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-basenpx skills add DropFan/claude-code-plugins --skill lark-basegit 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 | $0.00084 | $0.06897 |
| Opus 5 | $0.00042 | $0.03449 |
| Sonnet 5 | $0.00017 | $0.01379 |
| Haiku 4.5 | $0.00008 | $0.00690 |
Grade A, and why
lark-base 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 — 187 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。)
base
何时使用
使用本 skill:
- 用户明确提到 Base / 多维表格 / bitable,或给出
/base/链接。 - 用户要在 Base 内建表、改表、管理字段、写记录、查记录、配视图。
- 用户要在 Base 内做公式字段、lookup 字段、跨表计算、派生指标、筛选聚合、TopN、统计分析。
- 用户要管理 Base 表单、仪表盘、workflow、高级权限或角色。
- 用户要把旧 Base 聚合式命令或旧写法迁移到当前
lark-cli base +...shortcut。
不要使用本 skill:
- 只是认证、初始化配置、切换身份、处理 scope 或权限授权恢复,转
lark-shared。 - 把本地文件导入成 Base,或将 Base 导出为本地文件,转
lark-drive。 - 泛化数据分析、字段设计、公式讨论,但没有 Base/多维表格上下文。
使用边界
- Base 业务操作只使用
lark-cli base +...shortcut,不使用旧聚合式+table / +field / +record / +view / +history / +workspace。 - 执行 update 前必须先查当前 shortcut 的
--help或对应 reference。若命令要求完整配置,首次请求必须基于可信的当前配置执行 read-modify-write:只修改用户明确指定的内容,保留其他仍适用的可写配置,并按命令要求的结构提交。若命令支持局部/delta update,按其契约提交最小合法 payload;不得以不完整请求试错补参。 - Base CLI/OpenAPI 当前不支持视图行高、冻结列、列宽等 UI-only 外观设置。遇到这类需求,说明能力边界并停止,不要猜测未文档化参数或改走 raw API。
- 本地文件与 Base 之间的导入/导出转
lark-drive,具体格式、参数、路径限制和仅结构导出规则由lark-drive负责;导入完成后再回到 Base 命令。 - 在线复制 Base 使用
+base-copy,不要绕行导出/导入。 - 认证、初始化、scope、身份切换、权限不足恢复属于
lark-shared;Base 文档只保留会影响 Base 路径选择的权限规则。
先获取 Base Token 和所需 ID
进入任何需要目标 Base 的 shortcut 前,必须先拿到可用的 base_token,以及当前任务需要的 table_id / view_id / record_id / form_id / dashboard_id / workflow_id 等真实 ID;不要把完整 URL、wiki token、workspace token 或孤立 raw token 直接当作 --base-token。
- 用户输入 URL 或分享链接:先运行
lark-cli base +url-resolve --url "<url>" --as user,用返回的base_token和相关 ID 继续后续命令。 - Base/Wiki URL 的
table=query 参数实际表示当前选中的顶层 block,可能是数据表、仪表盘或 workflow;不要按参数名自行当成table_id。以+url-resolve返回的block_type以及table_id/dashboard_id/workflow_id为准;selection_source=url_query只说明 URL 当前选中了该 block,不代表它覆盖用户明确点名的目标。若用户点名的 dashboard 与block_name不一致,先用+dashboard-list按名称匹配;若只返回中性block_id,按 hint 用+base-block-list确认类型。 - 用户输入 Base 标题、关键词或不确定名称:先运行
lark-cli base +title-resolve --title "<keyword>" --as user;--title传入标题中的短关键词,不超过 30 个字符;过长标题先取最有区分度的短关键词;多候选时先让用户消歧,不要猜。 - 文档嵌入 Base 标签:直接读取
<bitable>/<base_refer>的token作为--base-token,table-id作为--table-id,view-id作为--view-id;孤立 raw token 不走+url-resolve。 - 仍无法定位且用户不是要新建 Base 时,先反问用户要操作哪一个 Base;用户要新建时才用
+base-create。
What ships with it
26 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/dashboard-block-data-config.md 14 KB
- references/formula-field-guide.md 54 KB
- references/lark-base-cell-value.md 5.5 KB
- references/lark-base-dashboard-block-get-data.md 24 KB
- references/lark-base-dashboard.md 12 KB
- references/lark-base-data-analysis-sop.md 11 KB
- references/lark-base-data-query-guide.md 2.8 KB
- references/lark-base-data-query.md 20 KB
- references/lark-base-field-create.md 4.4 KB
- references/lark-base-field-json.md 16 KB
- references/lark-base-field-update.md 9.4 KB
- references/lark-base-filter-condition.md 4.4 KB
- references/lark-base-form-detail.md 2.9 KB
- references/lark-base-form-questions-create.md 7.2 KB
- references/lark-base-form-questions-update.md 7.2 KB
- references/lark-base-form-submit.md 7.2 KB
- references/lark-base-record-batch-create.md 2.1 KB
- references/lark-base-record-batch-update.md 2.0 KB
- references/lark-base-record-history-list.md 1.4 KB
- references/lark-base-record-upsert.md 2.3 KB
- references/lark-base-role-guide.md 3.8 KB
- references/lark-base-view-set-filter.md 2.6 KB
- references/lark-base-workflow-guide.md 27 KB
- references/lark-base-workflow-schema.md 38 KB
- references/lookup-field-guide.md 18 KB
- references/role-config.md 21 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.
- 2d ago First seen · 187 lines · 84 tokens per session scan A b6e9cc0c9c02
lark-base is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 84 tokens to every session and 6,897 once invoked, about $0.0004 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
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.
session-relay
Continue real repository work between Claude Code, Codex CLI, and Grok Build with a privacy-bounded, drift-aware handoff packet. Use for cross-vendor takeover, context-limit checkpoints, multi-hop Claude→Codex→Grok relays, or receiving an existing Director packet. Use native resume commands for same-CLI history; never…
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.
skill-template
Generate custom skill/command from template. Use when creating a new skill or slash command from scratch, or scaffolding a skill file with correct frontmatter.