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 grahama1970/agent-skills --skill create-architecturegit clone --depth 1 https://github.com/grahama1970/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/grahama1970/agent-skills/create-architecture)<a href="https://agentmods.dev/skills/grahama1970/agent-skills/create-architecture"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/create-architecture/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/grahama1970/agent-skills/create-architecture"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/create-architecture.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 | $0.00051 | $0.01449 |
| Opus 5 | $0.00026 | $0.00724 |
| Sonnet 5 | $0.00010 | $0.00290 |
| Haiku 4.5 | $0.00005 | $0.00145 |
Grade A, and why
create-architecture 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
24 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.
- .ask/browser-oracles.yaml 50 B
- .gitignore 35 B
- create_architecture.py 24 KB runs code
- docs/CHART_DESIGN.md 3.2 KB
- docs/hub-verification.md 3.3 KB
- examples/chart_examples_bad.py 10 KB runs code
- examples/chart_examples_data.py 300 B runs code
- examples/chart_examples_good.py 38 KB runs code
- examples/learn_chart_examples.py 1.5 KB runs code
- examples/queryspec-pipeline.yaml 6.0 KB
- fixtures/agentic_eval.json 2.5 KB
- hub_cli.py 2.6 KB runs code
- hub_models.py 6.8 KB runs code
- hub.py 16 KB runs code
- pyproject.toml 298 B
- references/hub-contract.md 2.8 KB
- references/legacy-excalidraw.md 5.3 KB
- run.sh 963 B runs code
- sanity-live.sh 206 B runs code
- sanity.sh 356 B runs code
- scripts/eval_hub.py 14 KB runs code
- tests/test_execution_gate.py 1.4 KB runs code
- tests/test_sanity.py 3.2 KB runs code
- uv.lock 39 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.
- 6d ago Changed · -36 lines · -14 tokens per session acd6490bbf64
- 9d ago First seen · 166 lines · 65 tokens per session scan A e2048b20362b
create-architecture is a skill published in the GitHub repository grahama1970/agent-skills (6 stars, last pushed today), with no licence file. It adds 51 tokens to every session and 1,449 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
dstack-prototyping
Use with the dstack skill for model-serving work when the image, serving command, resources, backend/fleet choice, or service behavior is not proven. Guides task-first prototyping on real hardware, choosing fleets/backends that can reuse idle instances and caches, checking vLLM/SGLang sources, and verifying the final…
ranui
Use when building UI with the ranui web-component library (elements like , , , , ) or its fluent DOM builder (ranui/builder — Div/View/Span/signal/createEffect/EventManager). Covers the import map, the full element inventory, conventions, accessibility, and where the authoritative API reference lives.
form-list-layout
Configure what a form and a list look like — sysuiform, sysuisection and sysuielement for forms; sysuilist, sysuilistelement and sysuirelatedlist for lists; sysfilter for saved filters. Views, why a field must exist in the dictionary first, and what snowcreatemenu really writes.
sequence-diagrams
Create animated sequence diagrams showing interactions between participants using the Excalimate MCP server. Use when asked to visualize API call sequences, message flows, protocol handshakes, request/response patterns, authentication flows, or communication between services, users, and systems.
reka-ui
Use when building with Reka UI (headless Vue components) - provides component API, accessibility patterns, composition (asChild), controlled/uncontrolled state, virtualization, and styling integration. Formerly Radix Vue.