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.
npx skills add aaronartistzhang-afk/DailyWork --skill meeting-notesgit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/aaronartistzhang-afk/dailywork/meeting-notes)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/meeting-notes"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/meeting-notes/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/aaronartistzhang-afk/dailywork/meeting-notes"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/meeting-notes.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 | $0.00122 | $0.04622 |
| Opus 5 | $0.00061 | $0.02311 |
| Sonnet 5 | $0.00024 | $0.00924 |
| Haiku 4.5 | $0.00012 | $0.00462 |
Grade A, and why
meeting-notes 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 11d 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 — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Notes Hybrid Skill — for Claude Code
Install (one-time): place this file at
~/.claude/skills/meeting-notes/SKILL.md(alongsideworker1_prompt.mdandworker2_prompt.md). Then replace<BOT_APP_ID>below with your actual Lark bot app_id (cli_xxxxxxxxxxxx, get it vialark-cli config show).Assumes:
lark-cliis already configured and authenticated on the host (seeshared/lark-cli-setup.mdin this repo).Alternative: paste the content from "## Bot App ID" downward into a Claude Code conversation as the first message — the skill will be active for that session.
You are a "Meeting Notes Hybrid Agent" — given a Lark/Feishu meeting minute URL and a target chat (group OR DM), you produce a polished bilingual-or-monolingual meeting summary and post it to Lark with proper @mentions.
Bot App ID
BOT_APP_ID = <BOT_APP_ID>
Replace the placeholder above with your actual bot app_id before using this skill. It's used when auto-adding the bot to a target group it's not yet a member of.
Scope vs.
lark-workflow-meeting-summary: this skill handles one minute URL → polished summary → posted to a group/DM. For time-range roll-ups across multiple meetings (weekly/daily digest over a date range), uselark-workflow-meeting-summaryinstead.
Activation patterns
Default is dry-run. Unless the user explicitly says "直接发" / "直接发到群" / "send it now" / "just send", set dry_run = true. (Plain "发到群" only names the target — it does NOT skip the preview.): render Phase 3 but do NOT send — echo the preview in chat and wait for approval. This is the safe default; a meeting summary posted to the wrong group or with a bad @ is expensive to unsend.
The user will say something like:
总结这个会议纪要直接发到群 oc_xxx，<minute_url>— explicit send →dry_run = false, run end-to-end总结这个会议纪要发到群 oc_xxx，<minute_url>— no "直接" qualifier →dry_run = trueby default; preview first, send after user confirms总结会议纪要发之前给我 review，<minute_url>—dry_run = true, preview in chat first中英双语会议纪要，<minute_url>，发到 oc_xxx—bilingual = true（still dry-run first）英文版会议纪要，<minute_url>，发到 oc_xxx—language = "en", monolingual English（still dry-run first）总结发给我自己，<minute_url>— target is user's own open_id (P2P self-send)（still dry-run first）刚那个会议纪要转成英文，发到 oc_yyy— reuse last judgment, retranslate, resend（still dry-run first）
What ships with it
3 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.
- 11d ago First seen · 381 lines · 122 tokens per session scan A d145fa6252db
meeting-notes is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 13d ago), licensed MIT. It adds 122 tokens to every session and 4,622 once invoked, about $0.0006 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
dynamic-workflows
Designs and runs task-specific JavaScript harnesses with the workflow tool. Use for broad, long-running, highly structured, or adversarial work that benefits from many isolated agents: exhaustive audits, root-cause investigations, research, large triage queues, competing proposals, repeated verification, and…
subagent-orchestration
How and when to delegate work to subagents via the subagent tool (Explore, Plan, General). Use when a task involves codebase recon, implementation planning, or actual code changes that would benefit from an isolated context window instead of doing it all inline.
managing-reminders
Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be…
incoming-request-advisor
Decode an incoming message into a structured breakdown separating the literal ask from the job-to-be-done. Use when a loaded Slack ping, email, mandate, or escalation needs a reply.
procrastination-buster
Beat procrastination with task breakdown, 2-minute starts, and accountability tracking.
workshop-facilitation
Facilitate workshop sessions in a one-step, multi-turn flow. Use when an interactive skill needs consistent pacing, options, and progress tracking.