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 0xmariowu/Autosearch --skill tikhub-fallbackgit clone --depth 1 https://github.com/0xmariowu/AutosearchWrote 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/0xmariowu/autosearch/tikhub-fallback)<a href="https://agentmods.dev/skills/0xmariowu/autosearch/tikhub-fallback"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/tikhub-fallback/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/0xmariowu/autosearch/tikhub-fallback"><img src="https://agentmods.dev/badge/skills/0xmariowu/autosearch/tikhub-fallback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00080 | $0.01309 |
| Opus 5 | $0.00040 | $0.00655 |
| Sonnet 5 | $0.00016 | $0.00262 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
autosearch:tikhub-fallback 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TikHub Fallback Decision Tree — Advisory
Cost anchor: TikHub averages $0.0036 per request (per docs/mcp-channels-playbook.md measurement). A research session with 1000 TikHub calls costs about $3.60/month. Cheap per call, but accumulates fast if every query defaults to paid.
Boss rule: Free paths first; TikHub is the paid cushion, not the default.
Covered Platforms (5)
| Platform | Free native skill | TikHub endpoint | Free path reliability |
|---|---|---|---|
| Xiaohongshu | search-xiaohongshu (requires cookie) |
xiaohongshu/web/search_notes |
Low — reliably gated; TikHub is usually required |
search-weibo (free API) |
web/fetch_search |
Medium — free works but TikHub upstream is flaky | |
| Douyin | search-douyin (free native) |
TikHub + mcporter-routed free MCP |
Medium — free works, TikHub more complete |
| Zhihu | search-zhihu (free native) |
TikHub endpoint | Low — Zhihu blocks aggressive scraping |
| Twitter / X | search-twitter-exa |
search-twitter-xreach (XReach) |
Medium — Exa covers public, XReach covers deeper signal |
Other hard Chinese platforms not covered by TikHub (do not escalate, degrade gracefully):
- WeChat Mini Programs
- Private Xiaohongshu accounts
- Facebook / Instagram private pages
- Any account-gated content
Decision Tree
Apply per query, not per session:
1. Try the free native channel skill first.
├─ Returns usable results? → DONE (do not escalate).
└─ Blocked / empty / flaky? → step 2.
2. If `TIKHUB_API_KEY` is not set in env:
├─ Try the mcporter free MCP if applicable (Weibo, Douyin).
└─ Otherwise report to user: "no free path, no TikHub key — gracefully degraded."
3. If `TIKHUB_API_KEY` is set AND the platform is one of the 5 covered:
├─ If query is research-critical (user explicitly asked or Best-tier step) → escalate to TikHub.
├─ If query is exploratory / fan-out → skip TikHub, try a different channel instead.
└─ After 3 failed TikHub requests on the same session / same query shape → stop, do not retry a 4th time (rate-limit or upstream regression signal).
4. Bundle call patterns to reduce cost:
├─ Dedupe queries across channels before calling TikHub.
└─ Prefer single calls that return rich payloads over multiple narrow calls.
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.
- 11d ago First seen · 93 lines · 80 tokens per session scan A 593061d4fab4
autosearch:tikhub-fallback is a skill published in the GitHub repository 0xmariowu/Autosearch (44 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,309 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 2026-08-30.
Other skills, from other repositories
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
sanity-best-practices
Sanity development best practices for schema design, GROQ queries, TypeGen, Visual Editing, images, Portable Text, Studio structure, localization, migrations, Sanity Functions, webhooks, Blueprints, and framework integrations such as Next.js, Nuxt, Astro, Remix, SvelteKit, Angular, Hydrogen, and the App SDK. Use this…
portable-text-serialization
Render and serialize Portable Text to React, Svelte, Vue, Astro, HTML, Markdown, and plain text. Use when implementing Portable Text rendering in any frontend framework, building custom serializers for non-standard block types, converting Portable Text to HTML strings server-side, converting Portable Text to Markdown…
development-assistant
Guides through adding new features, MCP tools, analyzers, and extending the patent creator system.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.
video-perception
Use when the user mentions a video file (.mp4, .mov, .avi, .mkv, .webm), a YouTube URL, asks to watch/analyze/review a video, or references video content in conversation.