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/DropFan/claude-code-pluginsnpx agentmods add skills/dropfan/claude-code-plugins/lark-eventWrote 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/dropfan/claude-code-plugins/lark-event)<a href="https://agentmods.dev/skills/dropfan/claude-code-plugins/lark-event"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-event/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/dropfan/claude-code-plugins/lark-event"><img src="https://agentmods.dev/badge/skills/dropfan/claude-code-plugins/lark-event.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 | $0.00118 | $0.03056 |
| Opus 5.5 | $0.00047 | $0.01222 |
| Sonnet 5.5 | $0.00024 | $0.00611 |
| Haiku 4.5 | $0.00012 | $0.00306 |
Grade A, and why
lark-event 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 25d 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.
This is a copy
92% identical to lark-event — 11 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚙️ Cowork / Claude Desktop 执行环境说明（自动注入）
本技能依赖本地
lark-cli（@larksuite/cli，可用command -v lark-cli定位）及其~/.lark-cli登录态（应用密钥存于 macOS keychain）。在 Cowork 中运行任何
lark-cli命令时，必须在本地 macOS 上执行（使用 Desktop Commander 的start_process/interact_with_process，或其它本地 shell 工具），不要用隔离的 Linux 沙箱mcp__workspace__bash——沙箱里没有 lark-cli、也读不到 keychain。 执行前确保 npm 全局 bin 目录（npm prefix -g输出目录下的bin）在 PATH 中。（在 Claude Code 中可忽略本说明，lark-cli 在本机 shell 直接可用。）
Lark Events
Prerequisite: Read
../lark-shared/SKILL.mdfirst for authentication,--as user/botswitching,Permission deniedhandling, and safety rules.
Core commands
| Command | Purpose |
|---|---|
lark-cli event list [--json] |
List all subscribable EventKeys |
lark-cli event schema <EventKey> [--json] |
Show an EventKey's params and output schema |
lark-cli event consume <EventKey> [flags] |
Blocking consume; events → stdout NDJSON |
lark-cli event status [--json] [--fail-on-orphan] |
Inspect the local bus daemon status |
lark-cli event stop [--all] [--force] |
Stop the bus daemon |
Common flags
| Flag | Description |
|---|---|
--param key=value / -p |
Business params (repeatable; comma-separated for multi-value). Unknown keys fail with valid names listed inline |
--jq <expr> |
jq expression to filter / transform each event; empty output skips the event |
--max-events N |
Exit after N events. Default 0 = unlimited |
--timeout D |
Exit after duration D (e.g. 30s, 2m). Default 0 = no timeout. Whichever of --max-events / --timeout fires first wins |
--output-dir <dir> |
Write each event as a file (relative paths only; prevents traversal) |
--quiet |
Suppress ready/exit markers and per-event stderr diagnostics, including drop warnings. This can hide event loss. AI should not use this — it removes readiness and integrity signals |
--as user|bot|auto |
Identity for the session (see lark-shared) |
What ships with it
7 files 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.
- 25d ago Changed · +3 lines c28f253084be
- 1mo ago First seen · 168 lines · 118 tokens per session scan A c82f180f842b
lark-event is a skill published in the GitHub repository DropFan/claude-code-plugins (8 stars, last pushed 26d ago), licensed MIT. It adds 118 tokens to every session and 3,056 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 92% identical to lark-event, differing in 11 lines, and is treated as a copy.
Other skills, from other repositories
fly
Fly one thought to its destination across concurrent agents, on whatever the project and harness already have. Lands only when the user has accounted for every detail, never on an agent's say-so.
deepen
Hold an ask to the bar a top professional in its field would set — a deeper ask, never a bigger one. Use when an ask is clear but nothing yet names the sources, methods, target, or outside check the work will meet.
consult
Bring how named experts would think about the question. Use when the user wants expert thinking on a tradeoff, choice, or stuck problem — not a verdict.
setup
Use when installing or refreshing sound taste rules in a project — an explicit "sound setup", starting work in a repo with no .claude/sound/, or a taste-not-defined nudge. Also use to re-run after a stack change (new framework, new package in a monorepo).
auto-loop
TDD-based autonomous development loop with checkpoint recovery and observability changelog.
hook-template
Generate hook script from template. Use when adding a new hook, wiring a PreToolUse/PostToolUse/Stop/Notification hook, or scaffolding hook config for settings.json.