feishu-cli

feishu-cli is a skill for Claude Code, Codex from fanfan-de/anybox. It costs 58 tokens per session (1,096 once invoked), scanned A, original, MIT.

A command-line tool for operating Feishu (Lark), a workplace collaboration platform, from a terminal.

In plain words
What is it for?
Use it for messages, documents, calendars, spreadsheets, tasks, email, meetings, approvals, and other Feishu operations.
Why use it?
It lets coding agents and shell scripts work with Feishu services without manually navigating the web app.

Skill for Claude CodeCodex

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

Good fit Use it for messages, documents, calendars, spreadsheets, tasks, email, meetings, approvals, and other Feishu operations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fanfan-de/anybox/feishu-cli
Install

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.

Any agent
npx skills add fanfan-de/anybox --skill feishu-cli
Clone the repo
git clone --depth 1 https://github.com/fanfan-de/anybox

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-cli

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/fanfan-de/anybox/feishu-cli"><img src="https://agentmods.dev/badge/skills/fanfan-de/anybox/feishu-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,096 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 14
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
  • medium Excessive Agency · line 14
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium MCP Rug Pull · line 29
    npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.
    Fix: Pin the version: npx @scope/[email protected]
How audits are shown
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 $0.00058 $0.01096
Opus 5 $0.00029 $0.00548
Sonnet 5 $0.00012 $0.00219
Haiku 4.5 $0.00006 $0.00110

Measured 9d ago against content hash 3e3607793987, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

feishu-cli 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 9d 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.

plugins/Anybox-Plugins/feishu-cli/skills/feishu-cli/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feishu CLI

Use this skill when the user asks to use Feishu, Lark, Feishu CLI, Lark CLI, or lark-cli from the agent shell. This is a CLI-first workflow, not an MCP workflow. Use shell commands to call lark-cli directly.

Operating Model

  • Prefer lark-cli for Feishu/Lark work instead of direct HTTP calls when this skill is active.
  • Treat lark-cli as the owner of app configuration, OAuth login, scopes, user/bot identity selection, and local credential storage.
  • Do not ask the user for access tokens, refresh tokens, app secrets, or cookies. Do not print or save secrets.
  • Use --format json for read commands whenever supported so results are machine-readable.
  • Keep commands narrow and explicit. Avoid raw OpenAPI calls unless a shortcut or service command cannot do the job.

Setup Checks

First check whether the CLI is available:

lark-cli --version

If it is missing, tell the user it needs to be installed, then use the official installer when the user wants you to proceed:

npx @larksuite/cli@latest install

After installation, initialize app configuration if needed:

lark-cli config init --new

Then check login state:

lark-cli auth status

If not logged in, start login with recommended scopes:

lark-cli auth login --recommend

For agent-driven browser handoff, use non-blocking login when appropriate and relay only the authorization URL or next safe instruction to the user:

lark-cli auth login --recommend --no-wait

Safety Rules

  • Before sending messages, modifying documents, updating calendars, changing records, approving requests, deleting anything, or calling raw write APIs, get explicit user confirmation unless the user has already clearly asked for that exact action.
  • For write commands that support it, run --dry-run first and summarize the intended change before executing the real command.
  • Do not add the Feishu/Lark bot to public or broad group chats as part of setup. If group access is needed, ask the user to handle membership deliberately.
  • Never run broad destructive commands such as bulk delete, recursive permission changes, or mass updates unless the user explicitly scopes the target set.
  • When a command fails for missing scope or permission, report the missing capability and use lark-cli auth check or lark-cli auth login with a narrower domain or scope instead of retrying blindly.

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 58 tokens per session scan A 3e3607793987

Subscribe to this mod's changes

feishu-cli is a skill published in the GitHub repository fanfan-de/anybox (57 stars, last pushed 29d ago), licensed MIT. It adds 58 tokens to every session and 1,096 once invoked, about $0.0003 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 2026-09-03.

Related

Other skills, from other repositories