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 magnus919/agent-skills --skill software-architecturegit clone --depth 1 https://github.com/magnus919/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/magnus919/agent-skills/software-architecture)<a href="https://agentmods.dev/skills/magnus919/agent-skills/software-architecture"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/software-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/magnus919/agent-skills/software-architecture"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/software-architecture.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 | $0.00113 | $0.01447 |
| Opus 5 | $0.00056 | $0.00724 |
| Sonnet 5 | $0.00023 | $0.00289 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
software-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 9d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Software Architecture
Use this skill to make system-level design decisions and leave an inspectable path from drivers to evidence. It owns the architecture decision workflow, not the implementation of any subsystem.
Workflow
- Frame the decision. Establish the desired outcome, stakeholders, constraints, decision horizon, reversibility, affected systems, and evidence gaps. Do not invent scale, regulatory, latency, or ownership facts.
- Turn qualities into scenarios. Name the architecture characteristics that matter, express each as an observable scenario, prioritize them, and expose conflicts. Load
references/architecture-characteristics-and-tradeoffs.md. - Choose boundaries and shape. Compare styles, topology, and deployment granularity against the scenarios and team operating capacity. Load
references/styles-topologies-and-granularity.md. - Test ownership and coupling. Identify policy, data, change, runtime, and team boundaries. Treat a service split as a hypothesis, not a default. Load
references/coupling-modularity-and-data-ownership.md. - Make runtime behavior explicit. For asynchronous or distributed flows, specify authority, consistency, ordering, retries, duplicates, timeouts, partial failure, recovery, and reconciliation. Load
references/distributed-workflows-and-consistency.md. - Record and verify. Capture the decision and rejected alternatives in
templates/architecture-design-brief.mdandtemplates/tradeoff-record.md; usetemplates/architecture-review.mdfor challenge and sign-off. Define fitness evidence and drift response withreferences/evolution-fitness-functions-and-drift.md. - Plan change without hiding execution ownership. Identify evolutionary slices, coexistence assumptions, and handoff conditions. Load
references/migration-and-coexistence.md; route an approved transition tomigration-engineering. - Facilitate proportionately. Match review depth to blast radius, irreversibility, uncertainty, and cross-team impact. Load
references/architecture-practice-and-facilitation.md.
What ships with it
13 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.
- evals/evals.json 12 KB
- README.md 2.0 KB
- references/architecture-characteristics-and-tradeoffs.md 2.1 KB
- references/architecture-practice-and-facilitation.md 1.8 KB
- references/coupling-modularity-and-data-ownership.md 1.9 KB
- references/distributed-workflows-and-consistency.md 1.6 KB
- references/evolution-fitness-functions-and-drift.md 1.7 KB
- references/migration-and-coexistence.md 1.5 KB
- references/source-index.md 2.9 KB
- references/styles-topologies-and-granularity.md 1.9 KB
- templates/architecture-design-brief.md 1.1 KB
- templates/architecture-review.md 1.1 KB
- templates/tradeoff-record.md 768 B
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.
- 9d ago First seen · 67 lines · 113 tokens per session scan A a38b4b7996b9
software-architecture is a skill published in the GitHub repository magnus919/agent-skills (76 stars, last pushed yesterday), licensed MIT. It adds 113 tokens to every session and 1,447 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…