social-listening

social-listening is a skill for Claude Code from TikHub/tikhub-plugin. It costs 67 tokens per session (540 once invoked), scanned A, original, MIT.

A tool for tracking mentions of a brand, product, person, or keyword across social platforms and summarizing the tone and recurring topics in those mentions.

In plain words
What is it for?
Use it to monitor public discussion, measure sentiment, find repeated complaints or praise, and review representative posts with source links.
Why use it?
It brings scattered discussions into one digest instead of requiring manual searches on each platform. It groups mentions as positive, neutral, or negative and identifies common themes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the tikhub-plugin plugin — 19 skills, 7 MCP servers shipped together

Good fit Use it to monitor public discussion, measure sentiment, find repeated complaints or praise, and review representative posts with source links.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tikhub/tikhub-plugin/social-listening
Install

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.

Any agent
npx skills add TikHub/tikhub-plugin --skill social-listening
Clone the repo
git clone --depth 1 https://github.com/TikHub/tikhub-plugin

Made for: Claude Code.

Or install tikhub-plugin, the plugin that ships this one along with the rest of its 19 skills, 7 MCP servers.

Wrote 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.

agentmods badge for social-listening

README.md
[![agentmods](https://agentmods.dev/badge/skills/tikhub/tikhub-plugin/social-listening/github.svg)](https://agentmods.dev/skills/tikhub/tikhub-plugin/social-listening)
Your own site
<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.

agentmods 80×15 button for social-listening

Your own site · 80×15
<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>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 540 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash 212323741cc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

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.

skills/social-listening/SKILL.md · 49 lines

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

  1. Define the query: brand/keyword(s), platforms to cover, time window, target volume (e.g. ~100 mentions).
  2. Search each platform using its search endpoint (one query → paginate to the target volume):
    • TikTok app/v3/fetch_video_search_result, Douyin search/fetch_general_search_v2 (POST body), Instagram v2/general_search, Twitter web/fetch_search_timeline, YouTube web_v2/get_general_search, Xiaohongshu app_v2/search_notes.
    • Find exact paths via tikhub-find-endpoint "search" --platform <slug>.
  3. Collect posts/comments into one list (author, text, platform, url, timestamp, engagement).
  4. Classify sentiment (positive / neutral / negative) per mention — reason over the text.
  5. Cluster themes (recurring topics, complaints, praise) and pull representative quotes.
  6. 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

  1. Mentions actually match the query (filter false positives).
  2. Every theme/claim in the digest cites a real source URL.
  3. 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.
Changes

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.

  1. 10d ago First seen · 49 lines · 67 tokens per session scan A 212323741cc4

Subscribe to this mod's changes

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.

Related

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…

ilovekushgola/reelminner · 86 tokens

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.

artokun/comfyui-mcp · 68 tokens

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.

artokun/comfyui-mcp · 47 tokens

flux-txt2img

Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns.

artokun/comfyui-mcp · 44 tokens

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…

artokun/comfyui-mcp · 206 tokens

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).

artokun/comfyui-mcp · 76 tokens