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 TikHub/tikhub-plugin --skill trend-researchgit clone --depth 1 https://github.com/TikHub/tikhub-pluginWrote 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/tikhub/tikhub-plugin/trend-research)<a href="https://agentmods.dev/skills/tikhub/tikhub-plugin/trend-research"><img src="https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/trend-research.svg" alt="Measured on agentmods" 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 | $0.00491 |
| Opus 5 | $0.00036 | $0.00246 |
| Sonnet 5 | $0.00014 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
Grade A, and why
trend-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Trend Research
Surface trending content, hashtags, sounds, and rankings, optionally scoped to a region or niche.
Setup gate
[ -z "${TIKHUB_API_KEY:-}" ] && echo "Set TIKHUB_API_KEY first (see tikhub-onboarding)."
Sources by platform
| Platform | What | Endpoint |
|---|---|---|
| TikTok | Popular trends | GET /api/v1/tiktok/ads/get_popular_trends (period, country_code) |
| TikTok | Trending hashtags | GET /api/v1/tiktok/ads/get_trends_hashtag_list |
| TikTok | Hot sounds | GET /api/v1/tiktok/ads/get_sound_rank_list |
| Twitter/X | Trending topics | GET /api/v1/twitter/web/fetch_trending (country) |
For niche trends, also run keyword/hashtag search on the relevant platform skill. For other
platforms' trend sources, use tikhub-find-endpoint "<goal>" --platform <slug>.
Workflow
- Clarify scope: platform(s), region/country, niche/keyword, time window.
- Pull the relevant trend boards above (one call each).
- Normalize into a single ranked list (rank, name, volume/score, example content, platform).
- Deliver a trend report; optionally drill into a hot hashtag via
hashtag-research.
Cost awareness
Each board is 1 call. A multi-platform report is a handful of calls — cheap. Drilling into many hashtags/posts multiplies calls; warn before deep dives.
Verification gate
- Each board returns a non-empty ranked list.
- Region/period filters were actually applied (echo them in the report).
Red flags
- Presenting Ads-API "trends" as organic virality without noting the source.
- Mixing regions/time windows in one ranked table without labeling them.
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.
- 8d ago First seen · 49 lines · 71 tokens per session scan A 627fcffb54b1
trend-research is a skill published in the GitHub repository TikHub/tikhub-plugin (6 stars, last pushed 2mo ago), licensed MIT. It adds 71 tokens to every session and 491 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
reelminner
Scrape Instagram reels + followers via a Playwright user session. MCP tools manage the full application — jobs, sessions, results, settings, proxies, and status — plus the core scraping tools scrapereels, getstatus, importcookies, stopscrape, exportresults. Use for reel metadata extraction, follower counts, music…
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.
model-compatibility
Model family compatibility matrix covering loaders, resolutions, samplers, CFG, VAE, ControlNet, and LoRA compatibility for SD 1.5, SDXL, Flux, SD3, and video models.
flux-txt2img
Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.
panel-node-pack-sync
Keep the ComfyUI sidebar panel node-pack (comfyui-agent-panel) in step with the orchestrator after comfyui-mcp updates. Use this whenever the orchestrator was just updated (installcomfyui (action:"selfupdate"), npm i -g comfyui-mcp, a new version in the ENVIRONMENT line), when a panel/bridge command fails in a way…
civitai
Discover Civitai models with the BUILT-IN downloadmodel action:"searchcivitai" and install/generate them locally. Find a checkpoint/LoRA/embedding on Civitai, download it into ComfyUI, and use its trigger words. Optionally pair the official Civitai MCP for community features (images browsing, posting, collections).