feishu-approval

feishu-approval is a skill for Claude Code, Codex from alextangson/feishu_skills. It costs 17 tokens per session (1,422 once invoked), scanned A, original, MIT.

A Feishu approval tool for creating approval requests and checking their progress through Feishu's API. Feishu is a workplace collaboration platform commonly used by Chinese companies.

In plain words
What is it for?
Use it to start approval requests, check their status or details, list requests, approve or reject them, cancel them, transfer them, and send reminders.
Why use it?
It removes the need to manually build API requests for starting and tracking approvals. It also covers common actions such as approving, cancelling, transferring, and reminding about requests.

Skill for Claude CodeCodex

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is TOKEN="$(./scripts/get_feishu_token.sh)".

Good fit Use it to start approval requests, check their status or details, list requests, approve or reject them, cancel them, transfer them, and send reminders.

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/alextangson/feishu_skills
agentmods
npx agentmods add skills/alextangson/feishu_skills/feishu-approval

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 feishu-approval

README.md
[![agentmods](https://agentmods.dev/badge/skills/alextangson/feishu_skills/feishu-approval/github.svg)](https://agentmods.dev/skills/alextangson/feishu_skills/feishu-approval)
Your own site
<a href="https://agentmods.dev/skills/alextangson/feishu_skills/feishu-approval"><img src="https://agentmods.dev/badge/skills/alextangson/feishu_skills/feishu-approval/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 feishu-approval

Your own site · 80×15
<a href="https://agentmods.dev/skills/alextangson/feishu_skills/feishu-approval"><img src="https://agentmods.dev/badge/skills/alextangson/feishu_skills/feishu-approval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00017 $0.01422
Opus 5 $0.00009 $0.00711
Sonnet 5 $0.00003 $0.00284
Haiku 4.5 $0.00002 $0.00142

Measured 11d ago against content hash 2117035249b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

feishu-approval scanned grade A with 1 finding 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 11d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X GET "https://open.feishu.cn/open-apis/approval/v4/approvals?page_size=10" \
feishu-approval/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

飞书审批

通过 Approval API 创建和查询审批实例。

Base URL: https://open.feishu.cn/open-apis/approval/v4

认证与 Token 获取

feishu_skills 根目录执行共享脚本:

TOKEN="$(./scripts/get_feishu_token.sh)"

请求头统一使用 Authorization: Bearer ${TOKEN}

如果业务接口返回 token 无效、过期或 401,强制刷新后仅重试一次原请求:

TOKEN="$(./scripts/get_feishu_token.sh --force-refresh)"

环境变量:

  • FEISHU_APP_ID
  • FEISHU_APP_SECRET

本地缓存: ./.feishu_token_cache.json(未过期直接复用,默认提前 5 分钟刷新)


审批实例

API 端点 方法 请求体示例 说明
创建实例 /instances POST {"approval_code":"7C46...","user_id":"ou_xxx","form":"{\"widget1\":\"value1\"}"} 发起审批
查询实例 /instances/{instance_id} GET - 获取审批状态
审批操作 /instances/{instance_id}/approve POST {"comment":"同意","task_id":"xxx"} 同意/拒绝审批
撤回审批 /instances/{instance_id}/cancel POST {"user_id":"ou_xxx"} 申请人撤回
转交审批 /instances/{instance_code}/transfer POST {"user_id":"ou_xxx","transfer_user_id":"ou_yyy","comment":"转交"} 转交给他人
催办审批 /instances/{instance_id}/urge POST - 发送催办提醒
获取实例列表 /instances GET 查询参数:page_size=50&page_token=xxx&user_id=ou_xxx 支持筛选参数(分页)
查询实例详情 /instances/detail POST {"instance_code":"xxx"} 查询完整详情

创建实例:

{
  "approval_code": "7C468A54-8745-2245-9675-08B7C63E7A85",
  "user_id": "ou_xxx",
  "form": "{\"widget1\":\"value1\"}"
}

审批任务

API 端点 方法 请求体示例 说明
获取任务列表 /tasks GET - 查询待办任务
获取任务详情 /tasks/{task_id} GET - 查询任务详情
审批任务 /tasks/{task_id}/approve POST {"comment":"同意"} 处理审批任务
转交任务 /tasks/{task_id}/transfer POST {"transfer_user_id":"ou_xxx"} 转交任务

审批定义

API 端点 方法 请求体示例 说明
获取定义列表 /approvals GET - 查询所有审批模板
获取定义详情 /approvals/{approval_code} GET - 查询模板详情
获取定义表单 /approvals/{approval_code}/forms GET - 查询表单字段定义

Read the full file on GitHub · 156 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. 11d ago First seen · 156 lines · 17 tokens per session scan A 2117035249b8

Subscribe to this mod's changes

feishu-approval is a skill published in the GitHub repository alextangson/feishu_skills (65 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 1,422 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.