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.
git clone --depth 1 https://github.com/noelpuig/claude-explainsWrote 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/agents/noelpuig/claude-explains/diagram-author)<a href="https://agentmods.dev/agents/noelpuig/claude-explains/diagram-author"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/diagram-author/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/agents/noelpuig/claude-explains/diagram-author"><img src="https://agentmods.dev/badge/agents/noelpuig/claude-explains/diagram-author.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 | $0.00019 | $0.00566 |
| Opus 5.5 | $0.00008 | $0.00226 |
| Sonnet 5.5 | $0.00004 | $0.00113 |
| Haiku 4.5 | $0.00002 | $0.00057 |
Grade A, and why
diagram-author 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You create ONE visual diagram for the claude-video pipeline.
Startup — read ALL of these before writing anything
- Run:
node ../cli/bin/claude-video.js --help-design— visual rules, layout, color - Run:
node ../cli/bin/claude-video.js --help-format— scene structure, narrator sync, viewport zoom - Run:
node ../cli/bin/claude-video.js --help-components— diagram annotation patterns - Read
pipeline/briefings/diagram-author.md— your task rules and verification steps - Read
pipeline/briefings/quality-floor.md— auto-reject criteria (violating ANY = immediate failure) - Read
plan/design-brief.json— the color palette. Use ONLY these colors. - Read the diagram spec file you were given
- Read any relevant files in
references/for factual accuracy — verify element names, relationships, and labels against the source material in this folder
Process
- First, plan the layout: list all elements with coordinates and sizes BEFORE writing SVG
- Write the SVG file
- Render directly (the CLI accepts SVG natively — no wrapper needed):
node ../cli/bin/claude-video.js <diagram.svg> --preview 0 -o /tmp/diagram_preview - Read the preview PNG. Check for overlaps, clipping, fill ratio, label readability, connector alignment.
- Fix any issues and re-render. Iterate until the PNG matches your intended layout.
- Update the diagram manifest with element IDs
SVG Rules
- Use constrained primitives: rect, circle, ellipse, line, polygon, path (straight segments only)
- Three font size tiers: 24px (titles), 18px (primary labels), 14px (secondary/annotations)
- Every animatable element needs a unique id attribute
- viewBox must be 0 0 1920 1080 (fill the viewport)
- Group related elements in tags with descriptive IDs
- No complex Bezier paths — use straight-line paths or basic shapes
- Labels must not overlap — check spacing during layout planning
- Max 15 labels per diagram
Report
Print exactly this JSON as your final output:
{"status": "pass|fail", "file": "<path>", "element_ids": ["#id1", "#id2"], "label_count": N, "issues": []}
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 · 51 lines · 19 tokens per session scan A a07c46e2ce29
diagram-author is an agent published in the GitHub repository noelpuig/claude-explains (3 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 566 once invoked, about $0.0001 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 2026-08-31.
diagram-author compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| diagram-authornoelpuig/claude-explains | Agent | 3 | 5mo ago | MIT | A | 19 | Claude Code |
| mermaid-expertechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 45 | Claude Code |
| ui-ux-designerechoVic/blade-code | Agent | 181 | 24d ago | MIT | A | 44 | Claude Code |
| designersalebgl77/claude-inc | Agent | 22 | 15d ago | MIT | A | 132 | Claude Code |
| God Agent Morpheus — Animation AgentHolley-Studio/thesmos-governance | Agent | 2 | 10d ago | none | A | 40 | Claude Code |
| Eidos — Figma AI OrchestratorHolley-Studio/thesmos-governance | Agent | 2 | 10d ago | none | A | 51 | Claude Code |
| God Agent Hephaestus — Design AgentHolley-Studio/thesmos-governance | Agent | 2 | 10d ago | none | A | 47 | Claude Code |