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 jterratsdev/ableton-live-mcp --skill diagram-exportgit clone --depth 1 https://github.com/jterratsdev/ableton-live-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/jterratsdev/ableton-live-mcp/diagram-export)<a href="https://agentmods.dev/skills/jterratsdev/ableton-live-mcp/diagram-export"><img src="https://agentmods.dev/badge/skills/jterratsdev/ableton-live-mcp/diagram-export/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/jterratsdev/ableton-live-mcp/diagram-export"><img src="https://agentmods.dev/badge/skills/jterratsdev/ableton-live-mcp/diagram-export.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 | $0.00000 | $0.01206 |
| Opus 5 | $0.00000 | $0.00603 |
| Sonnet 5 | $0.00000 | $0.00241 |
| Haiku 4.5 | $0.00000 | $0.00121 |
Grade A, and why
diagram-export 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 8d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Diagram Export
Create, validate, and export architecture, workflow, and sequence diagrams.
When To Load
- Trigger:
diagram - Trigger:
mermaid - Trigger:
architecture - Trigger:
flow - Trigger:
sequence - Trigger:
draw.io - Trigger:
lucid
Procedure
- Load
docs/diagrams/diagram-master-prompt.mdas the canonical source-free diagram prompt when detailed generation or validation guidance is needed. - Identify the diagram purpose and authoritative architecture sources before drawing.
- Classify the task before drawing:
semantic,inspired-by-reference, orrecreation. - For
recreation, acceptance is pixel-perfect source fidelity unless the user explicitly accepts an approximation. Structural similarity is not enough. - For
recreation, inventory every visible source element before drawing: containers, labels, icons, connectors, arrowheads, line styles, colors, borders, spacing, rotations, z-order, and page/canvas bounds. - Choose the diagram style from the decision matrix before drafting.
- When there is no source reference, create a diagram contract before drawing: purpose, audience, node inventory, groups, relationships, labels, annotations, expected reading flow, and planned connector endpoints/anchors.
- Prefer text-native diagrams such as Mermaid unless the project requires another format.
- For recreated or high-fidelity diagrams, always perform a post-render visual QA pass against the source reference. Re-evaluate container sizing, text fit, spacing, connector bend points, and line/container overlaps after the diagram is rendered.
- After populating real text, subcards, chips, icons, and internal connectors, run a global layout reflow: grow parent containers when children need padding, then re-evaluate neighbors, connector routes, label lanes, and canvas bounds.
- Do not solve container overflow primarily by shrinking text. Prefer growing the parent container, repositioning children, or rerouting connectors unless the source reference requires tighter text.
- For
recreation, record source-vs-output gaps by element ID or visual region after each iteration. If the chosen target cannot reach pixel-perfect fidelity, reclassify as approximation and document the reason. - Avoid running connector lines over containers or important labels whenever practical. Add bend points, adjust spacing, or resize containers before treating the diagram as ready.
- Validate connector endpoint distance during the visual QA pass: every arrow must visibly leave the intended source edge and land on the intended target edge.
- Validate connector-label separation during the visual QA pass: labels must be placed in reserved whitespace or on readable label backgrounds, and must not touch connector strokes, arrowheads, or container borders.
- Validate element ordering during the visual QA pass: connectors and arrowheads must remain visible above the states or containers they connect, while accepted diagrams should remain visually stable across regenerations.
- Validate connector anchor aesthetics during the visual QA pass: choose source and target edge points that minimize bend count and unnecessary line travel without changing the intended relationship.
- Validate diagonal and crossing aesthetics during the visual QA pass: prefer orthogonal connectors and add line jumps or bridge arcs where unavoidable crossings remain.
- Validate layout simplification during the visual QA pass: before accepting a bent connector, check whether moving either connected element slightly creates a straighter route without breaking nearby spacing or semantics.
- Validate editable/rendered equivalence during the visual QA pass: draw.io XML and rendered SVG must describe the same moved elements, connectors, labels, and annotations.
- Validate annotation target clarity during the visual QA pass: every annotation arrow must visibly land on the exact element or line it describes, without obscuring target text or labels.
- For source-free diagrams, validate the rendered output against the diagram contract before handoff; correct and re-render when endpoints, labels, anchors, bend counts, or reading flow drift from the contract.
- Source-free diagrams still require a pixel-perfect quality pass against their own contract before delivery: text must fit, containers must be correctly sized, connectors must visibly attach to the intended source/target edges, arrowheads must remain visible, labels must not collide with lines or borders, and whitespace must be intentional.
- Never deliver the first render of a source-free diagram without re-evaluating sizes, line routing, connector anchors, text containment, z-order, and visual balance.
- After every correction, review the whole canvas again. Local fixes are incomplete until container containment, neighboring positions, connector routes, label lanes, z-order, and whitespace still pass globally.
- Before final handoff, perform diagram artifact hygiene:
- keep the accepted editable source, accepted render, prompt master or final prompt, and minimum QA evidence;
- archive or exclude intermediate previews, failed renders, temporary prompts, and one-off correction notes;
- do not publish source-specific prompt fragments into the prompt bank unless they have been rewritten as reusable rules;
- record where archived iterations or evidence can be found when traceability is required.
- Run
orchestra diagrams lint --file <diagram.mmd>for lint-only validation before sharing Mermaid diagrams. - Attach evidence with
orchestra diagrams lint --file <diagram.mmd> --task <task-id>when the diagram supports workflow delivery. - If
mmdcis missing, report the install guidance instead of pretending validation passed. - Mermaid outputs can be accepted as semantic diagrams, but not as pixel-perfect recreations when exact layout, connectors, icons, rotations, or reference styling are acceptance criteria. Escalate those cases to draw.io XML or Lucid.
What ships with it
1 file 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.
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.
- 8d ago First seen · 66 lines · 0 tokens per session scan A fe64f83e72ab
diagram-export is a skill published in the GitHub repository jterratsdev/ableton-live-mcp (0 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,206 tokens. 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).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.