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 Mathews-Tom/armory --skill architecture-diagramgit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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/mathews-tom/armory/architecture-diagram)<a href="https://agentmods.dev/skills/mathews-tom/armory/architecture-diagram"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/architecture-diagram/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/mathews-tom/armory/architecture-diagram"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/architecture-diagram.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00162 | $0.04691 |
| Opus 5 | $0.00081 | $0.02346 |
| Sonnet 5 | $0.00032 | $0.00938 |
| Haiku 4.5 | $0.00016 | $0.00469 |
Grade A, and why
architecture-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 4d 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 — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Diagram Generator
Produces standalone, fully editable .svg files: real inlined vector icons (AWS/Azure/GCP official architecture icons, or a hand-drawn generic set for everything else), deterministic zone-aware layout, orthogonal connection routing, and real <text> labels. deliver --emit drawio additionally produces a self-contained editable .drawio mxGraph companion. SVG output uses zero raster images and zero <use> clones; draw.io output uses independently editable cells with local vector icon data and no remote image, external URL, or provider stencil dependency.
When to use this
| Situation | Use this skill? |
|---|---|
| "Draw our AWS/Azure/GCP architecture" | Yes |
| "System topology diagram for docs" | Yes |
| "I need to edit this diagram afterward in Figma" | Yes — this is the differentiator vs. every raster-output alternative |
| Multi-cloud or hybrid (cloud + on-prem) diagram | Yes — mix provider: per node freely |
| Interactive, click-through, or animated diagram | No — use static-web-artifacts-builder |
| Hand-drawn / whiteboard-style sketch | No — use tldraw |
| Data chart, plot, or dashboard | No — use chart-clarity |
| Reviewing or critiquing an existing architecture | No — use architecture-reviewer |
| Single-frame concept illustration with no components/connections | No — use concept-to-image |
Prerequisites
Run the following commands from this skill directory (skills/architecture-diagram in a checkout).
-
python3withpyyamlinstalled (uv run --with pyyaml python3 -m engine ...if not already available). -
Cloud-provider icons need a one-time, per-machine network fetch. Icons are never bundled in this skill; their providers publish diagram-use terms, so
architecture-diagramrecords each provider's source and terms in the local cache rather than redistributing icon assets. The first time a diagram needs a given provider's icons, run:python3 -m engine.fetch_icons --provider aws # ~5s, 1037 icons python3 -m engine.fetch_icons --provider gcp # ~5s, 297 icons python3 -m engine.fetch_icons --provider azure # ~60s, 704 icons # or: --provider all
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/example-serverless.svg 14 KB
- assets/example-serverless.yaml 881 B
- assets/generic-icons.json 21 KB
- engine/__init__.py 45 B runs code
- engine/__main__.py 89 B runs code
- engine/commands.py 18 KB runs code
- engine/compare.py 4.9 KB runs code
- engine/data.py 405 B runs code
- engine/delivery.py 1.6 KB runs code
- engine/diagnostics.py 4.1 KB runs code
- engine/drawio.py 9.3 KB runs code
- engine/evidence.py 7.1 KB runs code
- engine/fetch_icons.py 14 KB runs code
- engine/geometry_checks.py 17 KB runs code
- engine/icons.py 5.5 KB runs code
- engine/layout.py 6.8 KB runs code
- engine/model.py 1.1 KB runs code
- engine/pipeline.py 3.0 KB runs code
- engine/profile.py 6.1 KB runs code
- engine/receipts.py 5.4 KB runs code
- engine/routing.py 8.6 KB runs code
- engine/spec.py 14 KB runs code
- engine/stencil2svg.py 8.1 KB runs code
- engine/svg_inline.py 4.7 KB runs code
- engine/svg.py 11 KB runs code
- engine/tests/__init__.py 0 B runs code
- engine/tests/conftest.py 201 B runs code
- engine/tests/fixtures/azure_virtual_machine.svg 3.8 KB
- engine/tests/fixtures/deployment-profile-ambiguous-region.yaml 366 B
- engine/tests/fixtures/deployment-profile-inconsistent-security-region.yaml 293 B
- engine/tests/fixtures/deployment-profile-missing-boundary-mechanism.yaml 417 B
- engine/tests/fixtures/deployment-profile-missing-owner.yaml 399 B
- engine/tests/fixtures/deployment-profile-missing-region.yaml 454 B
- engine/tests/fixtures/deployment-profile-missing-required-zone-kinds.yaml 279 B
- engine/tests/fixtures/deployment-profile-storage-outside-security.yaml 421 B
- engine/tests/fixtures/deployment-profile-valid.yaml 419 B
- engine/tests/fixtures/drawio-review.drawio 3.0 KB
- engine/tests/fixtures/drawio-review.yaml 282 B
- engine/tests/fixtures/example-serverless.layout.json 3.5 KB
- engine/tests/fixtures/real_shapes.xml 5.7 KB
- engine/tests/fixtures/spec-compare-base.yaml 471 B
- engine/tests/fixtures/spec-compare-head.yaml 460 B
- engine/tests/fixtures/spec-compare-reordered.yaml 471 B
- engine/tests/test_delivery.py 1.2 KB runs code
- engine/tests/test_deployment_profile.py 3.3 KB runs code
- engine/tests/test_drawio_delivery.py 3.1 KB runs code
- engine/tests/test_drawio.py 5.2 KB runs code
- engine/tests/test_evidence.py 6.9 KB runs code
- engine/tests/test_fetch_icons.py 10 KB runs code
- engine/tests/test_receipts.py 1.5 KB runs code
- engine/tests/test_render.py 55 KB runs code
- engine/tests/test_service_maps.py 3.5 KB runs code
- engine/tests/test_source_evidence_schema.py 2.7 KB runs code
- engine/tests/test_spec_compare.py 3.4 KB runs code
- engine/tests/test_stencil2svg.py 8.9 KB runs code
- engine/tests/test_svg_inline.py 4.3 KB runs code
- evals/cases.yaml 4.6 KB
- references/editability.md 4.2 KB
- references/icons-generic.md 23 KB
- references/services-aws.yaml 10 KB
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.
- 4d ago Changed · +4 lines · +16 tokens per session 0e09c028a09c
- 5d ago Changed · +32 lines 2d5fbfe7b307
- 11d ago First seen · 255 lines · 146 tokens per session scan A a26147922e8f
architecture-diagram is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 4d ago), licensed MIT. It adds 162 tokens to every session and 4,691 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
html-draft
Use when user wants a standalone HTML diagram in flat engineering blueprint style — architecture diagrams, system flows, technical spec sheets, component maps. Generates one HTML file using Tailwind v4 (browser CDN) for layout and D3 v7 (CDN) for SVG diagrams. User-invoked only — do NOT auto-trigger. Triggers on…
parallel-design-variants
A workflow for producing several genuinely different visual design directions at the same time. It uses distinct visual references, gathers the results into a comparison gallery, and can support choosing winners before another design round.
idea-superpowers-suite
Use when running the full idea workflow: capture a rough idea, expand it into design/UI/implementation docs, research similar products, and generate build-ready Markdown artifacts.
idea-to-design-doc
Use when turning a rough idea into a focused product/design Markdown doc through guided questions, without moving into implementation too early.
idea-to-ui-design-brief
Use when turning a product/design doc into a focused UI design brief, optional AI image-generation concept prompts, and implementation-ready UI direction without replacing the main idea workflow.