OpenBiliClaw is a local, open-source AI agent that learns a person's interests and discovers content across multiple social platforms and the open web. It is for people who want personalized content recommendations with their usage data kept on their own machine.
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 whiteguo233/OpenBiliClaw --skill searchgit clone --depth 1 https://github.com/whiteguo233/OpenBiliClawWrote 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/whiteguo233/openbiliclaw/search)<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/search"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/search/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/whiteguo233/openbiliclaw/search"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/search.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 | $0.00020 | $0.01671 |
| Opus 5 | $0.00010 | $0.00835 |
| Sonnet 5 | $0.00004 | $0.00334 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
bilibili_search 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 9d 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bilibili Search Skill
Search for videos on Bilibili based on the user's interests and soul profile. Supports both LLM-driven automatic query generation (for discovery cycles) and direct keyword search (for explicit user requests).
When to Use
- During content discovery cycles
- When the user explicitly asks to find content on a topic
- When generating exploratory searches for new interest domains
How It Works
- Query generation — If no explicit
keywordsare provided, the skill uses an LLM to generate multiple search queries from the user's soul profile (top interests, cognitive style, deep needs). Ifkeywordsare provided, they are used directly. - Sequential search — Each query is sent to the Bilibili WBI-signed search endpoint sequentially, with a jitter-randomised 0.5–1.0s delay between queries (v0.3.61+) so the requests don't land in the same Bilibili rate-limit bucket. A dedicated API client is used per strategy to isolate rate-limiting.
- Resilience & storm mode — Individual query failures (including Bilibili
412 Precondition Failed) degrade gracefully and don't interrupt the overall flow.client.searchretriesv_voucherchallenges 3× internally; three consecutive empty results trip "storm mode" (v0.3.61+) and the remaining queries are skipped (filled with empty results) rather than burned against an IP that's being challenged — the next refresh tick (~60s) gets a fresh shot. An active search cooldown short-circuits the remaining plan the same way. - Scoring — Results are evaluated against the soul profile via LLM and assigned a
relevance_score(0.0–1.0). Items below the threshold are discarded. - Output — Returns scored
DiscoveredContentitems.
Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
keywords |
string |
No | "" |
Search query string. If empty, the skill auto-generates queries from the soul profile. |
page |
integer |
No | 1 |
Page number for paginated results. |
limit |
integer |
No | 20 |
Maximum number of results to return. |
order |
string |
No | "totalrank" |
Sort order. One of: "totalrank" (relevance), "pubdate" (newest), "click" (most viewed), "dm" (most commented). |
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.
- 9d ago First seen · 142 lines · 20 tokens per session scan A 5b3715127c78
bilibili_search is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,223 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 1,671 once invoked, about $0.0001 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
search
Search local or remote sources quickly, narrow results, and surface the highest-signal matches for the task.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
audiocraft-audio-generation
AudioCraft: MusicGen text-to-music, AudioGen text-to-sound.
hyperframes
Render MP4/WebM videos from HTML compositions.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
stable-diffusion
Text-to-image generation, inpainting, and img2img.