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/dropfan/claude-code-plugins/lark-sheetsnpx skills add DropFan/claude-code-plugins --skill lark-sheetsgit clone --depth 1 https://github.com/DropFan/claude-code-pluginsWhat 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 | $0.00259 | $0.11372 |
| Opus 5 | $0.00130 | $0.05686 |
| Sonnet 5 | $0.00052 | $0.02274 |
| Haiku 4.5 | $0.00026 | $0.01137 |
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 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 — 246 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。)
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。
术语约定
下列词在本 skill 各文档中可能交替出现,但指同一对象;解析用户口语时按此映射,不要当成不同概念:
| 标准用语 | 同义 / 口语(均指同一对象) | 说明 |
|---|---|---|
| 工作表(sheet) | 子表、tab、标签页 | spreadsheet 内的单张表;sheet_id 是其稳定标识 |
| 电子表格(spreadsheet) | 工作簿、表格 | 顶层容器;由 --url 或 --spreadsheet-token 定位 |
| reference_id | id | 表内对象的稳定标识,即各对象主键 flag 接受的值(见下表)。⚠️ 与 lark-sheets-float-image 的 --image-uri(图片上传句柄)不是一回事,后者不属于 reference_id |
每类对象用各自的主键 flag 定位(命名不统一,按此表对照,不要凭直觉拼):
| 对象 | 主键 flag | 对象 | 主键 flag |
|---|---|---|---|
| 工作表 sheet | --sheet-id |
条件格式规则 | --rule-id |
| 图表 chart | --chart-id |
筛选视图 | --view-id |
| 透视表 pivot | --pivot-table-id |
迷你图(按组) | --group-id |
| 浮动图片 | --float-image-id |
飞书表格编辑准则(动手前必守,所有编辑类任务一律生效)
下列准则横切所有飞书表格任务,动手前先过一遍——即使你是被索引直接路由进某个工具参考也一律生效。每条只给一句话纲要,展开与边界见括注的 reference。
- 最小改动:除任务要改的单元格 / 列外,原表其它单元格、行列结构、Sheet 名、合并区、格式 1:1 保持;中间结果放原数据右侧或新建空白 Sheet,禁止删 / 改名 / 隐藏 / 移动已存在 Sheet;改写类任务精确圈定行列,不该转的原值 1:1 保留。
- 真实写回 + 回读校验:交付必须是对在线表格的真实写入,写完用
+csv-get/+cells-get/+<对象>-list回读确认实际生效——写操作返回ok只代表请求被接受、不代表结果符合预期;写公式后查错误码、筛选 / 排序后核对前几行、删除 / 清空后确认已空。禁止只在文本里声称"已完成"。 - 读全再写:批量填充 / 补齐 / 修正类任务先确认真实数据末行再写,只探前 N 行会漏写表尾(确定末行流程见
lark-sheets-read-data)。 - 公式优先于硬编码:能用公式表达的计算(总计 / 占比 / 增长率 / 提取 / 查找)一律写公式而非静态值;凡可由表内其它单元格推导的派生值默认就用公式,即使用户没说"联动 / 自动更新";写任何飞书公式前先读
lark-sheets-formula-translation,而且只要公式真实写入表格,收尾默认就要继续跑lark-sheets-formula-verify的+formula-verify,直到status='success'。 - 续写 / 扩展继承样式:续写、补齐、复制区块、新增行列时禁止只读值只写值,必须连带
cell_styles+border_styles+ 合并 + 行高一起继承(清单见lark-sheets-write-cells,四边框最易漏)。 - 多步写入合并
+batch-update:多个连续写入、或同一工具对多区域重复调用,合并为单次原子+batch-update(语义见lark-sheets-batch-update)。 - 分组汇总用透视表:"按 X 统计 Y / 分组汇总 / 各类数量金额"用
+pivot-{create|update|delete},禁止用 SUMIF / 本地脚本拼一张假透视表。 - 拆成可验证 checklist:落地前把指令拆成所有"独立可验证子要点",逐点
assert全过才交付(多维排序每维一点、多目标每目标一点、范围类核起 / 末 / 边界);只做第一个要点属违规。 - 全量处理前置断言条数:翻译 / 打标 / 批量公式落地等逐条任务,先把预期条数硬编码再
assert actual == expected,禁止输出"已完成前 N 条,剩余继续"的半成品。
What ships with it
20 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-sheets-batch-update.md 15 KB
- references/lark-sheets-changeset.md 5.1 KB
- references/lark-sheets-chart.md 21 KB
- references/lark-sheets-conditional-format.md 11 KB
- references/lark-sheets-filter-view.md 7.8 KB
- references/lark-sheets-filter.md 7.2 KB
- references/lark-sheets-float-image.md 11 KB
- references/lark-sheets-formula-translation.md 14 KB
- references/lark-sheets-formula-verify.md 5.8 KB
- references/lark-sheets-history.md 5.1 KB
- references/lark-sheets-pivot-table.md 14 KB
- references/lark-sheets-range-operations.md 20 KB
- references/lark-sheets-read-data.md 23 KB
- references/lark-sheets-search-replace.md 5.3 KB
- references/lark-sheets-sheet-structure.md 11 KB
- references/lark-sheets-sparkline.md 7.3 KB
- references/lark-sheets-visual-standards.md 17 KB
- references/lark-sheets-workbook.md 26 KB
- references/lark-sheets-write-cells.md 55 KB
- scripts/sheets_df.py 1.1 KB runs code
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 · 246 lines · 259 tokens per session scan A 1b4bd0aff3ce
lark-sheets is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 259 tokens to every session and 11,372 once invoked, about $0.0013 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
automating-numbers
Automates Apple Numbers via JXA with AppleScript dictionary discovery. Use when asked to "automate Numbers spreadsheets", "create spreadsheets programmatically", "JXA Numbers scripting", or "bulk data operations in Numbers". Focuses on sheets, tables, ranges, batch I/O, clipboard shim, and high-performance data…
automating-excel
Automates Microsoft Excel on macOS via JXA with AppleScript dictionary discovery. Use when asked to "automate Excel spreadsheets", "JXA Excel scripting", "Excel macOS automation", or "bulk Excel data operations". Focuses on workbooks, worksheets, ranges, 2D arrays, performance toggles, and VBA escape hatches.
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.
agent-check
Validate custom agent file format and structure. Use after creating or editing an agent, before committing agent changes, or when an agent fails to load.
skill-check
Validate skill/command file format and structure. Use after creating or editing a skill, before committing skill changes, or when a skill fails to load or trigger.