- gemini-worker: always available (no login required)
- grok-worker: requires Grok session in Chrome profile
- deepseek-worker: requires DeepSeek session in Chrome profile
- claude-worker: requires Claude session in Chrome profile
- chatgpt-worker: requires ChatGPT session in Chrome profile
If the preferred worker is unavailable (login required but session lost), fall back to gemini-worker and note the fallback in the output.
Step 3 — Route to worker
Load and execute the appropriate worker skill:
[skill] gemini-worker → for general tasks
[skill] grok-worker → for real-time search tasks
[skill] deepseek-worker → for reasoning/analysis tasks
[skill] claude-worker → for writing/long-form tasks
[skill] chatgpt-worker → for creative/general tasks
What ships with it
1 file 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 · 122 lines · 71 tokens per session scan A 00183dc100ce
web-ai-router is a skill published in the GitHub repository Syysean/web-ai-skills (8 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 1,069 once invoked, about $0.0004 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
edgeone skill scanner
A local static scanner that checks agent-skill files for security risks before they are installed or used. Static analysis examines files without running them.
patent-map
A tool for making a visual map of stored patent case notes in an Obsidian vault. Obsidian is a note-taking application that stores linked text files.
sandbase
Access 2,000+ AI models and API tools through one MCP interface for inference, media generation, search, scraping, embeddings, social data, and structured retrieval. Use sandbasediscover before building custom integrations or declaring external data inaccessible; prefer an existing dedicated tool or API key when the…
dev-workflow
The complete development workflow for SkillHub contributors including local dev, staging validation, testing, and PR creation. Ensures agents follow the correct sequence of steps.
video-frames
Extract a single frame from a local video at the first frame, a timestamp, or a zero-based frame index using FFmpeg.
convex-performance-audit
Audits Convex performance for reads, subscriptions, write contention, and function limits. Use for slow features, insights findings, OCC conflicts, or read amplification.