zyrax-guard: Agent for Claude Code

.claude/agents/architect.md

architect is an agent for Claude Code from tiagosilva07/zyrax-guard. It costs 85 tokens per session (583 once invoked), scanned A, original, MIT.

A software architecture planning agent that designs how a new feature or service should be structured before coding begins. It covers components, data movement, APIs, databases, and an implementation plan.

In plain words
What is it for?
Use it for new features, services, minimum viable products, or difficult structural decisions. It can outline system parts, request flows, API contracts, database tables, scaling needs, and ordered build steps.
Why use it?
It turns an unclear technical idea into a plan another developer can follow. This helps avoid adding unnecessary infrastructure or making major design decisions during coding.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is tiagosilva07/zyrax-guard's own configuration. It tells Claude Code how to work on zyrax-guard itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything zyrax-guard configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/tiagosilva07/zyrax-guard/main/.claude/agents/architect.md
Clone the repo
git clone --depth 1 https://github.com/tiagosilva07/zyrax-guard

Made for: Claude Code.

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 architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/tiagosilva07/zyrax-guard/architect.svg)](https://agentmods.dev/agents/tiagosilva07/zyrax-guard/architect)
Your own site
<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>
Per session 85 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 583 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00085 $0.00583
Opus 5 $0.00043 $0.00292
Sonnet 5 $0.00017 $0.00117
Haiku 4.5 $0.00009 $0.00058

Measured 6d ago against content hash 7209d3016cec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

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.

.claude/agents/architect.md · 57 lines

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:

  1. Problem & constraints — what we're building, expected scale, the 2-3 constraints that actually shape the design.
  2. System architecture — components and their responsibilities; what talks to what. A short text or mermaid diagram, not an essay.
  3. Data flow — how a key request travels end to end.
  4. API design — endpoints/contracts (method, path, request/response shape, error cases). For Go, sketch the handler/service boundary.
  5. Database schema — tables/collections, keys, indexes, the relationships that matter. Call out what will need to scale (hot tables, N+1 risks).
  6. Caching / scaling strategy — only where load justifies it; say where it does NOT yet.
  7. 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.

Read the full file on GitHub · 57 lines

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. 6d ago First seen · 57 lines · 85 tokens per session scan A 7209d3016cec

Subscribe to this mod's changes

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.