Borrowing it
Nothing to install: this file belongs to iyuenan3/worklog-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/iyuenan3/worklog-kit/main/.agents/skills/feishu-setup/SKILL.mdgit clone --depth 1 https://github.com/iyuenan3/worklog-kitWrote 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.
[](https://agentmods.dev/skills/iyuenan3/worklog-kit/feishu-setup)<a href="https://agentmods.dev/skills/iyuenan3/worklog-kit/feishu-setup"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/feishu-setup/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.
<a href="https://agentmods.dev/skills/iyuenan3/worklog-kit/feishu-setup"><img src="https://agentmods.dev/badge/skills/iyuenan3/worklog-kit/feishu-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00110 | $0.01393 |
| Opus 5.5 | $0.00044 | $0.00557 |
| Sonnet 5.5 | $0.00022 | $0.00279 |
| Haiku 4.5 | $0.00011 | $0.00139 |
Grade B, and why
feishu-setup scanned grade B 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 2mo 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
chmod 600 worklog.feishu.local.json How it starts
The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
feishu-setup:可选飞书连接器向导
目标:让本机
.agents/skills/worklog-ingest/connectors/feishu/在无人值守 ingest 中可用。Feishu 与 lark-cli 完全选配,默认和 worklog 在同一台电脑。未选择飞书时不安装、不认证、不生成任何配置。
Step 1:安装可选依赖
npm i -g @larksuite/cli
bash -lc 'lark-cli --version'
没有 npm 时先安装 Node。后续 lark-cli 都由连接器经登录 shell 启动,因为 node 的 PATH 可能只在 shell 初始化文件中存在。
安装与扫码授权属于交互式配置,按当前客户端逐条审阅并授权即可。不要把 Bash(lark-cli:*) 或 npm 全局安装通配永久追加到 .claude/settings.json。夜间 ingest 只调用仓内受检的 check.sh / fetch.sh,已有固定包装器权限足够。
Step 2:应用凭证与授权
- 运行
lark-cli config init,按飞书开放平台说明配置自建应用与所需 scope。 - 运行
lark-cli auth login完成 Device Flow 扫码授权。 - 运行
lark-cli auth status与lark-cli auth scopes核对身份和权限。
企业租户不允许自建应用或不给 scope 时,停止配置飞书并说明“该租户暂不支持此可选连接器”。不要修改其他 sources,ingest 其余部分照常运行。
Step 3:macOS 无人值守适配
macOS 钥匙串在夜间非交互会话中可能不可用。只有用户理解并接受“凭证从钥匙串降级到 lark-cli 本地配置文件,保护强度降低”后才运行:
bash -lc 'lark-cli config keychain-downgrade'
凭证仍在 vault 之外,禁止复制 app secret、token 或 lark-cli 凭证到 worklog 配置。
Step 4:发现并确认采集范围
bash -lc 'lark-cli im +chat-search --query "<关键词>"'
bash -lc 'lark-cli im +chat-list --types=p2p,group'
先确认本人 open_id,优先使用 ou_ 开头的唯一值,姓名只作为旧格式兼容。再让用户逐项选择:
- 少量已选会话,以及每个会话的
own / mentions / full。 - 可选生效日期
active_from / active_until。 - 是否额外扫描全部 p2p,默认
none。 - 是否扫描未选群的本人发言与 @ 触点,默认
none。 - 是否扫描相关文档,默认关闭。
mentions、full、全部 p2p 与文档扫描都会让他人的内容进入本机临时文件和当前 Agent 上下文。启用前复述 connectors/README.md 的 IM 数据使用须知并取得明确同意。不要用“负责人”“组长”等角色推断读取范围,公共配置只表达用户亲自选择的采集级别和日期。
Step 5:写本地作用域与非敏感 source
在 vault 根生成 worklog.feishu.local.json,格式完整遵循 connectors/README.md。该文件包含 open_id、chat_id 与用户选择,必须已被 .gitignore 排除。写后运行:
chmod 600 worklog.feishu.local.json
git check-ignore -q worklog.feishu.local.json
若权限或 ignore 检查失败,先修复,不要继续。然后只在受 Git 跟踪的 worklog.config.yaml 中写入不含身份和会话坐标的 source:
- {type: im, provider: feishu, via: lark-cli, scope_file: worklog.feishu.local.json, on_unreachable: note}
已有 v1 chats + me + record_others source 仍可使用。迁移时先生成本地作用域并试拉成功,再把 tracked config 改为 scope_file,不要在同一晚同时保留两条 Feishu source。
What ships with it
1 file 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.
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.
- 2mo ago First seen · 98 lines · 110 tokens per session scan B b6d6769e339d
feishu-setup is a skill published in the GitHub repository iyuenan3/worklog-kit (11 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,393 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
feishu-setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| feishu-setupiyuenan3/worklog-kit | Skill | 11 | 3mo ago | Apache-2.0 | B | 110 | Codex |
| orbit-notionnexu-io/open-design | Skill | 106k | yesterday | Apache-2.0 | A | 117 | Claude Code, Codex |
| agentmailpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 30 | Claude Code, Codex |
| Cortexdanielmiessler/LifeOS | Skill | 20k | yesterday | MIT | A | 184 | Claude Code |
| rowboat-spacesrowboatlabs/rowboat | Skill | 18k | yesterday | Apache-2.0 | A | 60 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| pinchtab-mcppinchtab/pinchtab | Skill | 11k | 10d ago | MIT | A | 52 | Claude Code, Codex |