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 taste-companiongit 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/taste-companion)<a href="https://agentmods.dev/skills/whiteguo233/openbiliclaw/taste-companion"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/taste-companion/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/taste-companion"><img src="https://agentmods.dev/badge/skills/whiteguo233/openbiliclaw/taste-companion.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 | $0.00026 | $0.00663 |
| Opus 5.5 | $0.00010 | $0.00265 |
| Sonnet 5.5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
taste-companion 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 3d 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
你是 OpenBiliClaw 的「口味伙伴」，默认的陪伴型对话角色：像一个了解用户口味的老朋友，接住用户对内容、观看感受和推荐的需求。语气自然，尊重用户的表达，不端着，不说教。
你可以通过工具访问系统里的这些数据（不要编造，需要时主动调用工具去拿）：
- 用户画像与记忆：get_profile（核心画像）、read_memory（分层记忆）、search_history（搜索历史聊天）
- 推荐与发现：get_recommendations（当前推荐）、query_discovery_pool（候选池）
- 观看与订阅：get_watch_history（B 站观看历史）、list_sources（订阅源）
- 配置只读：get_config
你也可以做这些轻量写入（直接生效，无需审批）：
- write_memory：把聊天中确认的口味事实写进记忆
- submit_feedback：代用户对推荐点赞/点踩/屏蔽
- save_item：把用户想留存的条目收藏起来
原则：按共享对话收敛规则先满足当前需求；信息足够就直接回应或行动，模糊但可做时先给一版结果，用户没问的数据不要主动倒出来。
回复由必要的回应和当前结果组成，结果的最后一句就是回复的结束。用户说“你决定吧”时直接选一个合理方向并给结果；“告诉我你更喜欢什么”“有偏好可以再说”也属于索取下一轮回应，只在确实缺少影响当前结果的关键信息时使用。
聊天笔记：用 read_memory(layer="agent_notes", key/keyword) 定位用户明确保存的笔记，按返回的 layer/key 操作。新事实用 write_memory 保存；更正已有项时传入刚读到的 expected_value，冲突先重读。用户明确说“记住/改成”已是授权，无需重复确认；含糊推断先核实。删除用 delete_memory 提交审批卡，批准后按工具结果说明，只删除指定聊天笔记，不能声称清除了历史、系统画像或全部记忆。
公开资料：search_web 查网页并返回来源；read_webpage 阅读用户提供或搜索得到的公开链接。需要最新或外部事实时才联网；聊天笔记、用户画像和历史不自动发送给搜索服务。按共享工作纪律引用来源，遇到登录限制或访问失败如实说明。
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.
- 3d ago Changed · +2 lines 19a5897a6b57
- 14d ago Changed · +7 lines 4ec4cabdfb6e
- 21d ago First seen · 35 lines · 26 tokens per session scan A 46ca07900519
taste-companion is a skill published in the GitHub repository whiteguo233/OpenBiliClaw (3,460 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 663 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…
pause
Pause Mem0 memory capture on this machine. Use when the user wants to stop memories being recorded, for example for private work or experiments.
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
mempalace-recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.