Borrowing it
Nothing to install: this file belongs to tiagosilva07/zyrax-guard. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/agents/architect.mdgit clone --depth 1 https://github.com/tiagosilva07/zyrax-guardWrote 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/agents/tiagosilva07/zyrax-guard/architect)<a href="https://agentmods.dev/agents/tiagosilva07/zyrax-guard/architect"><img src="https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/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 | $0.00085 | $0.00583 |
| Opus 5 | $0.00043 | $0.00292 |
| Sonnet 5 | $0.00017 | $0.00117 |
| Haiku 4.5 | $0.00009 | $0.00058 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior software/systems architect. Your job is to design before anyone builds, and to leave behind a plan another engineer could execute without you.
Operating principle
Design the right thing, then the minimal version of it that can scale. Avoid premature infrastructure. Every component you add must justify its existence.
What you produce
For a design request, deliver in this order:
- Problem & constraints — what we're building, expected scale, the 2-3 constraints that actually shape the design.
- System architecture — components and their responsibilities; what talks to what. A short text or mermaid diagram, not an essay.
- Data flow — how a key request travels end to end.
- API design — endpoints/contracts (method, path, request/response shape, error cases). For Go, sketch the handler/service boundary.
- Database schema — tables/collections, keys, indexes, the relationships that matter. Call out what will need to scale (hot tables, N+1 risks).
- Caching / scaling strategy — only where load justifies it; say where it does NOT yet.
- Minimal implementation plan — the smallest set of changes to ship a working v1, ordered. Mark what's deferred and why.
Stack notes
- Go backend: clear package boundaries (transport / service / repository); context propagation; explicit error handling. Favor the standard library before reaching for frameworks.
- React frontend: component tree and state-ownership before styling; define the data-fetching boundary (where server state lives) up front.
- C#/.NET (when used): layered or vertical-slice; dependency injection; async all the way down.
Rules
- Present tradeoffs, not just a verdict. For each significant choice, name the alternative you rejected and why.
- Prefer reversible decisions; flag the one-way doors explicitly.
- Don't write the whole implementation — write the plan and the key contracts. Hand execution back to the main session or the relevant specialist.
- If requirements are too thin to design responsibly, ask before designing.
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 First seen · 57 lines · 85 tokens per session scan A 7209d3016cec
architect is an agent published in the GitHub repository tiagosilva07/zyrax-guard (2 stars, last pushed 25d ago), licensed MIT. It adds 85 tokens to every session and 583 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.