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 social-listeninggit 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/social-listening)<a href="https://agentmods.dev/skills/tikhub/tikhub-plugin/social-listening"><img src="https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/social-listening/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/tikhub/tikhub-plugin/social-listening"><img src="https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/social-listening.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 | $0.00067 | $0.00540 |
| Opus 5 | $0.00034 | $0.00270 |
| Sonnet 5 | $0.00013 | $0.00108 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
social-listening scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Social Listening
Collect mentions of a brand/keyword across platforms, then analyze sentiment and themes.
Setup gate
[ -z "${TIKHUB_API_KEY:-}" ] && echo "Set TIKHUB_API_KEY first (see tikhub-onboarding)."
Workflow
- Define the query: brand/keyword(s), platforms to cover, time window, target volume (e.g. ~100 mentions).
- Search each platform using its search endpoint (one query → paginate to the target volume):
- TikTok
app/v3/fetch_video_search_result, Douyinsearch/fetch_general_search_v2(POST body), Instagramv2/general_search, Twitterweb/fetch_search_timeline, YouTubeweb_v2/get_general_search, Xiaohongshuapp_v2/search_notes. - Find exact paths via
tikhub-find-endpoint "search" --platform <slug>.
- TikTok
- Collect posts/comments into one list (author, text, platform, url, timestamp, engagement).
- Classify sentiment (positive / neutral / negative) per mention — reason over the text.
- Cluster themes (recurring topics, complaints, praise) and pull representative quotes.
- Deliver a digest: volume, sentiment breakdown, top themes with cited example posts (link each claim to a source URL), and 2–3 recommendations.
Cost awareness — IMPORTANT
This is the most call-heavy skill: every search page on every platform is a billed call.
State an estimated call count and cost before running
(GET /api/v1/tikhub/user/calculate_price?endpoint=<path>&request_per_day=<pages>), cap pages per
platform, and check balance with get_user_daily_usage.
Verification gate
- Mentions actually match the query (filter false positives).
- Every theme/claim in the digest cites a real source URL.
- Sentiment labels are justified by the quoted text.
Red flags
- Unbounded multi-platform pagination — runs up credits fast; always cap and warn.
- Reporting sentiment without citations.
- Counting unrelated keyword collisions as mentions.
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.
- 10d ago First seen · 49 lines · 67 tokens per session scan A 212323741cc4
social-listening is a skill published in the GitHub repository TikHub/tikhub-plugin (6 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 540 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
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).