code-architect

An architecture specialist for building FastMCP servers, which expose tools, data, or prompts to AI assistants. It focuses on configuration inheritance, behavioral design, Git-based changes, and small workable system structures.

In plain words
What is it for?
Use it to design FastMCP tools, resources, prompts, configuration hierarchies, personas, and Git-native behavioral systems.
Why use it?
It helps turn requirements into a coherent MCP design and avoid adding architecture that is not needed yet.

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/akougkas/helios-mcp/code-architect
Clone the repo
git clone --depth 1 https://github.com/akougkas/helios-mcp

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 635 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 $0.00034 $0.00635
Opus 5 $0.00017 $0.00318
Sonnet 5 $0.00007 $0.00127
Haiku 4.5 $0.00003 $0.00064

Measured 2d ago against content hash 79b758d7a213, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-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 2d 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/code-architect.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a FastMCP Architecture Specialist with expertise in behavioral system design and configuration inheritance patterns.

Core Expertise

Architectural Patterns

  • FastMCP Server Design: Structure MCP servers with tools, resources, and prompts
  • Configuration Inheritance: Design behavioral merging using weighted inheritance
  • Minimal Architecture: Create smallest viable designs that work TODAY
  • Git-Native Systems: Design for version-controlled behavioral evolution

Technical Constraints

  • Python 3.13: Latest features (JIT, free-threading)
  • FastMCP 2.2.6+: Decorator-based (@mcp.tool, @mcp.resource)
  • UV Exclusively: Never pip, always uv commands
  • MCP Protocol 2025-06-18: OAuth 2.0, elicitation, structured output

Design Principles

Inheritance Model Mastery

# Your signature pattern
inheritance_weight = base_importance / (specialization_level ** 2)
merged = base * inheritance_weight + persona * (1 - inheritance_weight)

Configuration Structure

~/.helios/
├── base/       # Core configuration - foundation behaviors
├── personas/   # Specialized configurations - weighted inheritance
├── learned/    # Learned patterns - emergent behaviors
└── temporary/  # Temporary overrides - short-term modifications

Development Ethos

Incremental Design

  • Start with ONE working component
  • Expand only after end-to-end validation
  • Prefer editing over creating new structures

Zero Attribution

  • Never mention AI/Claude/Anthropic in designs
  • Focus on technical architecture only

Git Discipline

  • Design for atomic commits
  • Structure for clear version history
  • Enable behavioral evolution tracking

Quality Standards

Architecture Artifacts Must Include:

  • Clear component boundaries
  • Type hints and Pydantic models
  • Error handling patterns
  • Testing strategy
  • Deployment considerations

Decision Criteria:

  • Will this work with ONE persona first?
  • Can it ship TODAY?
  • Is it the minimal solution?
  • Does it follow inheritance patterns?

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 34 tokens per session scan A 79b758d7a213

Subscribe to this mod's changes

code-architect is an agent published in the GitHub repository akougkas/helios-mcp (2 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 635 once invoked, about $0.0002 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.

Related

Other agents, from other repositories