lark-sheets

lark-sheets is a skill for Claude Code, Codex from larksuite/cli. It costs 297 tokens per session (8,184 once invoked), scanned A, original, MIT.

A tool for creating and managing Feishu spreadsheets, which are online workbooks with sheets, cells, formulas, and data objects such as charts and pivot tables.

In plain words
What is it for?
Use it to enter or update data, manage rows and columns, apply formulas and formatting, build summaries and financial models, and create charts, filters, pivot tables, and other spreadsheet objects.
Why use it?
It reduces manual spreadsheet editing and supports repeatable updates while preserving existing values, layout, and formatting where required.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **审批协议**:先 `--dry-run` 预览、向用户展示将执行的操作与影响范围,**获得用户明确同意后**再在原命令追加 `--yes` 执行。未经用户同意不得带 `--yes`,也不得在 exit 10 后静默补 `--yes` 重试——那等于禁用门禁。完整协议见 [`../lark-shared/SKILL..

Good fit Use it to enter or update data, manage rows and columns, apply formulas and formatting, build summaries and financial models, and create charts, filters, pivot tables, and other spreadsheet objects.

Compare 6 skills from other repositories ↓
About the project

Lark CLI is a command-line tool for using Lark/Feishu services such as messaging, documents, spreadsheets, calendars, mail, tasks, and meetings. It is intended for people and AI agents that need to work with these business tools through terminal commands.

larksuite/cli · 17,724 stars · on GitHub

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/larksuite/cli
agentmods
npx agentmods add skills/larksuite/cli/lark-sheets

Made for: Claude Code, Codex.

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-sheets

README.md
[![agentmods](https://agentmods.dev/badge/skills/larksuite/cli/lark-sheets/github.svg)](https://agentmods.dev/skills/larksuite/cli/lark-sheets)
Your own site
<a href="https://agentmods.dev/skills/larksuite/cli/lark-sheets"><img src="https://agentmods.dev/badge/skills/larksuite/cli/lark-sheets/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-sheets

Your own site · 80×15
<a href="https://agentmods.dev/skills/larksuite/cli/lark-sheets"><img src="https://agentmods.dev/badge/skills/larksuite/cli/lark-sheets.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 297 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,184 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. Third-party audits
  • Socket pass 16 Sept 2026
  • Snyk pass 16 Sept 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found 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 $0.00297 $0.08184
Opus 5.5 $0.00119 $0.03274
Sonnet 5.5 $0.00059 $0.01637
Haiku 4.5 $0.00030 $0.00818

Measured 1mo ago against content hash dfbf915c719c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lark-sheets 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 1mo ago.

The scan reads SKILL.md. This mod also ships 9 executable files (scripts/lark_chart_quality_check.py, scripts/lark_chart_size_advisor.py, scripts/lark_chart_size_rules.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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

Copies of this mod

2 near-identical copies found in the catalogue:

skills/lark-sheets/SKILL.md · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sheets

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。

场景 → 命令速查

按当前动作选行;下一步必须 Read 该行 reference,读取完成前不得执行命令。只读命中的文档;含公式 / 样式等横切动作时再读对应规范,禁止用目录枚举代替 Read。

你要做的事 ✅ 正确写法 动手前读(先 Read 再动手)
读数据 +csv-get(纯值/CSV)、+cells-get(公式/样式/批注) 读 references/lark-sheets-read-data.md
写入数据 +csv-put(无类型歧义纯文本)、+table-put(typed;量值/真日期;标签/编号/前导零/文本数字用 object,禁裸 csv-put)、+cells-set(公式/富写入)、+cells-set-style(样式)、+cells-set-image(单元格图片) 读 references/lark-sheets-write-cells.md
格式继承(新列/新行) 物理插行 / 插列用 +dim-insert --inherit-style before|after;往已有空白区域扩写用 +range-copy --paste-type formats 先铺样式再写值 读 references/lark-sheets-range-operations.md;插行插列再读 references/lark-sheets-sheet-structure.md
工作簿操作 +workbook-create、+workbook-info、+workbook-import、+sheet-copy、+revision-get、+workbook-export 读 references/lark-sheets-workbook.md
行列操作 排序用 +range-sort 原子移动整行;合并 / 取消合并用 +cells-merge / +cells-unmerge;清空内容才用 +cells-clear;尺寸用 +cols-resize / +rows-resize 读 references/lark-sheets-range-operations.md;涉结构布局再读 references/lark-sheets-sheet-structure.md
美化收尾 +styles-put 读 references/lark-sheets-styles-put.md
子表结构 +sheet-info、+dim-insert;删整行 / 列用 +dim-delete,不能用 clear 代替 读 references/lark-sheets-sheet-structure.md
画图表 / 可视化 / 柱状图 / 折线图 / 饼图 / 趋势 / 占比 单图用 +chart-create-basic,多图用扁平输入的 +batch-chart-create;改已有图的数据源用 +chart-data-update、配置用 +chart-config-update;只有语义 shortcut 表达不了的单系列 / 单数据点 / 高级字段才用 +chart-create / +chart-update,且只提交必要的局部 properties。动手前先断言每张图的类型、横轴字段、分组字段和目标张数,画完 +chart-list 逐项核;图片迁移成真图表后删除并复查原浮动图片 读 references/lark-sheets-chart.md;含透视 / 分组汇总再读 references/lark-sheets-pivot-table.md
分组汇总 / 透视 +pivot-create 读 references/lark-sheets-pivot-table.md
筛选 / 只看符合条件的行 +filter-create 读 references/lark-sheets-filter.md
查找 / 替换文本 +cells-search、+cells-replace 读 references/lark-sheets-search-replace.md
条件格式 / 条件高亮 / 数据条 / 色阶 随数据变化的标色用 +cond-format-create;固定刷色只用于用户点名要静态着色 读 references/lark-sheets-conditional-format.md
插图:自由摆放的装饰 +float-image-create 读 references/lark-sheets-float-image.md
迷你图 / 单元格内趋势线 +sparkline-create 读 references/lark-sheets-sparkline.md
批量清除多区域 +cells-batch-clear 读 references/lark-sheets-batch-update.md(high-risk)
复核编辑变更 / 取版本间差异 +changeset-get 读 references/lark-sheets-changeset.md
保存多份筛选状态 / 命名筛选视图 +filter-view-create;视图与 +filter-create 相互独立、可在同一子表共存 读 references/lark-sheets-filter-view.md
查编辑历史 / 回滚到历史版本 +history-list 取版本,+history-revert(high-risk,异步)回滚后用 +history-revert-status 轮询 读 references/lark-sheets-history.md

Read the full file on GitHub · 140 lines

Files

What ships with it

29 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.

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. 1mo ago Changed · -115 lines · +40 tokens per session dfbf915c719c
  2. 1mo ago Changed · +2 lines e2387f34558b
  3. 1mo ago Changed · +1 lines 09393e1be052
  4. 1mo ago First seen · 252 lines · 257 tokens per session scan A 8984c32687cc

Subscribe to this mod's changes

lark-sheets is a skill published in the GitHub repository larksuite/cli (17,724 stars, last pushed 3d ago), licensed MIT. It adds 297 tokens to every session and 8,184 once invoked, about $0.0012 per session on Opus 5.5. 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.