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 KornLabs/truss --skill diagrams-archifygit clone --depth 1 https://github.com/KornLabs/trussWrote 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/kornlabs/truss/diagrams-archify)<a href="https://agentmods.dev/skills/kornlabs/truss/diagrams-archify"><img src="https://agentmods.dev/badge/skills/kornlabs/truss/diagrams-archify/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/kornlabs/truss/diagrams-archify"><img src="https://agentmods.dev/badge/skills/kornlabs/truss/diagrams-archify.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 | $0.00165 | $0.04021 |
| Opus 5.5 | $0.00066 | $0.01608 |
| Sonnet 5.5 | $0.00033 | $0.00804 |
| Haiku 4.5 | $0.00016 | $0.00402 |
Grade A, and why
diagrams-archify 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 today.
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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files 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.
- assets/JetBrainsMono-OFL.txt 4.3 KB
- assets/template.html 768 KB
- bin/archify.mjs 282 KB runs code
- bin/delivery-update.mjs 3.6 KB runs code
- bin/finalize.mjs 49 KB runs code
- bin/open-artifact.mjs 4.0 KB runs code
- bin/preview.mjs 36 KB runs code
- bin/recover-output.mjs 1.3 KB runs code
- bin/visual-check.mjs 118 KB runs code
- brand-marks/catalog.json 14 KB
- brand-marks/README.md 1.4 KB
- delta/architecture-delta.mjs 77 KB runs code
- examples/agent-run.lifecycle.json 3.2 KB
- examples/agent-tool-call.workflow.json 4.8 KB
- examples/archify-dev-activity.timeline.json 4.4 KB
- examples/archify-repository.tree.json 4.3 KB
- examples/async-job-roundtrip.sequence.json 3.7 KB
- examples/brand-aware-delivery.architecture.json 2.7 KB
- examples/cache-miss-request.sequence.json 3.7 KB
- examples/checkout-platform.base.architecture.json 2.2 KB
- examples/checkout-platform.head.architecture.json 2.4 KB
- examples/checkout-request.waterfall.json 1.2 KB
- examples/delivery.explainer.json 4.5 KB
- examples/deployment-release.lifecycle.json 4.1 KB
- examples/event-stream.dataflow.json 4.7 KB
- examples/example-rebuild.waterfall.json 4.5 KB
- examples/holiday-planning.workflow.json 2.9 KB
- examples/incident-response.workflow.json 4.6 KB
- examples/locales/de.json 28 KB
- examples/locales/fr.json 29 KB
- examples/locales/fr.partial.json 959 B
- examples/locales/it.json 28 KB
- examples/locales/ja.json 32 KB
- examples/locales/pt.json 28 KB
- examples/locales/ru.json 36 KB
- examples/orders.erd.json 7.1 KB
- examples/payment-incident.timeline.json 1.4 KB
- examples/payment-platform.tree.json 1.2 KB
- examples/payment-processors.class.json 7.1 KB
- examples/payments.class.json 2.8 KB
- examples/product-analytics.dataflow.json 4.9 KB
- examples/production-deployment.architecture.json 4.6 KB
- examples/release-delivery.workflow.json 4.4 KB
- examples/subscription-billing.erd.json 12 KB
- examples/web-app.architecture.json 3.1 KB
- explainer/browser-check.mjs 30 KB runs code
- explainer/charts.mjs 5.9 KB runs code
- explainer/check.mjs 15 KB runs code
- explainer/diagrams.mjs 38 KB runs code
- explainer/diff.mjs 8.3 KB runs code
- explainer/inline.mjs 8.5 KB runs code
- explainer/layout.mjs 2.5 KB runs code
- explainer/page-bundle.mjs 1.1 KB runs code
- explainer/parse.mjs 27 KB runs code
- explainer/patch.mjs 12 KB runs code
- explainer/prepare.mjs 9.6 KB runs code
- explainer/reader.css 46 KB
- explainer/reader.js 50 KB runs code
- explainer/render.mjs 33 KB runs code
- explainer/revision.mjs 1.9 KB runs code
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.
- today First seen · 139 lines · 165 tokens per session scan A 36a2b7a07a3d
diagrams-archify is a skill published in the GitHub repository KornLabs/truss (2 stars, last pushed today), with no licence file. It adds 165 tokens to every session and 4,021 once invoked, about $0.0007 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 2026-10-25.
Other skills, from other repositories
diagram-maker
Generate clean SVG/HTML diagrams for architecture, flows, sequences, ER diagrams, and whiteboards. Use when the user asks to "draw", "diagram", "visualize architecture/flow", or wants a schematic.
adversarial-ux-test
Test an app as a difficult, low-patience persona, then filter complaints into actionable UX issues.
excalidraw
Hand-drawn-style diagrams and sketches via the Excalidraw format (.excalidraw JSON), exportable to SVG/PNG. Use for whiteboard-style, concept, and freeform sketches.
game-ui
Design, implement, and test game HUDs, menus, overlays, inventories, input prompts, accessibility, localization, and responsive layouts without obscuring or fighting the playfield.
blender-headless
Build, render, and visually verify 3D models with Blender's Python API in headless mode, using the image tool to inspect renders and iterate.
theme-pack-authoring
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.