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 agentmods add skills/fattain-naime/engineering-docs/system-architecture-documentnpx skills add fattain-naime/engineering-docs --skill system-architecture-documentgit clone --depth 1 https://github.com/fattain-naime/engineering-docsWhat 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 | $0.00054 | $0.03402 |
| Opus 5 | $0.00027 | $0.01701 |
| Sonnet 5 | $0.00011 | $0.00680 |
| Haiku 4.5 | $0.00005 | $0.00340 |
Grade A, and why
system-architecture-document 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 2d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Produce a System Architecture Document (SAD) that gives every stakeholder - from non-technical product leadership to infrastructure engineers - the right level of detail about the system's structure. This document answers:
- What components make up the system?
- How do they communicate?
- Why was the architecture designed this way?
- Where does data flow and where are the trust boundaries?
- What are the non-functional constraints the architecture must satisfy?
Input
Works best with: The name of the system or subsystem being documented. Also valuable: Existing diagrams, technology stack decisions, known integration points, existing ADRs, NFR targets.
Example invocation: Create a system architecture document for PayFlow, a multi-brand payment gateway with a PHP 8.3 backend, MySQL database, custom plugin system, and white-label domain routing.
Key Concepts
C4 Model (Simon Brown)
The C4 Model provides a hierarchical, developer-friendly approach to architecture documentation - like a "Google Maps" with multiple zoom levels:
- Level 1: System Context - The system's place in the world. Users and external systems. Intended for all stakeholders.
- Level 2: Container - The major deployable units (web apps, APIs, databases, queues). Intended for technical leads and architects.
- Level 3: Component - The internal structure of a container (controllers, services, repositories). Intended for developers.
- Level 4: Code - Class/function level. Usually omitted as IDEs serve this better.
Always use Mermaid for diagrams to keep them version-controllable.
4+1 View Model (Kruchten)
Five complementary views of the same architecture:
- Logical View - Functional decomposition (classes, modules, layers)
- Process View - Runtime behavior, concurrency, synchronization
- Development View - Code organization, modules, packages
- Deployment / Physical View - Infrastructure, nodes, network topology
- Scenarios (+1) - Key use cases that validate the other four views
What ships with it
2 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.
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.
- 2d ago First seen · 273 lines · 54 tokens per session scan A 5b32b461bdf2
system-architecture-document is a skill published in the GitHub repository fattain-naime/engineering-docs (4 stars, last pushed 18d ago), licensed MIT. It adds 54 tokens to every session and 3,402 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…