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 ddpie/lark-mcp-on-agentcore --skill lark-wikigit clone --depth 1 https://github.com/ddpie/lark-mcp-on-agentcoreWrote 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/ddpie/lark-mcp-on-agentcore/lark-wiki)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-wiki"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-wiki/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/ddpie/lark-mcp-on-agentcore/lark-wiki"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-wiki.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 | $0.00169 | $0.02483 |
| Opus 5 | $0.00084 | $0.01241 |
| Sonnet 5 | $0.00034 | $0.00497 |
| Haiku 4.5 | $0.00017 | $0.00248 |
Grade A, and why
lark-wiki 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki (v2)
成员管理硬限制:
- 如果目标是"部门",先判断身份,再决定是否继续。
- bot identity 对应
tenant_access_token。官方限制:这种身份下不能使用部门 ID (opendepartmentid) 添加知识空间成员。- 遇到"部门 + bot identity"时,禁止先调用
lark_wiki_member_add试错;直接说明该路径不可行。- ⚠️ bot identity 相关操作不可通过 MCP server 执行(MCP server 始终使用 user identity)。
身份说明
知识空间和节点都是用户的个人资源。MCP server 始终使用 user identity(authentication is handled automatically by the MCP server)。
快速决策
- 用户要整理 / 盘点 / 归类 / 重构知识库、个人文档库、文档库目录或 Wiki 节点结构,或要生成整理方案、目标目录树、移动计划时,不要只使用 Wiki 节点 API。必须先调用
lark_get_skill(domain="drive", section="workflow"),再按其中Workflow Registry进入knowledge_organizeworkflow(调用lark_get_skill(domain="drive", section="workflow-knowledge-organize"));该 workflow 负责 Drive / Wiki / 个人文档库的统一入口解析、资源盘点、分类计划、写前确认和结果验证。 - 用户给的是知识库 URL(
.../wiki/<token>),且后续要查成员/加成员/删成员:先调用lark_invoke(tool_name="lark_wiki_spaces_get_node", args={params: {"token": "<wiki_token>"}})获取space_id,后续成员接口统一使用space_id。 - 用户要删除知识空间(
lark_wiki_delete_space)但只给了名称或 URL:不能把名称 / URL 原样传给space_id,必须先解析出真实space_id。解析方式:- URL(
.../wiki/<token>):lark_invoke(tool_name="lark_wiki_spaces_get_node", args={params: {"token": "<wiki_token>"}, format: "json"}),读data.node.space_id。 - 只知名称:
lark_wiki_space_list(format="json"),边翻页边收集 items 并按name精确匹配;一旦任一页累计到至少 1 条精确匹配就停止翻页。只有当翻完所有页(has_more=false)仍无精确匹配时,才对已收集的全量 items 做宽松匹配(nametrim 空格、大小写不敏感、子串包含)。 - 关键安全约束:无论精确还是模糊,无论命中 1 条还是多条,发起删除前都必须把候选(
name+space_id+description+space_type)列给用户,由用户明确选定一个space_id再执行。不要因为"只命中一条"就自动执行删除。 - 命中 0 条:停下来问用户是名称拼错了还是调用方无权限;不要自行改名字重试。
- 用户明确选定后再执行
lark_wiki_delete_space(space_id="<ID>", _confirm=true)(高风险写操作)。 - 反例:不要把 wiki URL / 名称直接当
space_id(如space_id="https://.../wiki/<wiki_token>");务必先用lark_invoke(tool_name="lark_wiki_spaces_get_node", ...)解析出data.node.space_id再传。
- URL(
- 用户要在知识库中创建新节点,优先使用
lark_wiki_node_create。 - 用户要列出 Wiki 节点:先用
lark_wiki_space_list拿数字space_id,再用lark_wiki_node_list(space_id="<space_id>")。不要把 wiki URL、node token、doc token、名称直接当space_id。钻子节点时parent_node_token必须是 wiki node token;如果用户给的是 docx/sheet/base URL,先用lark_wiki_node_get(node_token="<url>")解析出node_token。 lark_wiki_node_list命中invalid_parameters、not_found、permission_denied时,不要重复调用同一参数;按 hint 修space_id/parent_node_token/ 权限。只有rate_limit才做退避重试。- 用户说"给知识库添加成员/管理员":先把目标解析成"用户 / 群 / 部门 / 应用"四类之一,再决定
member_type,不要先调lark_wiki_member_add再根据报错反推类型。 - 用户说"部门 + bot":这是已知不支持路径。⚠️ This operation requires bot identity and is not available via the MCP server.
- 用户说"用户 / 群 / 应用 + 添加成员":先解析对应 ID,再执行
lark_wiki_member_add。 - 用户说"查看 / 列出空间成员":用
lark_wiki_member_list;该 shortcut 默认只取一页,多成员场景显式加page_all=true。 - 用户说"移除 / 删除空间成员":用
lark_wiki_member_remove,必须传齐原始授予时的member_type和member_role(不知道就先lark_wiki_member_list查一下)。
What ships with it
12 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.
- references/lark-wiki-delete-space.md 7.8 KB
- references/lark-wiki-member-add.md 2.9 KB
- references/lark-wiki-member-list.md 2.6 KB
- references/lark-wiki-member-remove.md 2.3 KB
- references/lark-wiki-move.md 8.9 KB
- references/lark-wiki-node-copy.md 2.3 KB
- references/lark-wiki-node-create.md 4.2 KB
- references/lark-wiki-node-delete.md 2.7 KB
- references/lark-wiki-node-get.md 2.1 KB
- references/lark-wiki-node-list.md 3.7 KB
- references/lark-wiki-space-create.md 1.3 KB
- references/lark-wiki-space-list.md 2.1 KB
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 · 106 lines · 169 tokens per session scan A 7bf72f3e5f0f
lark-wiki is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 12d ago), licensed MIT. It adds 169 tokens to every session and 2,483 once invoked, about $0.0008 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 2026-08-31.
Other skills, from other repositories
lark-cli
A command-line tool for working with Lark, also called Feishu, a workplace collaboration platform. It covers services such as calendars, meetings, documents, spreadsheets, messaging, tasks, approvals, and shared files.
minutes
Access Lark Minutes recordings - get metadata, export transcripts, download audio/video. Use when user asks about meeting recordings, transcripts, or minutes.
larksnap-fetch
A bridge for downloading Feishu/Lark documents or ordinary webpages into local files, with options such as Markdown, HTML, or PDF. Feishu, also called Lark, is a workplace collaboration platform.
notion
Use the Notion API to create/read/update pages, data sources (databases), and blocks.
google-workspace
Use the native Google Workspace tools for Gmail, Calendar, Drive, Docs, and Sheets.
claude-to-im
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge"…