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.
Borrowing it
Nothing to install: this file belongs to ShenSeanChen/waku-agent. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ShenSeanChen/waku-agent/main/.claude/skills/excalidraw/SKILL.mdgit 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/excalidraw)<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/excalidraw"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/excalidraw/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/excalidraw"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/excalidraw.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 | $0.00077 | $0.01308 |
| Opus 5 | $0.00039 | $0.00654 |
| Sonnet 5 | $0.00015 | $0.00262 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
excalidraw 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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Excalidraw whiteboards, Sean's way
Boards are generated from code so they match the masters in ~/Developer/Excalidraw
exactly — Sean films with them directly. Never hand-write .excalidraw JSON; use the
style engine, which locks the values that a from-scratch board always gets wrong.
The five things a naive board gets wrong (all fixed by the engine)
fontFamily 5(Excalifont) — NOT1(legacy Virgil). Wrong font = wrong board.roughness 1(controlled) — NOT2(scratchy).- Stroke-width hierarchy
1detail /2container /4emphasis — not flat2. - Type scale = Excalidraw presets S=16 / M=20 / L=28. Majority is S/M; L (28) reserved for big titles only. Don't inflate past the presets.
- Signature green
#b2f2bb, frames, socials block, watermark, source labels.
How to build one
from waku.ops.whiteboard import style as S
e = []
e.append(S.text(60, 40, "Title", size=S.FS_TITLE))
e.append(S.underline(64, 120, 800, color=S.PAL["orange"][1]))
e += S.labeled_box(80, 200, 300, 140, "A box\nwith a note", color="green")
e += S.pill_header(80, 400, 600, "SECTION", color="blue")
e += S.ellipse(500, 200, 180, 120, "agent", color="pink")
e += S.diamond(700, 200, 140, 100, "gate?", color="green")
e += S.labeled_arrow(380, 270, 500, 260, "tool calls")
e += S.socials_block(1980, 44)
e.append(S.watermark(80, 1030))
e.append(S.source_label(80, 900, "per <vendor>, <date>")) # standing rule
e.append(S.red_note(80, 960, "honest red-ink opinion")) # standing rule
S.validate(e) # catches broken bound-text ids
doc = S.document(e) # wraps with appState + white bg
Write json.dumps(doc, indent=2) to docs/whiteboards/<name>.excalidraw.
See waku/ops/whiteboard/build_k3_tutorial.py for a full two-board example.
Palette (name → fill/stroke), meaning follows Sean's color system
greenloop / hero / final reply ·redharness boundary / cost / honest-inkblueLLM-ops / observability ·orangea loop step ·pinkLLM/agent nodesgreyneutral state/config ·yellowcallout ·plainbare container
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.
- 12d ago First seen · 100 lines · 77 tokens per session scan A 06eb0ca5a31e
excalidraw is a skill published in the GitHub repository ShenSeanChen/waku-agent (1,728 stars, last pushed today), licensed MIT. It adds 77 tokens to every session and 1,308 once invoked, about $0.0004 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
baoyu-infographic
A toolkit for creating pictures and text banners from ordinary keyboard characters, called ASCII art. It supports local command-line tools and some free online services for text, images, and related artwork.
canvas-design
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
infographic
A guide for creating infographics with only HTML and CSS. Infographics present structured information visually, such as timelines, comparisons, funnels and organisation charts.
mermaid-diagram
A guide for writing Mermaid code for structured diagrams. Mermaid is a text format that can describe diagrams such as flowcharts, architecture diagrams and timelines.
baoyu-infographic
An infographic generator that turns supplied content into a visual summary using different information layouts and visual styles. It supports standard and custom image proportions and multiple languages.
sn-infographic
An image-making tool that turns supplied content into an infographic, a visual format for explaining information with arranged text and graphics.