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 stablebaseline/mcp --skill sb-diagramgit clone --depth 1 https://github.com/stablebaseline/mcpWrote 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/stablebaseline/mcp/sb-diagram)<a href="https://agentmods.dev/skills/stablebaseline/mcp/sb-diagram"><img src="https://agentmods.dev/badge/skills/stablebaseline/mcp/sb-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 5.1 | $0.00127 | $0.02115 |
| Opus 5 | $0.00063 | $0.01058 |
| Sonnet 5 | $0.00025 | $0.00423 |
| Haiku 4.5 | $0.00013 | $0.00212 |
Grade A, and why
sb-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 6d 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Stable Baseline: diagrams
What this skill does
Turns a description into real diagram code, renders it, and either hands back the image or persists it inside a document or a whiteboard. Diagrams stay editable: the source DSL is kept alongside the render, so a diagram can be corrected later rather than redrawn.
Every call runs under the signed in user's own Stable Baseline identity.
IDs are never hardcoded. Resolve projectId, documentId and diagramId at runtime
from listing calls made in this conversation.
Never guess DSL syntax
This is the single biggest cause of failed diagrams. Two calls, in this order, before you write any diagram code:
listDiagramTypes. Passqueryand it searches by name and by intent, semantically, so "wiring harness", "timing waveform", "network topology" or "database schema" all resolve to a real type. Use the returnedtypevalue verbatim.getDiagramTypeGuidewith thattype. It returns the DSL writing instructions and an example for exactly that renderer.
Skipping step 2 because a type looks familiar is how a Mermaid dialect mismatch turns into a render error the user sees.
For an infographic, call searchInfographicTemplates first with a description of the
intent, for example "compare two options", "process timeline", "pyramid of priorities". It
ranks 276 AntV templates and returns a key that becomes line 1 of the DSL as
infographic <key>, plus a usage note explaining how that family maps to data fields.
For software and cloud architecture, listArchitectureIcons returns an iconPath such
as dev/docker.svg that can be used directly in D2 code. The catalogue is software and
cloud only. It deliberately returns nothing for non-technical subjects, so do not force an
unrelated tech logo onto a general concept.
Choosing where the diagram goes
| Intent | Tool | Notes |
|---|---|---|
| Just show me the picture | renderDiagram |
Needs diagramType and source. Nothing is persisted. Returns a temporary link available for one hour, plus the image inline for png and jpeg |
| Put it in a document | insertDiagramInDocument |
Needs documentId, type, diagramCode, prompt |
| Put it on a whiteboard | insertWhiteboardDiagram |
Needs documentId (the board), diagramType, source |
| Show an existing one | getDiagramImage |
Needs diagramId |
| Change an existing one | updateDiagramInDocument |
Needs diagramId |
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.
- 6d ago First seen · 175 lines · 127 tokens per session scan A ca472c0558c9
sb-diagram is a skill published in the GitHub repository stablebaseline/mcp (0 stars, last pushed today), licensed MIT. It adds 127 tokens to every session and 2,115 once invoked, about $0.0006 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 skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.