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 GregoryHo/arcforge --skill diagramming-obsidiangit clone --depth 1 https://github.com/GregoryHo/arcforgeWrote 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/gregoryho/arcforge/diagramming-obsidian)<a href="https://agentmods.dev/skills/gregoryho/arcforge/diagramming-obsidian"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/diagramming-obsidian/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/gregoryho/arcforge/diagramming-obsidian"><img src="https://agentmods.dev/badge/skills/gregoryho/arcforge/diagramming-obsidian.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 | $0.00061 | $0.02301 |
| Opus 5.5 | $0.00024 | $0.00920 |
| Sonnet 5.5 | $0.00012 | $0.00460 |
| Haiku 4.5 | $0.00006 | $0.00230 |
Grade A, and why
diagramming-obsidian scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagramming Obsidian
A diagram should ARGUE, not display. Structure carries the claim: strip every label out, and a good diagram still says one source fans out to many, many inputs converge, this loop feeds back. A grid of boxes is a failed diagram, and no amount of labelling repairs it.
DESIGN → BUILD → VALIDATE → SAVE, and you own all four. Two layers run through
every phase: HARD is mechanical — the tools verify it, or violating it
silently corrupts the output — and SOFT is judgment about the concept you are
drawing.
Running the helpers
The Python helpers ship inside this skill's own references/ directory and every
command below runs from there. Its absolute path came with this skill when it
loaded, on the line reading Base directory for this skill — resolve
references/ against that path, never against the user's working directory.
BASE=<the path from that line>
cd "$BASE/references" && uv run python <helper> ...
# a missing dependency is first-run setup, not a defect:
cd "$BASE/references" && uv sync && uv run playwright install chromium
HARD — process invariants
Detect the theme before building anything. The wrong palette silently yields an unreadable diagram — dark colors on a light canvas wash out, light on dark go near-invisible — and the renderer will happily produce it with no feedback.
obsidian eval code="document.body.classList.contains('theme-dark') ? 'dark' : 'light'"
No answer within 5 seconds: pick from prompt signals ("dark mode" in the request, the hour) and state the assumption in your final output. Never assume silently.
Render and view the PNG on every Validate iteration. Composition,
readability, and hierarchy are not visible in JSON. The overlap checker finds
bounding-box collisions; it cannot see an arrow crossing an unrelated shape at an
acute angle, text too small to read, or a hero that fails to dominate. Read
/tmp/diagram.png with the Read tool every single iteration.
What ships with it
15 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.
- references/.gitignore 26 B
- references/check_overlaps.py 22 KB runs code
- references/color-palette.md 3.0 KB
- references/depth-enhancements.md 6.6 KB
- references/element-templates.md 10.0 KB
- references/layout-heuristics.md 9.2 KB
- references/painters-toolkit.md 11 KB
- references/plan_layout.py 12 KB runs code
- references/pyproject.toml 127 B
- references/render_excalidraw.py 10 KB runs code
- references/render_template.html 2.0 KB
- references/save-format.md 1.8 KB
- references/uv.lock 20 KB
- references/verify_saved_diagram.py 8.1 KB runs code
- references/visual-patterns.md 4.3 KB
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.
- today First seen · 186 lines · 61 tokens per session scan A 51fe7cc9f537
diagramming-obsidian is a skill published in the GitHub repository GregoryHo/arcforge (8 stars, last pushed 12d ago), licensed MIT. It adds 61 tokens to every session and 2,301 once invoked, about $0.0002 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 2026-11-07.
diagramming-obsidian compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagramming-obsidianGregoryHo/arcforge | Skill | 8 | 12d ago | MIT | A | 61 | Claude Code, Codex |
| gke-compute-classesgoogle/skills | Skill | 22k | yesterday | Apache-2.0 | A | 83 | Claude Code, Codex |
| jetson-diagnosticNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 30 | Claude Code, Codex |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 34 | Claude Code, Codex |
| offensive-z-waveSnailSploit/Claude-Red | Skill | 10k | 25d ago | MIT | A | 113 | Claude Code, Codex |
| doca-socket-relayNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | A | 236 | Claude Code, Codex |
| hsb-flashNVIDIA/skills | Skill | 3.9k | yesterday | Apache-2.0 | B | 94 | Claude Code |