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 wigtn/wigtn-plugins --skill handdrawn-diagramgit clone --depth 1 https://github.com/wigtn/wigtn-pluginsWrote 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/wigtn/wigtn-plugins/handdrawn-diagram)<a href="https://agentmods.dev/skills/wigtn/wigtn-plugins/handdrawn-diagram"><img src="https://agentmods.dev/badge/skills/wigtn/wigtn-plugins/handdrawn-diagram/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/wigtn/wigtn-plugins/handdrawn-diagram"><img src="https://agentmods.dev/badge/skills/wigtn/wigtn-plugins/handdrawn-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to medium
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 →
- medium MCP Rug Pull · line 82 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 83 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 86 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 96 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
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 | $0.00166 | $0.01474 |
| Opus 5 | $0.00083 | $0.00737 |
| Sonnet 5 | $0.00033 | $0.00295 |
| Haiku 4.5 | $0.00017 | $0.00147 |
Grade A, and why
handdrawn-diagram 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hand-drawn diagram (Mermaid look:handDrawn → SVG/PNG)
Renders identically everywhere (README, GitHub/GitLab, Devpost, slides), unlike inline Mermaid (depends on the viewer's Mermaid version) or AI image generators (garbled text).
When to use
- User asks for a "hand-drawn / sketch / 손그림" architecture or flow diagram.
- A diagram is needed as an image file (Devpost, slides, print), not just inline.
Method
1. Write the Mermaid source (.mmd)
---
config:
look: handDrawn
theme: default
themeVariables:
fontFamily: "Apple SD Gothic Neo, Malgun Gothic, Noto Sans KR, sans-serif"
---
flowchart TD
A(["Trigger"]):::main --> B["main step"]:::main
B --> C{"decision?"}:::decision
C -->|Yes| D["highlighted path"]:::main
C -->|No| E["side step"]:::muted
D --> F[("datastore")]:::muted
E -.-> G["error / end"]:::alert
classDef main fill:#e8eaf6,stroke:#3949ab,stroke-width:2.5px,color:#1a237e;
classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px,color:#e65100;
classDef muted fill:#fff,stroke:#9e9e9e,color:#616161;
classDef alert fill:#ffebee,stroke:#e53935,color:#b71c1c;
Rules that avoid broken output:
- Quote every label
["..."]—·—≥→/()break unquoted. - No emojis in nodes — headless Chromium renders them as tofu; use words.
- Shapes carry meaning — pick by role, not looks:
([..])start/end terminal ·[..]process step ·[(..)]datastore/DB{..}decision (diamond) — every decision MUST have labeled branches:C{"logged in?"} -->|Yes| DandC -->|No| E. Don't fake a branch with a plain[..]step; a fork without a diamond + condition labels reads as a straight line and loses the "when this / when that" meaning.
<br/>for line breaks; Korean renders fine with the fontFamily above.
Color — meaning, not decoration (60-30-10)
Coloring every node flattens the hierarchy and nothing reads as important. Use 2–3 colors that each carry meaning, and let most nodes stay neutral:
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 · 109 lines · 166 tokens per session scan A ed1f5c5850e9
handdrawn-diagram is a skill published in the GitHub repository wigtn/wigtn-plugins (45 stars, last pushed today), licensed Apache-2.0. It adds 166 tokens to every session and 1,474 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 2026-08-30.
Other skills, from other repositories
ai-native-design
A workflow for turning a product brief and API contract into frontend design prompts and implementation guidance. It supports three outside design channels and keeps generated frontend work aligned with the same brief and contract.
scroll-craft
Build premium scroll-driven landing pages for service, product, food, and drink brands. Plan the visitor journey, page grammar, emotional peak, and bespoke signature move. Create dimensional heroes with independent visual planes, restrained motion, and separate mobile composition. Use supplied photos and footage or…
ccc-brainstorm
Design-first ideation gate. Forces 3 alternatives before any code is written. Triggers AskUserQuestion to pick the path.
design-tree
Make design decisions as an explicit branching tree — genuine alternatives, decisive rationale, rejected branches preserved. INVOKE PROACTIVELY when planning or designing any implementation approach, or choosing between architectures, libraries, or data models — especially in plan mode. Skip trivial or forced changes…
colors
Color systems for web interfaces — OKLCH conversion and palette generation, contrast measurement (APCA/WCAG), gamut and P3 fallbacks, theming, one meaning per color. INVOKE PROACTIVELY when converting color values, building or extending a palette or token set, checking or reporting contrast, or theming light and dark…
ux-audit
A multi-perspective review of a website or app’s user interface, usability, and accessibility. It uses five independent reviewers and can inspect source code, screenshots, or a live browser session.