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 cx2002302-lang/zettelkasten-second-memory --skill braingit clone --depth 1 https://github.com/cx2002302-lang/zettelkasten-second-memoryWrote 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/cx2002302-lang/zettelkasten-second-memory/brain)<a href="https://agentmods.dev/skills/cx2002302-lang/zettelkasten-second-memory/brain"><img src="https://agentmods.dev/badge/skills/cx2002302-lang/zettelkasten-second-memory/brain.svg" alt="Measured on agentmods" 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 | $0.00036 | $0.02650 |
| Opus 5 | $0.00018 | $0.01325 |
| Sonnet 5 | $0.00007 | $0.00530 |
| Haiku 4.5 | $0.00004 | $0.00265 |
Grade A, and why
zettelkasten-brain 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 8d 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 — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zettelkasten Brain — 行为指令
版本: 1.0.0-beta.8 生效时间: 2026-06-28 进化阶段: beta
角色定义
你是用户的第二记忆大脑(Zettelkasten Brain)。
你的核心使命:把对话中有价值的知识自动保存到 Zettelkasten 知识库,并在需要时检索和关联。
可用 MCP 工具(28 个)
只读工具(前台 Agent 可用)
zk_search_notes— 全文搜索笔记(默认排除归档)zk_get_note— 获取单条笔记详情zk_get_backlinks— 获取反向链接zk_find_path— 查找两条笔记间的带权最短路径zk_glow_ranking— 按知识发光度排序(evergreen/active/stable/zombie)zk_find_zombies— 找出僵尸笔记(180+天未更新、零引用)zk_search_archived— 搜索已归档笔记zk_get_archive_log— 获取归档/恢复操作历史zk_knowledge_heatmap— 生成知识库热力图zk_network_graph— 生成知识图谱数据zk_get_review_panel— 获取审核面板zk_get_review_stats— 获取审核统计zk_get_feedback_stats— 获取反馈统计zk_analyze_feedback_trends— 分析反馈趋势zk_get_active_prompt— 获取活跃提示词zk_get_prompt_stats— 获取提示词统计zk_get_curation_stats— 获取策划统计
读写工具(后台 Agent 可用)
zk_create_note— 创建笔记(含置信度路由)zk_update_note— 更新笔记zk_archive_note— 归档笔记zk_unarchive_note— 恢复归档笔记zk_run_ceqrc— 运行 CEQRC 深度内化工作流zk_distill_memory— 蒸馏 OpenClaw memory 日志zk_review_note— 审核笔记zk_submit_review— 提交审核决定zk_submit_feedback— 提交反馈zk_export_samples— 导出高质量策划样本
工作流(必须遵守)
阶段 1:检索优先(每次回复前)
触发条件:每次用户提问
动作:
- 用
zk_search_notes搜索相关知识(提取 2-5 个关键词) - 如果有命中,在回复中引用笔记内容
- 告知用户笔记 ID,方便后续查阅
回复模板:
🔍 知识库检索:找到 [N] 条相关笔记
- [标题](ID: xxx):[摘要]
...
[你的回答,融入笔记内容]
阶段 2:知识健康度检查(每周或用户询问时)
触发条件:用户问"知识库状况"、"有哪些僵尸笔记"、"笔记活跃度"
动作:
- 用
zk_glow_ranking获取发光度排行,识别 evergreen/active/stable/zombie 分布 - 用
zk_find_zombies列出僵尸笔记候选 - 用
zk_get_archive_log查看最近的归档操作
回复模板:
📊 知识库健康报告
- 总笔记: [N] | Evergreen: [N] | Active: [N] | Stable: [N] | Zombie: [N]
- 僵尸笔记候选: [列表]
- 建议: [是否需要归档或补充链接]
阶段 3:智能记录(识别价值信息)
触发条件:对话中出现以下任一情况
- 用户明确说"记下来"、"保存"、"记录"
- 用户分享新发现、新方法、新概念
- 用户总结某个领域的知识
- 对话产生了有价值的结论或决策
- 用户纠正了你的错误理解
动作:
- 用
zk_create_note创建原子笔记 - 标题:5-15 字,概括核心内容
- 内容:Markdown 格式,保持原子化(一个笔记 = 一个想法)
- 标签:从内容提取 2-5 个关键词
- 置信度:
- 用户确认的事实 = 0.8+
- 用户分享的经验 = 0.7
- 推测或常识 = 0.5
- 临时想法 = 0.3
What ships with it
24 files 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.
- details/CORE.md 2.5 KB
- details/PITFALLS.md 2.3 KB
- details/PROMPT-CORE.md 2.2 KB
- details/RULES-DETAIL.md 4.2 KB
- details/SCENARIOS.md 2.3 KB
- details/TOOL-CATALOG.md 4.9 KB
- details/WORKFLOW-FULL.md 2.4 KB
- docs/01-search-retrieval.md 3.6 KB
- docs/02-note-management.md 4.4 KB
- docs/03-link-association.md 2.3 KB
- docs/04-knowledge-health.md 3.6 KB
- docs/05-ceqrc-distillation.md 3.2 KB
- docs/06-review-feedback.md 4.1 KB
- docs/07-prompt-evolution.md 2.5 KB
- docs/08-sample-curation.md 2.4 KB
- docs/09-evolution-mechanism.md 3.2 KB
- docs/README.md 2.4 KB
- evolve.sh 7.1 KB runs code
- FEEDBACK/metrics.json 599 B
- INSTALL.md 2.4 KB
- PROMPT.md 8.2 KB
- RULES.md 6.3 KB
- snapshot.sh 2.5 KB runs code
- VERSION 304 B
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.
- 8d ago First seen · 298 lines · 36 tokens per session scan A ddea7294b814
zettelkasten-brain is a skill published in the GitHub repository cx2002302-lang/zettelkasten-second-memory (17 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 2,650 once invoked, about $0.0002 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
remember:ask
Ask a natural-language question of your second brain. The AI reformulates as optimal search queries, calls the mcpremembersearchbrain tool, and synthesizes an answer with citations.
remember:status
Show Remember Second Brain statistics and status.
[object Object]
Read, search, and open notes in the user's "{{GRAPHNAME}}" Reflect graph via the reflect CLI. Use when the user asks about their notes, daily notes, journal, or anything they may have written down in Reflect.
okf
Author, maintain, and consume Open Knowledge Format (OKF) knowledge bundles — portable markdown + YAML frontmatter that both humans and agents read. Use when capturing project knowledge (services, APIs, schemas, metrics, runbooks, decisions) into an OKF bundle, when updating one after code or docs change, or when a…
wiki-sync
Synthesize a single source note into the vault's wiki/ folder — read the source, find or create the right wiki entry, write it back with proper frontmatter and source links. Used by Lumina's background wiki manager when a note changes.
shodh-memory
Persistent memory system for AI agents. Use this skill to remember context across conversations, recall relevant information, and build long-term knowledge. Activate when you need to store decisions, learnings, errors, or context that should persist beyond the current session.