diagramming-obsidian

diagramming-obsidian is a skill for Claude Code, Codex from GregoryHo/arcforge. It costs 61 tokens per session (2,301 once invoked), scanned A, original, MIT.

Excalidraw diagram builder for an Obsidian vault. Use when the user asks to be shown something visually — an architecture, a flow, a mind map, a "draw this" — or when a note's content needs a diagram beyond an embedded Mermaid block.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install with agentmods
npx agentmods add skills/gregoryho/arcforge/diagramming-obsidian
Install

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.

Any agent
npx skills add GregoryHo/arcforge --skill diagramming-obsidian
Clone the repo
git clone --depth 1 https://github.com/GregoryHo/arcforge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for diagramming-obsidian

README.md
[![agentmods](https://agentmods.dev/badge/skills/gregoryho/arcforge/diagramming-obsidian/github.svg)](https://agentmods.dev/skills/gregoryho/arcforge/diagramming-obsidian)
Your own site
<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.

agentmods 80×15 button for diagramming-obsidian

Your own site · 80×15
<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>
Per session 61 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured today against content hash 51fe7cc9f537, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 4 executable files (references/check_overlaps.py, references/plan_layout.py, references/render_excalidraw.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/core/diagramming-obsidian/SKILL.md · 186 lines

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.

Read the full file on GitHub · 186 lines

Changes

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.

  1. today First seen · 186 lines · 61 tokens per session scan A 51fe7cc9f537

Subscribe to this mod's changes

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.

Related

diagramming-obsidian compared with skills from other repositories

diagramming-obsidian next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
diagramming-obsidianGregoryHo/arcforgeSkill812d agoMITA61Claude Code, Codex
gke-compute-classesgoogle/skillsSkill22kyesterdayApache-2.0A83Claude Code, Codex
jetson-diagnosticNVIDIA/skillsSkill3.9kyesterdayApache-2.0A30Claude Code, Codex
holoscan-install-wheelNVIDIA/skillsSkill3.9kyesterdayApache-2.0A34Claude Code, Codex
offensive-z-waveSnailSploit/Claude-RedSkill10k25d agoMITA113Claude Code, Codex
doca-socket-relayNVIDIA/skillsSkill3.9kyesterdayApache-2.0A236Claude Code, Codex
hsb-flashNVIDIA/skillsSkill3.9kyesterdayApache-2.0B94Claude Code