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-approvalnpx skills add DropFan/claude-code-plugins --skill lark-approvalgit 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 | $0.00091 | $0.02151 |
| Opus 5 | $0.00046 | $0.01076 |
| Sonnet 5 | $0.00018 | $0.00430 |
| Haiku 4.5 | $0.00009 | $0.00215 |
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 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.
This is a copy
98% identical to lark-approval — 15 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.
How it starts
The opening of the file, as written. The whole thing — 111 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。）
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
所有命令默认 --as user（审批是人的动作）。调用前先按需读取 references 下对应的文件，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-cli ... --help、lark-cli schema 等方式补充确认字段。
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 lark-approval，不要让渡给 lark-task。
明确归 lark-approval 的高优先级语义
出现以下任一语义时，优先走 lark-approval：
- 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 lark-approval。只有当用户处理的是非审批类任务/待办时，才走 lark-task。
选哪个命令
| 想做什么 | 命令 | 按需读取 reference |
|---|---|---|
| 搜可发起定义 | approvals search |
lark-approval-approvals-search.md |
| 看审批定义详情/提单前确认表单与流程 | approvals get |
lark-approval-approvals-get.md |
| 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 | instances create |
lark-approval-initiate.md |
| 查待办/已办 | tasks query（topic：1待办 2已办 17未读 18已读） |
lark-approval-tasks-query.md |
| 看表单/进度/当前节点 | instances get |
lark-approval-instances-get.md |
| 同意审批 | tasks approve |
lark-approval-tasks-approve.md |
| 拒绝审批 | tasks reject |
lark-approval-tasks-reject.md |
| 转交审批 | tasks transfer |
lark-approval-tasks-transfer.md |
| 加签审批 | tasks add_sign |
lark-approval-tasks-add-sign.md |
| 退回审批 | tasks rollback |
lark-approval-tasks-rollback.md |
| 催办审批 | tasks remind |
lark-approval-tasks-remind.md |
| 撤回已发起审批 | instances cancel |
lark-approval-instances-cancel.md |
| 给审批实例追加抄送 | instances cc |
lark-approval-instances-cc.md |
| 按定义查已发起审批 | instances initiated |
lark-approval-instances-initiated.md |
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 4.9 KB
- references/lark-approval-approvals-search.md 4.0 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 4.5 KB
- references/lark-approval-instances-cancel.md 3.1 KB
- references/lark-approval-instances-cc.md 4.8 KB
- references/lark-approval-instances-get.md 5.8 KB
- references/lark-approval-instances-initiated.md 5.4 KB
- references/lark-approval-tasks-add-sign.md 5.8 KB
- references/lark-approval-tasks-approve.md 3.6 KB
- references/lark-approval-tasks-query.md 4.1 KB
- references/lark-approval-tasks-reject.md 3.1 KB
- references/lark-approval-tasks-remind.md 3.6 KB
- references/lark-approval-tasks-rollback.md 4.4 KB
- references/lark-approval-tasks-transfer.md 4.5 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 · 111 lines · 91 tokens per session scan A 22faa1e549ee
lark-approval is a skill published in the GitHub repository DropFan/claude-code-plugins (7 stars, last pushed 27d ago), licensed MIT. It adds 91 tokens to every session and 2,151 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to lark-approval, differing in 15 lines, and is treated as a copy.
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.