system-design-artifact-intake

system-design-artifact-intake is a skill for Claude Code, Codex from HoangNguyen0403/agent-skills-standard. It costs 74 tokens per session (1,043 once invoked), scanned A, original, MIT.

A process for extracting a reviewable fact sheet from a system design artifact such as a diagram, screenshot, PDF, slide deck, or infrastructure configuration.

In plain words
What is it for?
Use it when reviewing architecture diagrams, whiteboard images, draw.io files, presentation diagrams, PDFs, Mermaid or PlantUML designs, or infrastructure-as-code.
Why use it?
It helps reviewers confirm what the design actually contains before judging it, including connections, embedded source data, extracted text, and confidence in each relationship.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

Good fit Use it when reviewing architecture diagrams, whiteboard images, draw.io files, presentation diagrams, PDFs, Mermaid or PlantUML designs, or infrastructure-as-code.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake
Install

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.

Any agent
npx skills add HoangNguyen0403/agent-skills-standard --skill system-design-artifact-intake
Clone the repo
git clone --depth 1 https://github.com/HoangNguyen0403/agent-skills-standard

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for system-design-artifact-intake

README.md
[![agentmods](https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake/github.svg)](https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake)
Your own site
<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake/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.

agentmods 80×15 button for system-design-artifact-intake

Your own site · 80×15
<a href="https://agentmods.dev/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake"><img src="https://agentmods.dev/badge/skills/hoangnguyen0403/agent-skills-standard/system-design-artifact-intake.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,043 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00074 $0.01043
Opus 5 $0.00037 $0.00522
Sonnet 5 $0.00015 $0.00209
Haiku 4.5 $0.00007 $0.00104

Measured 13d ago against content hash ca664f644f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

system-design-artifact-intake 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 13d 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.

.agents/skills/system-design/system-design-artifact-intake/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design Artifact Intake

Priority: P1 (HIGH)

The artifact is not the design; the extracted fact sheet is. Never review what you have not provably read.

Classify the Artifact First

Class Members Route
A - structured text Mermaid, PlantUML/C4, Structurizr DSL, Excalidraw JSON, raw .drawio, Archify JSON, IaC, ASCII art Parse directly
B - embedded structure .drawio.png / .drawio.svg, pptx/docx with glued connectors, Confluence drawio-macro attachments, Lucid/Miro/Figma exports or API, Whimsical-to-Mermaid Extract the source, then treat as Class A
C - vision only Plain images, whiteboard photos, rendered PDF pages Vision protocol below
D - mixed prose + artifacts PDF docs, Confluence/Notion pages, Word/Markdown docs Split streams, classify each embed, cross-check prose against topology

Probe Before Vision

  • A "screenshot" is often a .drawio.png: check PNG text chunks for an mxfile key before reading pixels. .drawio.svg carries the model in the root content attribute; pptx connectors live in stCxn/endCxn; Confluence drawio macros store the XML as a page attachment.
  • One probe replaces an entire lossy vision pass. Recipes per format: artifact formats.
  • A share link is not an artifact. Ask for an export or API access; never scrape a link.

The Design Fact Sheet

Extract every artifact into the same shape before any judgment:

  • Nodes: id, label, inferred type - never a guessed type without marking it inferred.
  • Edges: source, target, direction, label, and a confidence mark per edge.
  • Boundaries: kind (trust, deployment, ownership) and member nodes.
  • Prose claims: each with its source location, kept separate from drawn topology.
  • UNRECOVERABLE: what the artifact cannot tell you (numbers, SLOs, consistency, intent).

Vision Protocol (Class C)

  1. Enumerate every node with label and position first. No edge before the node list is complete.
  2. Resolve each edge against that node list: source, target, direction, label. Arrowheads and crossing lines are the least reliable pixels - mark ambiguity per edge, never per diagram.
  3. Boundaries third: dashed frames, tints, swimlanes become containment lists.
  4. An unlabeled arrow stays an unlabeled edge. Never infer a protocol from proximity.
  5. Request the source file when fidelity matters, and say why: the extraction is lossy and the review inherits every loss.

Read the full file on GitHub · 81 lines

Files

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.

Changes

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.

  1. 13d ago First seen · 81 lines · 74 tokens per session scan A ca664f644f2b

Subscribe to this mod's changes

system-design-artifact-intake is a skill published in the GitHub repository HoangNguyen0403/agent-skills-standard (565 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 1,043 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 2026-08-30.

Related

Other skills, from other repositories

elite-engineer

The operating system for elite software engineering in TypeScript, React, and Next.js. Enforces the cognitive models, architecture laws, type-level patterns, component design, visual standards, and performance mandates that separate exceptional software from the ordinary — grounded in named sources (Torvalds…

Kerim-Sabic/elite-engineer · 167 tokens

oma-frontend

Frontend specialist for React, Next.js, Angular, TypeScript with FSD-lite architecture, shadcn/ui, and design system alignment. Use for UI, component, page, layout, CSS, Tailwind, shadcn, Angular, and RxJS work.

first-fluke/fullstack-starter · 58 tokens

design-patterns

Frontend design patterns with React 19.2 and TypeScript 6 examples (Composition, Compound Components, Custom Hooks, Render Props, HOC, State Machines). Use when user asks "implement pattern", "use composition", or when designing reusable components.

altmemy/claude-code-templates · 55 tokens

react-nextjs

React 19.2 + Next.js 16 development - Server Components, Cache Components, proxy.ts, View Transitions, App Router, TypeScript 6, and Tailwind CSS v4. Use when building frontend apps, creating components, or asking "how do I set up X?".

altmemy/claude-code-templates · 63 tokens

code-quality

Comprehensive frontend code review for TypeScript 6 and React 19.2 — clean code principles, component patterns, type safety, accessibility, and performance. Use when user says "review code", "refactor", "check this PR", or before merging changes.

altmemy/claude-code-templates · 57 tokens

server-side-calls

Call tRPC procedures directly from server code using t.createCallerFactory() and router.createCaller(context) for integration testing, internal server logic, and custom API endpoints. Catch TRPCError and extract HTTP status with getHTTPStatusCodeFromError(). Error handling via onError option.

trpc/trpc · 61 tokens