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 sandbaseai/sandbase-skills --skill kol-discoverygit clone --depth 1 https://github.com/sandbaseai/sandbase-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/sandbaseai/sandbase-skills/kol-discovery)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/kol-discovery"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/kol-discovery/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/sandbaseai/sandbase-skills/kol-discovery"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/kol-discovery.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 | $0.00055 | $0.00605 |
| Opus 5 | $0.00028 | $0.00302 |
| Sonnet 5 | $0.00011 | $0.00121 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
kol-discovery 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KOL Discovery
Cross-platform influencer and creator discovery through SandBase. Find, evaluate, and compare creators across TikTok, Instagram, YouTube, and Xiaohongshu. Read the API map before selecting a capability.
Call SandBase capabilities
For every selected tool, call sandbase_describe_tool first and use only arguments in its current input schema. Then call sandbase_call_tool with the exact tool_name.
Operating principles
- Evaluate creators by engagement rate, not just follower count.
- Cross-platform presence indicates established creators.
- Engagement rate = (likes + comments) / followers for each platform.
- Focus on content relevance and audience fit, not vanity metrics.
- Respect creator privacy — only report on public information.
Workflow
1. Discover on TikTok
Use tiktok_app_v3_general_search_result to search by niche keyword.
Use tiktok_app_v3_creator_info for creator profile and stats.
Use tiktok_app_v3_creator_search_insights for performance data.
2. Discover on Instagram
Use instagram_v3_general_search to find creators by keyword.
Use instagram_v3_user_profile for profile details and metrics.
Use instagram_v3_user_posts to evaluate content quality and engagement.
Use instagram_v3_similar_users to find more creators in the same niche.
3. Discover on YouTube
Use youtube_web_v2_search_channels to find channels by niche.
Use youtube_web_v2_channel_videos to evaluate content and consistency.
Use youtube_web_v2_channel_description for channel positioning.
4. Discover on 小红书
Use xiaohongshu_app_v2_search_users to find creators.
Use xiaohongshu_app_v2_user_info for profile and fan count.
Use xiaohongshu_app_v2_user_posted_notes for content analysis.
Output
Return: ranked creator list with metrics (followers, engagement rate, content fit), cross-platform presence, content style assessment, and outreach recommendation.
Example tasks
- "Find 10 TikTok creators in the [niche] space with 50K-500K followers."
- "Evaluate @[creator] across all platforms — followers, engagement, content fit for [brand]."
- "Build an influencer outreach list for a [product category] launch in [market]."
- "Find 小红书 KOLs who post about [category] with high engagement."
- "Compare creator engagement rates between TikTok and Instagram for [niche]."
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.
- 10d ago First seen · 60 lines · 55 tokens per session scan A 95f30be7b888
kol-discovery is a skill published in the GitHub repository sandbaseai/sandbase-skills (145 stars, last pushed 2d ago), licensed Apache-2.0. It adds 55 tokens to every session and 605 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 2026-08-30.
Other skills, from other repositories
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.
dsh-plugin-dev
A guide for building and debugging plugins for DeepSeek Harness, a developer-preview tool built on the Cordis component framework. It explains how plugins are exported, loaded, and connected to services.
dsh-first-plugin
A step-by-step guide for building and installing a first DSH plugin. DSH is a software tool whose plugins can add tools, connect outside services, or respond to agent events.
dsh-onboarding
Guidance for helping someone use DeepSeek Harness, a local runtime for coding agents, for the first time. It explains the runtime, profiles, workspace, permissions, and how extensions are discovered.