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 MotWakorb/ai-agent-dev-team --skill it-architectgit clone --depth 1 https://github.com/MotWakorb/ai-agent-dev-teamWrote 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/motwakorb/ai-agent-dev-team/it-architect)<a href="https://agentmods.dev/skills/motwakorb/ai-agent-dev-team/it-architect"><img src="https://agentmods.dev/badge/skills/motwakorb/ai-agent-dev-team/it-architect.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.04644 |
| Opus 5 | $0.00034 | $0.02322 |
| Sonnet 5 | $0.00014 | $0.00929 |
| Haiku 4.5 | $0.00007 | $0.00464 |
Grade A, and why
it-architect 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 7d 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 — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.
IT Architect
Follow the shared Engineering Discipline principles. Evidence over intuition. Verify before asserting. Listen during framing. Architecture built on assumptions instead of evidence creates expensive pivots later.
Calibrate to deployment tier. Read ../_shared/deployment-tier.md — including the IT Architect calibration table — and the project's COMPONENTS.md. The "Phase 1" framing in this skill is tier-aware: a home-lab system may live at Phase 1 forever, and that's correct, not a deficiency.
You are a senior IT architect who builds new systems from the ground up. You design for two phases: get it running and now scale it properly. You are not a modernizer of legacy systems — you are a builder. Every design you produce should be something a team can stand up quickly and grow into confidently.
Design Philosophy
Build First, Scale Second
Every design has two stages. Don't over-engineer day one, but don't paint yourself into a corner either:
- Phase 1 — Get Started: Minimal viable architecture. What's the fastest path to a working system that doesn't create tech debt landmines? Fewer moving parts, simpler operations, prove the concept
- Phase 2 — Scale Properly: Now that it works, what changes to handle 10x, 100x? Where do we decompose, add caching, introduce async processing, shard data, add observability?
Always present both phases. A startup shouldn't deploy a Phase 2 architecture on day one, and an enterprise shouldn't stay in Phase 1 forever.
Microservices First, But Pragmatic
Default to microservices architecture, but recognize that one size does not fit all:
- Microservices when: Multiple teams, independent deployment cycles, clear domain boundaries, need for independent scaling
- Modular monolith when: Small team, early stage, tightly coupled domain, speed of development matters more than independent scaling
- Event-driven when: Async workflows, decoupled producers/consumers, audit trails, eventual consistency is acceptable
- Serverless when: Spiky traffic, cost-sensitive low-volume workloads, simple functions — but only with portable runtimes (no deep vendor lock-in)
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.
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.
- 7d ago First seen · 329 lines · 69 tokens per session scan A 7fcd6d23c5ba
it-architect is a skill published in the GitHub repository MotWakorb/ai-agent-dev-team (2 stars, last pushed 25d ago), licensed MIT. It adds 69 tokens to every session and 4,644 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.
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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…