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 agentmods add instructions/cx2002302-lang/zettelkasten-second-memory/agents-mdgit 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/instructions/cx2002302-lang/zettelkasten-second-memory/agents-md)<a href="https://agentmods.dev/instructions/cx2002302-lang/zettelkasten-second-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/cx2002302-lang/zettelkasten-second-memory/agents-md.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 | $0.01918 | $0.01918 |
| Opus 5 | $0.00959 | $0.00959 |
| Sonnet 5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
Grade A, and why
zettelkasten-second-memory AGENTS.md 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 5d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zettelkasten Project Guidelines
系统版本信息(每次思考必须考虑)
- OpenClaw 版本: 2026.4.24 / 2026.6.x(兼容 >= 2026.4.23)
- Zettelkasten 插件版本: v1.0.0-beta.8
- Skill 版本: v1.0.0-beta.8
- Hermes Agent: v0.17.0+(实验性支持)
- Node 要求: >= 22.14.0(
node:sqlite需要 Node 22+)
兼容性保障索引
所有兼容性相关决策、已知坑、版本矩阵、测试命令都记录在 docs/COMPATIBILITY.md。
每次修改兼容性相关代码前,先更新该文档。
OpenClaw 2026.6.x 兼容性变更
2026.6.x 引入了基于 contracts.tools 的插件工具契约:
- 插件 manifest 必须声明
contracts.tools(已在src/plugin/openclaw.plugin.json中补齐全部zk_*工具名)。未声明时,运行时api.registerTool(...)会被拒绝,agent 看不到任何 zk 工具。 - 工具 allowlist 仍通过
tools.alsoAllow配置,但推荐使用插件 ID 或group:plugins:2026.4.x:tools.alsoAllow: ["zettelkasten"]2026.6.x+:tools.alsoAllow: ["group:plugins"]或["zettelkasten"](两者在 manifest 声明 contracts 后都会被正确展开为具体工具)
- systemPromptOverride 已移除:2026.6.x+ 不再接受
agents.defaults.systemPromptOverride,Skill 通过skills.load.extraDirs正常加载即可。 - 修改 manifest 后需要刷新插件索引:
openclaw plugins registry --refresh openclaw gateway restart
OpenClaw 2026.4.24 配置字段备忘
| 常见错误 | 正确字段 |
|---|---|
agents.default |
agents.defaults |
agents.defaults.systemPrompt |
agents.defaults.systemPromptOverride |
agents.defaults.skills 填文件路径 |
agents.defaults.skills 填 skill ID(如 ["zettelkasten-brain"]) |
⚠️ 关键配置(部署时必须检查)
-
插件工具暴露 —
tools.alsoAllow应包含"zettelkasten":{ "tools": { "profile": "coding", "alsoAllow": ["zettelkasten"] } }否则 agent 无法调用
zk_search_notes等 MCP 工具。⚠️ 注意:
alsoAllow中不要放入 Skill ID(如"zettelkasten-brain")。alsoAllow只接受 Tool Name(以zk_为前缀的工具名,如"zk_search_notes"、"zk_create_note"等)。放入 Skill ID 会导致 OpenClaw Gateway 工具策略验证失败,引发崩溃-重启循环(BUG-001)。 -
systemPromptOverride — 不支持
file:前缀,需直接填入文本内容:# 错误 openclaw config set agents.defaults.systemPromptOverride "file:..." # 正确:直接写入文本(或通过脚本读取文件内容后设置)
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.
- 5d ago First seen · 153 lines · 1,918 tokens per session scan A 5a9adf1787fe
zettelkasten-second-memory AGENTS.md is an instructions file published in the GitHub repository cx2002302-lang/zettelkasten-second-memory (17 stars, last pushed 1mo ago), licensed MIT. It adds 1,918 tokens to every session, about $0.0096 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 instructions, from other repositories
obsidian-llm-wiki CLAUDE.md
Claude Code instructions for green-dalii/obsidian-llm-wiki, a project described as: Karpathy's LLM Wiki implementation plugin for Obsidian - turns notes and PDFs into a linked, LLM-powered knowledge base with entity pages, concept pages, graph-powered Q&A, and local-first privacy.
obsidian-llm-wiki AGENTS.md
AGENTS.md instructions for green-dalii/obsidian-llm-wiki, covering llm wiki plugin project development standards, 🛡️ six-gate quality closure, gate 1: five-gate automated, gate 2: no side effects and gate 3: no breaking changes.
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
hippocampus CLAUDE.md
Instructions for sturlese/hippocampus, covering layout, frontmatter schema, conventions, answering questions from the vault (read order) and contradictions.
mnemonic memory-files.instructions.md
Instructions for modeled-information-format/mnemonic, covering memory file guidelines (mif level 3), required frontmatter fields, optional temporal fields, optional provenance fields and memory types.
context-canopy AGENTS.md
Instructions for YusenZhang0601/context-canopy, covering contextcanopy agent entry, route before acting, privacy and authority boundary, portability claims and completion evidence.