What is feishu-cli CLAUDE.md?

A project guide for feishu-cli, a command-line program for Feishu that handles documents, messages, permissions, approvals, knowledge bases, files, and comments. It explains the project's tools, structure, build commands, and quality checks.

Use it when developing feishu-cli, including building its Go code, running tests and static checks, and verifying commands with the compiled program.

It gives coding agents the repository-specific rules needed to build, test, and verify changes correctly.

How riba2534/feishu-cli configures Claude Code

About the project

feishu-cli is a command-line tool for controlling the Feishu collaboration platform, including documents, knowledge bases, spreadsheets, messages, calendars, and tasks. People and AI coding agents use it to manage Feishu through commands, with particular support for converting Markdown to Feishu documents and back. Its catalogue skills provide ready-made AI-agent workflows for these operations.

riba2534/feishu-cli · 1,425 stars · on GitHub

Reuse

Borrowing it

Nothing to install: this file belongs to riba2534/feishu-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/riba2534/feishu-cli/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/riba2534/feishu-cli

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/riba2534/feishu-cli/claude-md/github.svg)](https://agentmods.dev/instructions/riba2534/feishu-cli/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/riba2534/feishu-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/riba2534/feishu-cli/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/riba2534/feishu-cli/claude-md"><img src="https://agentmods.dev/badge/instructions/riba2534/feishu-cli/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 13,527 This file is loaded in full into every session.

When invoked 13,527 The same file — it is already loaded in full.

Security scan C 2 findings. 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.

Model	Per session	Once invoked
Fable 5.1	$0.13527	$0.13527
Opus 5.5	$0.05411	$0.05411
Sonnet 5.5	$0.02705	$0.02705
Haiku 4.5	$0.01353	$0.01353

Measured 15d ago against content hash 42f0fb5398f7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

feishu-cli CLAUDE.md scanned grade C with 2 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 15d 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.

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

7. 验证：`curl -fsSL https://raw.githubusercontent.com/riba2534/feishu-cli/main/install.sh | bash`

Makes network callslowCapability

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

7. 验证：`curl -fsSL https://raw.githubusercontent.com/riba2534/feishu-cli/main/install.sh | bash`

CLAUDE.md · 535 lines

How it starts

The opening of the file, as written. The whole thing — 535 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md - 飞书 CLI 项目指南

项目概述

feishu-cli 是一个功能完整的飞书开放平台命令行工具，核心功能是 Markdown ↔ 飞书文档双向转换，支持文档操作、消息发送、权限管理、审批查询、知识库操作、文件管理、评论管理等功能。

技术栈

组件	选型	说明
CLI 框架	github.com/spf13/cobra	子命令、自动补全
飞书 SDK	github.com/larksuite/oapi-sdk-go/v3	官方 SDK
配置管理	github.com/spf13/viper	YAML/环境变量
Markdown	github.com/yuin/goldmark	GFM 扩展支持

项目结构：cmd/（CLI 命令）、internal/auth（OAuth）、internal/client（API 封装）、internal/converter（Markdown 转换器）、skills/（Claude Code 技能）。按需 ls 查看详情。

开发指南

构建与测试

go build -o feishu-cli .          # 快速构建
make build                        # 构建到 bin/feishu-cli
make build-all                    # 多平台构建（发版用，自动注入版本号）
make release-package VERSION=vX.Y.Z  # 发版打包：规范命名 tar.gz + checksums.txt + 结构自检
go test ./...                     # 运行所有测试
go vet ./...                      # 静态检查
make check-privacy                # 隐私扫描（内部邮箱、企业前缀域名、疑似真实 token）

CI（.github/workflows/ci.yml）在 PR 与 push main 时运行 gofmt / vet / test / check-skills / check-privacy，不使用任何飞书凭证。

质量标准（任何改动提交前必须满足）

实物验证铁律：任何改动，都必须使用实际编译的二进制产物进行验证。 先 go build -o feishu-cli .（或 make build）编译当前代码，再用编译出的二进制实跑受影响的命令确认行为符合预期（读操作真实调用；写操作优先 --dry-run，必要时在测试文档/画板上真实执行）。禁止只凭 go vet、单元测试或静态读代码就宣告完成；文档/技能中对 CLI 行为的描述，同样以新编译二进制的实跑结果为准。
基线全绿：gofmt -l cmd internal 无输出、go test ./...、go vet ./...、make check-privacy 通过（与 CI 一致）。
结论附证据：报告"已完成/已修复"必须附带验证命令及其输出（或退出码/截图），不做未验证的声明。
可执行文档必须实跑：README / skills 里给出的命令、脚本、示例，改动后逐条实跑；涉及可视化配色的改动，从仓库根运行 node skills/feishu-cli-visual/references/workflows/dataviz/scripts/validate_palette.js 复验定稿色板、 node skills/feishu-cli-visual/references/workflows/dataviz/scripts/check_docs.js 核查文档一致性，全绿才算完成。
Skill 结构校验：修改 skills/、CLI 命令或源码中的 Skill 路径后运行 make check-skills；该目标会先从当前源码重新构建 bin/feishu-cli，再检查 Skill 结构、引用和命令唯一归属。
隐私扫描：提交前运行 make check-privacy，并按下方"开发规范"第 9 条检查敏感信息。

发版有更严格的完整清单，见「发布 Release 规范」。

Read the full file on GitHub · 535 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.

15d ago Changed · +73 lines · +3,345 tokens per session 42f0fb5398f7
1mo ago First seen · 462 lines · 10,182 tokens per session scan C 11c76d012672

Subscribe to this mod's changes

feishu-cli CLAUDE.md is an instructions file published in the GitHub repository riba2534/feishu-cli (1,425 stars, last pushed 15d ago), licensed MIT. It adds 13,527 tokens to every session, about $0.0541 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 9,715 tokens

feishu-cli: Instructions file for Claude Code