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-approvalgit 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-approval)<a href="https://agentmods.dev/skills/ddpie/lark-mcp-on-agentcore/lark-approval"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-approval/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-approval"><img src="https://agentmods.dev/badge/skills/ddpie/lark-mcp-on-agentcore/lark-approval.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 | $0.00091 | $0.02019 |
| Opus 5 | $0.00046 | $0.01009 |
| Sonnet 5 | $0.00018 | $0.00404 |
| Haiku 4.5 | $0.00009 | $0.00202 |
Grade A, and why
lark-approval 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 11d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
所有操作默认以当前用户身份执行（审批是人的动作）。调用前先按需调用 lark_get_skill(domain="approval", section="<对应小节>") 读取参考，查参数结构，不要猜字段；references 是第一信息源，只有在 reference 未覆盖的原生 / 高级场景下，才额外用 lark_discover(query="approval.<resource>.<method>") 补充确认字段。
路由优先级（先判断是不是审批，再选命令）
审批待办不是飞书任务。只要用户的核心对象是审批单据 / 审批待办 / 审批实例，就优先使用 approval 域，不要让渡给 task 域。
明确归审批的高优先级语义
出现以下任一语义时，优先走 approval 域：
- 审批待办 / 审批单据 / 审批实例 / 审批意见 / 审批定义
- 同意 / 拒绝 / 转交 / 退回 / 撤回 / 催办 / 加签 / 抄送
- 待办列表 / 待办单据 / 已发起审批 / 已办审批 / 审批详情 / 同意可编辑
判定规则： 只要最终动作是对审批单据做同意、拒绝、转交、退回、撤回、催办、加签、抄送、查详情、查已发起/已办/待办，就归 approval 域。只有当用户处理的是非审批类任务/待办时，才走 lark_get_skill(domain="task")。
选哪个命令
| 想做什么 | 调用 | 按需读取 reference |
|---|---|---|
| 搜可发起定义 | lark_invoke(tool_name="lark_approval_approvals_search", args={...}) |
lark_get_skill(domain="approval", section="approvals-search") |
| 看审批定义详情/提单前确认表单与流程 | lark_invoke(tool_name="lark_approval_approvals_get", args={...}) |
lark_get_skill(domain="approval", section="approvals-get") |
| 发起原生审批实例/提交请假审批/提交报销审批/创建审批实例 | lark_invoke(tool_name="lark_approval_instances_create", args={...}) |
lark_get_skill(domain="approval", section="initiate") |
| 查待办/已办 | lark_invoke(tool_name="lark_approval_tasks_query", args={params: {"topic":"1"}})（topic：1待办 2已办 17未读 18已读） |
lark_get_skill(domain="approval", section="tasks-query") |
| 看表单/进度/当前节点 | lark_invoke(tool_name="lark_approval_instances_get", args={...}) |
lark_get_skill(domain="approval", section="instances-get") |
| 同意审批 | lark_invoke(tool_name="lark_approval_tasks_approve", args={...}) |
lark_get_skill(domain="approval", section="tasks-approve") |
| 拒绝审批 | lark_invoke(tool_name="lark_approval_tasks_reject", args={...}) |
lark_get_skill(domain="approval", section="tasks-reject") |
| 转交审批 | lark_invoke(tool_name="lark_approval_tasks_transfer", args={...}) |
lark_get_skill(domain="approval", section="tasks-transfer") |
| 加签审批 | lark_invoke(tool_name="lark_approval_tasks_add_sign", args={...}) |
lark_get_skill(domain="approval", section="tasks-add-sign") |
| 退回审批 | lark_invoke(tool_name="lark_approval_tasks_rollback", args={...}) |
lark_get_skill(domain="approval", section="tasks-rollback") |
| 催办审批 | lark_invoke(tool_name="lark_approval_tasks_remind", args={...}) |
lark_get_skill(domain="approval", section="tasks-remind") |
| 撤回已发起审批 | lark_invoke(tool_name="lark_approval_instances_cancel", args={...}) |
lark_get_skill(domain="approval", section="instances-cancel") |
| 给审批实例追加抄送 | lark_invoke(tool_name="lark_approval_instances_cc", args={...}) |
lark_get_skill(domain="approval", section="instances-cc") |
| 按定义查已发起审批 | lark_invoke(tool_name="lark_approval_instances_initiated", args={...}) |
lark_get_skill(domain="approval", section="instances-initiated") |
What ships with it
16 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-approval-approvals-get.md 4.8 KB
- references/lark-approval-approvals-search.md 3.8 KB
- references/lark-approval-initiate.md 12 KB
- references/lark-approval-instance-form-control-parameters.md 26 KB
- references/lark-approval-instance-value-sourcing.md 4.6 KB
- references/lark-approval-instances-cancel.md 2.7 KB
- references/lark-approval-instances-cc.md 4.3 KB
- references/lark-approval-instances-get.md 5.8 KB
- references/lark-approval-instances-initiated.md 4.9 KB
- references/lark-approval-tasks-add-sign.md 5.2 KB
- references/lark-approval-tasks-approve.md 3.2 KB
- references/lark-approval-tasks-query.md 3.2 KB
- references/lark-approval-tasks-reject.md 2.6 KB
- references/lark-approval-tasks-remind.md 3.1 KB
- references/lark-approval-tasks-rollback.md 3.6 KB
- references/lark-approval-tasks-transfer.md 3.9 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.
- 11d ago First seen · 92 lines · 91 tokens per session scan A 178583f02447
lark-approval is a skill published in the GitHub repository ddpie/lark-mcp-on-agentcore (8 stars, last pushed 14d ago), licensed MIT. It adds 91 tokens to every session and 2,019 once invoked, about $0.0005 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
calendar
Manage Lark calendar - view schedule, create/update/delete events, check availability, find meeting slots, RSVP to invitations. Use when user asks about meetings, schedule, availability, or calendar.
luma-event-promo
End-to-end Luma event launch: research comparable events in the target city, draft copy that doesn't read like AI slop, create a Private draft via the admin API, fix the startat / duration / capacity traps, and polish theme, font, and cover. Use this whenever the user wants to publish, edit, or shape an event for…
recipe-project-tracker
Sync project data between Lark and Notion.
daily-standup
An automated weekday stand-up process for a laboratory. It gathers yesterday's progress, today's plans, and blockers, then posts a summary to the lab's group chat at 09:30.
manage-papers
A workflow for managing research papers in a Papers table, including papers from arXiv, a research-paper repository, or DOI records. It can also handle manually entered papers and link them to projects.
meeting-agenda
A workflow for preparing a group meeting: collecting topics 24 hours beforehand, creating an agenda document, sharing it with the lab group, and sending reminders.