lark-task

lark-task is a skill for Claude Code from DropFan/claude-code-plugins. It costs 125 tokens per session (3,907 once invoked), scanned A, a copy of lark-task, MIT.

A Feishu task skill for managing to-do items, task lists, subtasks, assignments, attachments, and task-focused agents.

In plain words
What is it for?
Use it to create, search, update, split, assign, and track tasks; manage lists; upload attachments; and register or maintain task agents.
Why use it?
It keeps work, responsibility, progress, and supporting files organised in one task system.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Claude Code.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is - **走 [lark-meeting](../lark-meeting/SKILL.md) 的 `minutes +todo`**(禁止本 skill):上下文含 **妙记 / 会议纪要 / minute_token / 妙记 URL**(`/minutes/`);或「在某某妙记里新建/修改待办」「妙记 AI 待办」.

Part of the lark plugin — 28 skills shipped together

Good fit Use it to create, search, update, split, assign, and track tasks; manage lists; upload attachments; and register or maintain task agents.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/DropFan/claude-code-plugins
agentmods
npx agentmods add skills/dropfan/claude-code-plugins/lark-task

Made for: Claude Code.

Or install lark, the plugin that ships this one along with the rest of its 28 skills.

Wrote 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.

agentmods badge for lark-task

README.md
[![agentmods](https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-task/github.svg)](https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-task)
Your own site
<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-task"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-task/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.

agentmods 80×15 button for lark-task

Your own site · 80×15
<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-task"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 125 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,907 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 83% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00125 $0.03907
Opus 5.5 $0.00050 $0.01563
Sonnet 5.5 $0.00025 $0.00781
Haiku 4.5 $0.00013 $0.00391

Measured 25d ago against content hash 81513cd1bd16, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lark-task 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 25d 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.

Origin

This is a copy

83% identical to lark-task — 18 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/lark/skills/lark-task/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

⚙️ Cowork / Claude Desktop 执行环境说明(自动注入)

本技能依赖本地 lark-cli(@larksuite/cli,可用 command -v lark-cli 定位)及其 ~/.lark-cli 登录态(应用密钥存于 macOS keychain)。

在 Cowork 中运行任何 lark-cli 命令时,必须在本地 macOS 上执行(使用 Desktop Commander 的 start_process / interact_with_process,或其它本地 shell 工具),不要用隔离的 Linux 沙箱 mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。 执行前确保 npm 全局 bin 目录(npm prefix -g 输出目录下的 bin)在 PATH 中。

(在 Claude Code 中可忽略本说明,lark-cli 在本机 shell 直接可用。)

task (v2)

CRITICAL — 开始前 MUST 先用 Read 工具读取 ../lark-shared/SKILL.md,其中包含认证、权限处理

命令选择与渐进式发现(必读)

执行任何 Task 命令前,必须先确认能力真实存在,禁止根据用户意图自行拼接或猜测 +<verb>:

  1. 先将用户意图与下方 Shortcut 表精确匹配。只有表中明确列出的 shortcut 才可直接选择;参数不确定时读取对应 reference 或运行该 shortcut 的 --help。
  2. 没有精确匹配、或无法确认当前版本是否支持时,先运行 lark-cli task --help,以当前 CLI 输出的命令列表为准。
  3. help 中存在匹配 shortcut 时,使用 help 列出的完整 shortcut token(例如 +create)运行 lark-cli task <shortcut> --help,再按真实 flag 执行。
  4. help 中没有匹配 shortcut 时,不得尝试相似的 +<verb>;从 help 中选择原生 resource,运行 lark-cli task <resource> --help 确认 method,再运行 lark-cli schema task.<resource>.<method> 获取参数结构,最后调用 lark-cli task <resource> <method> ...。
  5. 遇到 unknown_subcommand 时必须停止猜测或尝试变体,回到第 2 步重新发现能力。

shortcut 名称只能来自本 Skill 的 Shortcut 表或 lark-cli task --help;原生 resource/method 以逐级 help 为准,参数名、类型和嵌套结构以 method schema 为准。

任务搜索技巧:先区分用户是否特地指定使用搜索 skill,以及是否真的提供了查询关键字(例如任务名称、关键词、片段描述)。如果用户特地指定使用搜索 skill,或明确给出了任务查询关键字,则目标是任务时优先使用 +search。如果用户没有特地指定使用搜索 skill,且意图里没有查询关键字,只有范围条件(例如“今年以来”“已完成”“由我创建”“我关注的”),并且使用 +search 与 +get-related-tasks / +get-my-tasks 都能达到目的时,应优先使用列表型能力,而不是搜索型能力。其中,“与我相关 / 我关注的 / 由我创建”等优先考虑 +get-related-tasks;“我负责的 / 分配给我”的列表优先考虑 +get-my-tasks。不要把时间范围词(例如“今年以来”)本身误当成 query 去走搜索。 任务搜索相关性提示:+search 当前不会自动判断搜索结果与搜索发起人的相关性。如果用户明确要求搜索“与我相关”的任务,必须先识别具体关系,获取当前用户的 open_id,并显式传入对应的 --assignee(负责人)、--creator(创建人)或 --follower(关注人)过滤条件;不能只依赖 query 期待自动返回与当前用户相关的任务。 任务清单搜索技巧:任务清单也遵循同样的判断逻辑。先区分用户是否特地指定使用搜索 skill,以及是否真的提供了清单查询关键字(例如清单名称、关键词、片段描述)。如果用户特地指定使用搜索 skill,或明确给出了清单查询关键字,则优先使用 +tasklist-search。如果用户没有特地指定使用搜索 skill,且意图里没有查询关键字,只有范围条件(例如“由我创建的任务清单”“今年以来创建的清单”),并且使用搜索或原生列取清单都能达到目的时,应优先使用原生 tasklists.list 接口列取清单(先 schema task.tasklists.list,再 lark-cli task tasklists list --as user ...),再按 creator、created_at 等字段做本地筛选和分页控制。 意图区分补充:像“搜索飞书中今年以来我关注的任务”这类表达,虽然字面带有“搜索”,但如果没有真正的查询关键字,且本质是在限定“与我相关 + 时间范围”,则应优先走 +get-related-tasks;像“搜索飞书中由我创建的任务清单”这类表达,如果没有清单关键字,且本质是在限定“清单范围 + 创建者”,则应优先走原生 tasklists.list 后筛选,而不是直接走搜索型 shortcut。 用户身份识别:在用户身份(user identity)场景下,如果用户提到了“我”(例如“分配给我”、“由我创建”),请默认获取当前登录用户的 open_id 作为对应的参数值。 术语理解 — 待办 disambiguation(必读):

  • 用户提到「待办 / todo / 任务」时,先判断归属,不要默认走本 skill。
  • 走 lark-meeting 的 minutes +todo(禁止本 skill):上下文含 妙记 / 会议纪要 / minute_token / 妙记 URL(/minutes/);或「在某某妙记里新建/修改待办」「妙记 AI 待办」「会议录制里的待办」。
  • 走本 skill(lark-task):任务清单、分配给我、项目待办、截止日期/提醒、子任务、任务清单成员;或 applink 含 client/todo/task?guid=;或明确说「飞书任务」「任务中心」「我的任务清单」。
  • 禁止:用户要在妙记里加待办时,不要调用 task tasklists list、task +create 或任何 task 命令去「找清单再放任务」。 友好输出:在输出任务(或清单)的执行结果给用户时,建议同时提取并输出命令返回结果中的 url 字段(任务链接),以便用户可以直接点击跳转查看详情。

Read the full file on GitHub · 199 lines

Changes

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.

  1. 25d ago Changed · +12 lines 81513cd1bd16
  2. 1mo ago First seen · 187 lines · 125 tokens per session scan A eea9ed4bbd34

Subscribe to this mod's changes

lark-task is a skill published in the GitHub repository DropFan/claude-code-plugins (8 stars, last pushed 26d ago), licensed MIT. It adds 125 tokens to every session and 3,907 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 83% identical to lark-task, differing in 18 lines, and is treated as a copy.