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 agentmods add commands/theclaymethod/artifacture/generate-web-diagramgit clone --depth 1 https://github.com/theclaymethod/artifactureWrote 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/commands/theclaymethod/artifacture/generate-web-diagram)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/generate-web-diagram"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/generate-web-diagram.svg" alt="Measured on agentmods" 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 | $0.00012 | $0.01258 |
| Opus 5 | $0.00006 | $0.00629 |
| Sonnet 5 | $0.00002 | $0.00252 |
| Haiku 4.5 | $0.00001 | $0.00126 |
Grade A, and why
generate-web-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 4d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read cards/web-diagram.md. If the request is primarily a comparison or data table, read cards/comparison-table.md instead.
Load the visual-explainer skill, then generate an HTML diagram for: $@
MDX/React pipeline. Prefer the generated pipeline for this command:
- Author the editable source as
.mdxby default, or.tsxwhen the diagram needs local React state, custom interaction, or generated SVG logic. - Use shared components from
visual-explainer-mdx/components.tsxsuch asExplainerShell,Section,DiagramCanvas,Pipeline,DecisionMatrix,RiskLedger, andCallout. - Export the final artifact with
npm run ve:export -- <source.mdx|source.tsx> --out ~/.agent/diagrams/<slug>.html. - Treat the generated
.htmlas an artifact only. Do not hand-edit the final HTML to make content changes; change the MDX/TSX source and re-export. - Browser-verify the generated HTML using the same desktop/mobile/no-overflow checks below.
Raw HTML templates remain reference material for style and parity, not the preferred authoring surface.
Clarify. This is a Tier 1 command per ./references/clarify.md. Before generating, check that you can form a 1-sentence brief covering topic, audience, depth, and aesthetic. If any dimension is unclear, ask 1–3 questions via AskUserQuestion. If all four are answerable from the request + context, generate directly. Bypass with --no-ask.
Follow the visual-explainer skill workflow and the selected card. Default to the OA Design preset and read references/oa-design.md unless the user explicitly requests a named alternative.
Sub-agent fan-out (default for 3+ sections)
After drafting the page outline, count the major sections.
- Outline has 1–2 sections, or
--no-parallelwas passed: build sequentially yourself. Skip the rest of this section. - Outline has 3+ sections: fan out to specialized sub-agents in parallel. Each sub-agent produces one section as a structured fragment; you stitch them together.
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.
- 4d ago First seen · 55 lines · 12 tokens per session scan A 6fdf03bc59d2
generate-web-diagram is a command published in the GitHub repository theclaymethod/artifacture (2 stars, last pushed 12d ago), licensed MIT. It adds 12 tokens to every session and 1,258 once invoked, about $0.0001 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 2026-08-31.
Other commands, from other repositories
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
Markdown・テキストファイルを原始人形式へ安全圧縮.
save
Save this conversation as a new or existing reusable context.
wp-polylang
Translate an existing WordPress site into a second language using Polylang.
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.