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 karaage0703/ai-assistant-workspace --skill xs-diagram-generatorgit clone --depth 1 https://github.com/karaage0703/ai-assistant-workspaceWrote 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/karaage0703/ai-assistant-workspace/xs-diagram-generator)<a href="https://agentmods.dev/skills/karaage0703/ai-assistant-workspace/xs-diagram-generator"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-diagram-generator/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/karaage0703/ai-assistant-workspace/xs-diagram-generator"><img src="https://agentmods.dev/badge/skills/karaage0703/ai-assistant-workspace/xs-diagram-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 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 37 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 84 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
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 | $0.00081 | $0.02037 |
| Opus 5.5 | $0.00032 | $0.00815 |
| Sonnet 5.5 | $0.00016 | $0.00407 |
| Haiku 4.5 | $0.00008 | $0.00204 |
Grade A, and why
xs-diagram-generator 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 2mo 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 — 217 lines — stays where its author put it; the contents beside it link to each section on GitHub.
スマート図表生成支援
内容に応じて最適な図表形式を自動選択し、画像を生成する。
判断フロー
Mermaidコードがすでにある?
├─ YES → Docker mermaid-cli で画像化(最優先)
└─ NO → 内容に応じて選択
├─ フロー/シーケンス → Mermaidコード作成 → Docker mermaid-cli
└─ アーキテクチャ/階層 → Pillow(uv run)で直接生成
1. Mermaid → 画像化(Docker mermaid-cli)
Mermaidコードがある場合はこれを最優先で使う。
# 1. Mermaidファイルを作成
cat > /tmp/diagram.mmd << 'EOF'
flowchart TB
A[開始] --> B[処理]
B --> C{判断}
C -->|Yes| D[完了]
C -->|No| B
EOF
# 2. Docker版 mermaid-cli で画像生成
docker run --rm -u $(id -u):$(id -g) \
-v /tmp:/data \
minlag/mermaid-cli \
-i /data/diagram.mmd -o /data/diagram.png -b white
ポイント:
-u $(id -u):$(id -g)でパーミッション問題を回避-b whiteで白背景(スライド向け)- 日本語・絵文字も表示可能
- SVG出力:
-o /data/diagram.svg
⚠️ Mermaid記法の注意(よく間違えるやつ)
改行は <br> を使う! \n は使わない!
# NG(\n がそのまま表示される)
A["Gateway\nRust / Axum"]
# OK(ちゃんと改行される)
A["Gateway<br>Rust / Axum"]
subgraphのタイトルが長いと途中で改行される:
- タイトルは短くする(15文字以内推奨)
- 補足は中のノードに書く
線の交差を減らすコツ:
direction LR/direction TBをsubgraph内で使い分ける- 関連するノードを近くに配置する
- 包含関係はsubgraphのネストで表現する(矢印より明確)
subgraphのネスト例(包含関係の表現):
subgraph outer["親システム"]
subgraph inner["子システム"]
A["コンポーネントA"]
end
B["コンポーネントB"] --> A
end
複数ファイルを一括変換
for f in /tmp/*.mmd; do
docker run --rm -u $(id -u):$(id -g) \
-v /tmp:/data \
minlag/mermaid-cli \
-i /data/$(basename "$f") -o /data/$(basename "$f" .mmd).png -b white
done
2. Pillow で直接画像生成(uv run)
Mermaidを経由せず、直接画像を生成したい場合に使用。
スクリプト実行
uv run --with pillow python [SKILL_DIR]/draw_diagram.py <type> -o <output.png> -d '<json>'
対応する図の種類
アーキテクチャ図 (architecture)
uv run --with pillow python [SKILL_DIR]/draw_diagram.py architecture \
-o /tmp/arch.png -d '{
"title": "システム構成",
"boxes": [
{"id": "api", "label": "API Server", "color": "blue", "row": 0, "col": 1},
{"id": "db", "label": "Database", "sublabel": "PostgreSQL", "color": "green", "row": 1, "col": 0},
{"id": "cache", "label": "Cache", "sublabel": "Redis", "color": "orange", "row": 1, "col": 2}
],
"arrows": [
{"from": "api", "to": "db", "label": "query"},
{"from": "api", "to": "cache", "label": "read/write"}
]
}'
What ships with it
1 file 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.
- 2mo ago First seen · 217 lines · 81 tokens per session scan A aa604fb3ce43
xs-diagram-generator is a skill published in the GitHub repository karaage0703/ai-assistant-workspace (137 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 2,037 once invoked, about $0.0003 per session on Opus 5.5. 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.
xs-diagram-generator compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| xs-diagram-generatorkaraage0703/ai-assistant-workspace | Skill | 137 | 1mo ago | MIT | A | 81 | Claude Code, Codex |
| kami-landingnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 81 | Claude Code, Codex |
| applying-brand-guidelinesanthropics/claude-cookbooks | Skill | 54k | 4d ago | MIT | A | 27 | Claude Code, Codex |
| html-ppt-obsidian-claude-gradientnexu-io/open-design | Skill | 107k | today | Apache-2.0 | A | 53 | Claude Code, Codex |
| surfsense-htmlMODSetter/SurfSense | Skill | 17k | yesterday | Apache-2.0 | A | 89 | Claude Code, Codex |
| kamitw93/Kami | Skill | 12k | today | MIT | A | 78 | Claude Code |
| readtw93/Waza | Skill | 7.5k | 6d ago | MIT | A | 61 | Claude Code |