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.
git clone --depth 1 https://github.com/cloveric/tarocubnpx agentmods add skills/cloveric/tarocub/lark-bot-permissionsWrote 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/cloveric/tarocub/lark-bot-permissions)<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.
<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>- NVIDIA SkillSpector warn
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.
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 | $0.00157 | $0.02020 |
| Opus 5 | $0.00078 | $0.01010 |
| Sonnet 5 | $0.00031 | $0.00404 |
| Haiku 4.5 | $0.00016 | $0.00202 |
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.
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-messagesgroup (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.
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.
- 9d ago First seen · 139 lines · 157 tokens per session scan A 3323899a85fc
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.
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.
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.
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.
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…
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…
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.