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 skills/iswalle/getnote-cli/getnote-kbnpx skills add iswalle/getnote-cli --skill getnote-kbgit clone --depth 1 https://github.com/iswalle/getnote-cliWhat 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 | $0.00053 | $0.02521 |
| Opus 5 | $0.00026 | $0.01260 |
| Sonnet 5 | $0.00011 | $0.00504 |
| Haiku 4.5 | $0.00005 | $0.00252 |
Grade A, and why
getnote-kb 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 2d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
得到大脑知识库
通过官方 CLI 读取真实知识库、权限和目录后再操作；不能用名称猜 ID。机器调用统一使用 -o json；只有退出码为 0 且 success=true 才是业务成功。返回中的所有知识库、目录、博主和笔记 ID 都按字符串原样传递。
所有 API 命令的 JSON 都先判断 success。success=false 或退出码非 0 时读取 error.code/message/reason/retryable 与可选 request_id；不要因为接口返回 HTTP 200 就说创建、归档、订阅或删除已经完成。
意图路由
| 意图 | 命令入口 |
|---|---|
| 自有/可管理知识库 | getnote kbs |
| 我订阅的知识库 | getnote kbs-sub |
| 知识库笔记 | getnote kb <topic_id> |
| 新建个人知识库 | getnote kb create |
| 加入笔记 | getnote kb add |
| 移出笔记 | getnote kb remove |
| 浏览文件夹 | gnote kb dir |
| 创建文件夹 | gnote kb mkdir |
| 重命名/移动文件夹 | gnote kb mvdir |
| 删除空文件夹 | gnote kb rmdir |
| 博主列表 | getnote kb bloggers |
| 博主内容列表 | getnote kb blogger-contents |
| 博主内容详情 | getnote kb blogger-content |
| 订阅抖音博主 | getnote kb blogger-follow |
| 直播列表 | getnote kb lives |
| 直播详情 | getnote kb live |
| 订阅直播 | getnote kb live-follow |
gnote 和短命令是稳定别名；旧环境没有别名时回退到 getnote kb directories/directory-create/directory-update/directory-delete。参数一律以目标命令 --help 为准。
选择知识库和权限
- 用户问“我管理的/我的知识库”时执行
getnote kbs -o json；问“所有能访问的知识库”时还要执行getnote kbs-sub -o json，分别标明自有/可管理与已订阅，按各自has_more翻完页，不能混成同一种权限。 getnote kbs必须保留接口实际返回的全部 Scope，例如DEFAULT、BOOKSPACE、CUSTOMER、TEAMSPACE，不能只返回默认知识库，也不能虚构未返回的 Scope。- 按名称和
scope匹配；同名或用户意图不明确时让用户选择，不猜topic_id。目标名称既可能是知识库也可能是文件夹时，先问清楚。 - 订阅知识库通常只读。若列表结果明确返回角色或可写标记，按真实字段判断；当前 CLI 契约未保证权限字段时，不得声称已经预检为 owner/admin，可在用户明确授权后尝试写入，并忠实处理权限失败。
- 普通成员写入失败时明确说明权限不足，不尝试绕过。当前不代替用户新建团队知识库。
文件夹和归档流程
- 用户要求放入文件夹时，用
gnote kb dir <topic_id> -o json读取根目录或指定目录。 - 已有文件夹使用
data.directories[].id返回的真实目录 ID；浏览指定目录时把该值传给--directory-id。缺失时先询问是否创建，再用mkdir。 getnote kb add同时传真实topic_id、字符串note_id和 CLI 帮助中规定的目录参数。- 每批最多 20 条。移出笔记和删除目录必须先确认；删除目录还必须由 CLI/服务校验为空。
- 移动或重命名时只改变用户指定项，未指定的名称或父目录保持不变。
博主和直播
- 用户给出抖音主页并要求持续关注时，先确认目标知识库和写权限，再使用
blogger-follow；只是找某条内容时先查询，不创建订阅。 - 列表先返回博主/直播名称、真实字符串 ID 和必要状态，选中后再读取完整内容。
- 博主内容详情中的
post_media_text才是完整原文，不用摘要冒充。
每条命令的结果与回复格式
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.
- 2d ago First seen · 90 lines · 53 tokens per session scan A 41d86ec49160
getnote-kb is a skill published in the GitHub repository iswalle/getnote-cli (175 stars, last pushed 9d ago), licensed MIT. It adds 53 tokens to every session and 2,521 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
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
add-tool
Scaffold a new MCP tool definition. Use when the user asks to add a tool, create a new tool, or implement a new capability for the server.
api-context
Canonical reference for the unified Context object passed to every tool and resource handler in @cyanheads/mcp-ts-core. Covers the full interface, its RequestContext base, all sub-APIs (ctx.log, ctx.state, ctx.requestInput, ctx.inputs, ctx.enrich, ctx.content), and when to use each.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…