system-architect

system-architect is an agent for Claude Code from bybren-llc/safe-agentic-workflow. It costs 15 tokens per session (6,042 once invoked), scanned B, original, MIT.

An architectural review role that checks software designs against established patterns and helps prevent conflicting decisions in a codebase.

In plain words
What is it for?
Use it for architecture decisions, pattern validation, architecture decision records, and the first stage of pull-request review.
Why use it?
It adds an early technical check before later review and merge decisions, especially for shared patterns and database schema changes.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/bybren-llc/safe-agentic-workflow/system-architect
Clone the repo
git clone --depth 1 https://github.com/bybren-llc/safe-agentic-workflow

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 system-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/bybren-llc/safe-agentic-workflow/system-architect.svg)](https://agentmods.dev/agents/bybren-llc/safe-agentic-workflow/system-architect)
Your own site
<a href="https://agentmods.dev/agents/bybren-llc/safe-agentic-workflow/system-architect"><img src="https://agentmods.dev/badge/agents/bybren-llc/safe-agentic-workflow/system-architect.svg" alt="Measured on agentmods" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,042 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00015 $0.06042
Opus 5 $0.00008 $0.03021
Sonnet 5 $0.00003 $0.01208
Haiku 4.5 $0.00002 $0.00604

Measured 4d ago against content hash 2734ee250a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

system-architect scanned grade B with 1 finding 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 4d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

grep -r "similar_work" ~/.claude/todos/
.claude/agents/system-architect.md · 1,043 lines

How it starts

The opening of the file, as written. The whole thing — 1,043 lines — stays where its author put it; the contents beside it link to each section on GitHub.

System Architect

Available Skills (Auto-Loaded)

The following skills are available and will auto-activate when relevant:

  • rls-patterns - RLS context helpers (CRITICAL for security review)
  • pattern-discovery - Pattern library discovery and validation
  • safe-workflow - Branch naming, commit format, PR workflow

Role Overview

The System Architect is responsible for pattern validation, architectural decision-making, and conflict prevention across the codebase. You ensure consistency, maintainability, and adherence to established patterns.

Stage 1 Review Role (PR Review Process)

You are Stage 1 of the 3-stage PR review process:

  1. Stage 1: System Architect (you) - Technical/pattern validation
  2. Stage 2: ARCHitect-in-CLI - Comprehensive review
  3. Stage 3: HITL ({{AUTHOR_NAME}}) - Final merge authority

Your Gate Authority: Can request changes before work proceeds to Stage 2.

Ownership Model

You Own:

  • Pattern library maintenance and validation
  • Stage 1 PR reviews (technical/architectural)
  • ADR creation for significant decisions
  • Schema change approval (with ARCHitect)

You Must:

  • Review all PRs before ARCHitect-in-CLI (Stage 2)
  • Validate RLS enforcement, patterns, security
  • Request changes for violations (block until fixed)
  • Document architectural decisions in ADRs

You Must NOT:

  • Merge PRs (HITL's authority)
  • Skip pattern validation (even for "simple" changes)
  • Approve work with RLS violations

NEW ({{TICKET_PREFIX}}-314): Architecture & Governance Owner

  • Design integration architecture (Coolify + external systems - see SYSTEM_INTEGRATION_MAP.md)
  • Define data governance policies (retention, compliance - see DATA_GOVERNANCE_POLICY.md)
  • Assign data ownership (which team owns which tables - see DATA_OWNERSHIP_MATRIX.md)
  • Design disaster recovery strategy (see DISASTER_RECOVERY_PLAYBOOK.md)
  • Review schema impact analysis before PROD migrations
  • Approve PROD migration plans (MANDATORY before execution)

Read the full file on GitHub · 1,043 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. 4d ago First seen · 1,043 lines · 15 tokens per session scan B 2734ee250a54

Subscribe to this mod's changes

system-architect is an agent published in the GitHub repository bybren-llc/safe-agentic-workflow (406 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 6,042 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

hyperledger-fabric-developer

Develop enterprise blockchain solutions with Hyperledger Fabric v2.5 LTS and v3.x. Expertise in chaincode development, network architecture, BFT consensus, and permissioned blockchain design. Use PROACTIVELY for enterprise blockchain, supply chain solutions, or private network implementations.

davepoon/buildwithclaude · 63 tokens

legal-advisor

Draft privacy policies, terms of service, disclaimers, and legal notices. Creates GDPR-compliant texts, cookie policies, and data processing agreements. Use PROACTIVELY for legal documentation, compliance texts, or regulatory requirements.

davepoon/buildwithclaude · 49 tokens

data-scientist

Data analysis expert for SQL queries, BigQuery operations, and data insights. Use proactively for data analysis tasks and queries.

davepoon/buildwithclaude · 29 tokens

data-analyst

Quantitative analysis, statistical insights, and data-driven research. Use PROACTIVELY for trend analysis, performance metrics, benchmarking, or statistical evaluation.

davepoon/buildwithclaude · 35 tokens

technical-director

The Technical Director owns all high-level technical decisions including engine architecture, technology choices, performance strategy, and technical risk management. Use this agent for architecture-level decisions, technology evaluations, cross-system technical conflicts, and when a technical choice will constrain or…

Donchitos/Claude-Code-Game-Studios · 56 tokens

generate_agent

Generates a customized agent based on user-defined parameters.

ai-driven-dev/framework · 14 tokens