lark-bot-permissions

lark-bot-permissions is a skill for Claude Code from cloveric/tarocub. It costs 157 tokens per session (2,020 once invoked), scanned A, original, MIT.

A browser-driven helper for opening permission scopes for an existing Feishu bot app. Feishu is a workplace collaboration platform, and permission scopes control what a bot can read or do.

In plain words
What is it for?
Use it to log in with a QR code, import a group of permissions, request approval, verify the result, and restart the bot instance.
Why use it?
It removes the need to find and complete the Feishu developer-console steps manually. It also distinguishes bot permissions from actions performed through a user's own login.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is node dist/src/index.js lark permissions.

Good fit Use it to log in with a QR code, import a group of permissions, request approval, verify the result, and restart the bot instance.

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/cloveric/tarocub
agentmods
npx agentmods add skills/cloveric/tarocub/lark-bot-permissions

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.

agentmods badge for lark-bot-permissions

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloveric/tarocub/lark-bot-permissions/github.svg)](https://agentmods.dev/skills/cloveric/tarocub/lark-bot-permissions)
Your own site
<a href="https://agentmods.dev/skills/cloveric/tarocub/lark-bot-permissions"><img src="https://agentmods.dev/badge/skills/cloveric/tarocub/lark-bot-permissions/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 lark-bot-permissions

Your own site · 80×15
<a href="https://agentmods.dev/skills/cloveric/tarocub/lark-bot-permissions"><img src="https://agentmods.dev/badge/skills/cloveric/tarocub/lark-bot-permissions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,020 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 Tool Misuse · line 136
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Rogue Agent · line 18
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Rogue Agent · line 116
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 $0.00157 $0.02020
Opus 5 $0.00078 $0.01010
Sonnet 5 $0.00031 $0.00404
Haiku 4.5 $0.00016 $0.00202

Measured 9d ago against content hash 3323899a85fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

lark-bot-permissions 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.

.claude/skills/lark-bot-permissions/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grant Feishu scopes to a TaroCub bot (console import via browser)

Productizes the manual flow: log into the Feishu developer console, bulk-import a scope group for a bot's app, 申请开通, verify it's live, restart the instance.

When this is needed (and when it is NOT)

  • Needed — the bot app must receive/send something it can't yet: non-@ group messages (im:message.group_msg), broad chat/member admin, or any advanced family imported as a tenant scope. The QR registration auto-grants NONE of these; they require a console import + (for non-personal apps) a version publish.
  • NOT needed — "create a Doc/Sheet/Calendar event as me". Those run through the operator's lark-cli user login (full user scopes), not the bot app, so they already work. Don't send the user to the console for these.
  • Creating a new bot is a different step: node dist/src/index.js lark setup --identity bot-only (QR PersonalAgent registration). This skill is only the permission part for an app that already exists.

Inputs

  • The instance name, e.g. ccfcc3 (state dir ~/.cctb/<inst>).
  • Which feature/scope group, e.g. "群里非@也回" → the group-messages group (im:message, im:message.group_msg). The exact JSON comes from step 1 — never hand-type scope strings.

Step 1 — Get the exact import JSON, appId, and console URL from the bridge

Do not guess scope names or URLs; the bridge prints them per feature group:

env CCTB_LARK_STATE_DIR="$HOME/.cctb/<inst>" CCTB_LARK_INSTANCE=<inst> TAROCUB_INSTANCE=<inst> \
  node dist/src/index.js lark permissions

Copy the line for the feature the user asked for, e.g.: • ordinary (non-@) group messages — /group all: {"scopes":{"tenant":["im:message","im:message.group_msg"]}} and note the app's permission URL: https://open.feishu.cn/app/<appId>/auth (also printed by lark provision as the "permissions page" line).

Step 2 — Browser session + Feishu console login

The browser is agent-browser (its own managed Chrome — NOT the user's main one), session name feishu. Saved console auth lives at ~/.cctb/feishu-console-auth.json.

Read the full file on GitHub · 139 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 · 139 lines · 157 tokens per session scan A 3323899a85fc

Subscribe to this mod's changes

lark-bot-permissions is a skill published in the GitHub repository cloveric/tarocub (12 stars, last pushed today), licensed MIT. It adds 157 tokens to every session and 2,020 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

shogun-screenshot

A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.

yohey-w/multi-agent-shogun · 149 tokens

browser-doctor

Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.

jmagly/aiwg · 56 tokens

browser-reset

Reconfigure the browser-control wiring. Rotate the Playwright MCP Bridge token, switch the target browser, or fully tear down the AIWG registration and provider injection. Walks the user through extension UI regeneration where needed; respects human-authorization gates for destructive operations.

jmagly/aiwg · 55 tokens

browser-setup

Interactive wizard that wires up @playwright/mcp end-to-end — detects the user's browsers, walks through Playwright MCP Bridge extension install, captures the per-install token, registers the MCP server in the AIWG registry with --extension and the env block, injects into the active provider's config, and verifies the…

jmagly/aiwg · 69 tokens

open-compute-bridge

Bindet das model-agnostische Computer-Use-Modul open-compute (Screenshot-Wahrnehmung, Windows-UIA-Elementklicks, sicherheitsgegatete Aktionen) fuer ALLE Agenten des Systems ein -- Claude Code, Codex und agy/Antigravity. Nutzen, wenn ein Dienst eine interaktive GUI- oder Browser-Aktion braucht, die kein reiner…

ellmos-ai/skills · 149 tokens

node-backend

Node.js backend development patterns for Express, NestJS, Fastify, and Hono. Use when implementing APIs, authentication, middleware, services, and server-side logic with Node.js and TypeScript. Provides project structure, code patterns, and best practices.

shahtuyakov/claude-setup · 55 tokens