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 jakenuts/agent-skills --skill agent-vision-diagramsgit clone --depth 1 https://github.com/jakenuts/agent-skillsWrote 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/jakenuts/agent-skills/agent-vision-diagrams)<a href="https://agentmods.dev/skills/jakenuts/agent-skills/agent-vision-diagrams"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/agent-vision-diagrams/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/jakenuts/agent-skills/agent-vision-diagrams"><img src="https://agentmods.dev/badge/skills/jakenuts/agent-skills/agent-vision-diagrams.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 | $0.00082 | $0.01038 |
| Opus 5 | $0.00041 | $0.00519 |
| Sonnet 5 | $0.00016 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
agent-vision-diagrams 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 11d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Vision — diagrams for the user
Agent Vision is a hosted diagram app. You write a small JSON document (the spec — a DSL), the app renders it (2D now, isometric later), stores every change as an immutable revision, and returns a public share URL plus a rendered PNG so you can show the user immediately.
This installed skill is a thin connection recipe. The full DSL, the color / idiom grammar, worked examples, ops-patch reference, icon catalog, and warning list live in the hosted, canonical skill doc — fetch it once at the start of a diagramming session and follow it:
<app-url>/skill.md (ask the user for their Agent Vision app URL)
(Replace the host with whatever app URL the user gave you; the skill doc lives
at <app-url>/skill.md.)
Connecting (given only the user's app <url>)
Step 0 — check the environment first: if AGENT_NATIVE_VISION_URL and
AGENT_NATIVE_VISION_TOKEN env vars are set (provisioned containers), use them
and skip all auth below — bearer header on every call, done.
Primary — device flow, you drive it. No pre-minted token, no password:
POST <url>/_agent-native/mcp/connect/device/start(empty JSON body, no auth) →{ device_code, user_code, verification_uri_complete, interval, expires_in }.- Tell the user in chat: "Open
<verification_uri_complete>and click Authorize this device (code<user_code>)." Any device where they're already logged in works. POST <url>/_agent-native/mcp/connect/device/pollwith{ "device_code": "<device_code>" }everyintervalseconds until it returnsapproved→{ token, mcpUrl, ... }(pending= keep going;expired/consumed= restart at step 1).- Use the token exactly as below.
Fallback — user-minted token: the user logs in, opens
<url>/_agent-native/mcp/connect, clicks Create connection token, and
pastes { url, token } to you. Tokens are per-user, scoped, expiry-bound, and
revocable from that same page.
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.
- 11d ago First seen · 86 lines · 82 tokens per session scan A a8e17d063a64
agent-vision-diagrams is a skill published in the GitHub repository jakenuts/agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 82 tokens to every session and 1,038 once invoked, about $0.0004 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).
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.