Waku Agent is a local-first personal AI assistant whose readable code implements the agent loop, memory, and evaluation system. It is for people who want an assistant they can run and understand on their own laptop, with memory stored in SQLite and built-in testing. The catalogue add-ons support its agent workflow.
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 ShenSeanChen/waku-agent --skill meeting-prepgit clone --depth 1 https://github.com/ShenSeanChen/waku-agentWrote 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/shenseanchen/waku-agent/meeting-prep)<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/meeting-prep"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/meeting-prep/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/shenseanchen/waku-agent/meeting-prep"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/meeting-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00055 | $0.00458 |
| Opus 5 | $0.00028 | $0.00229 |
| Sonnet 5 | $0.00011 | $0.00092 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
meeting-prep 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.
What it actually says
How to prep
- Find the meeting: call
list_eventsand pick the one that matches the name or time the user gave. Note the title, time, attendees, and notes. - Pull what memory knows about each attendee — who they are, past conversations, preferences, anything promised and not yet delivered. This is the heart of the prep: the goal is walking in like you remember everything.
- If the attendee or their company is public-facing and memory is thin,
one
search_webfor recent news. Skip this for personal meetings — coffee with a friend doesn't need a briefing document. - Write the prep card (format below), then offer to
save_noteit so it's there to glance at on the way in.
The prep card
- When — one line: time, duration, where/how.
- Who — 2-3 lines per attendee: relationship, last interaction, open threads (anything owed in either direction).
- Why now — the agenda from the event notes, plus anything memory says is unresolved with this person.
- Three talking points — concrete, memory first, web second. "Ask how the Berlin launch went" beats "discuss recent developments".
Keep it skimmable — it gets read in the elevator, not at a desk.
Edge cases
| Situation | Do |
|---|---|
| No matching event on the calendar | Say so, then prep from the name alone using memory and web |
| Several events match | Prep the next upcoming one; list the others in one line |
| Memory knows nothing about the attendee | Say that plainly, lead with web results, and offer to save_note who they are after the meeting |
| "Prep my day" | One compact card per meeting, ordered by time, sharpest points only |
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 · 40 lines · 55 tokens per session scan A 2020402c2926
meeting-prep is a skill published in the GitHub repository ShenSeanChen/waku-agent (1,720 stars, last pushed 13d ago), licensed MIT. It adds 55 tokens to every session and 458 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 2026-08-30.
Other skills, from other repositories
slacrawl
Archive and search Slack workspace messages, threads, and channels via the slacrawl CLI. Supports API sync, Slack export ZIP import, local desktop cache import, and full-text search.
obsidian
Read, search, and create notes in the Obsidian vault.
clip-hand-skill
Expert knowledge for AI video clipping — yt-dlp downloading, whisper transcription, SRT generation, and ffmpeg processing.
twitter-hand-skill
Expert knowledge for AI Twitter/X management — API v2 reference, content strategy, engagement playbook, safety, and performance tracking.
slack-tools
Slack workspace management and automation specialist.
routing-card-authoring
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.