Agent Design Architecture

Agent Design Architecture is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 62 tokens per session (3,403 once invoked), scanned A, original, MIT.

Architecture guidance for building AI agents that perceive information, reason about goals, use tools, and adapt across multiple steps. It covers patterns for connecting agents, tools, data, and human input.

In plain words
What is it for?
Use it when planning agent workflows, choosing agent patterns, defining capabilities, or designing multi-agent systems and tool ecosystems.
Why use it?
It helps turn a collection of model calls and tools into a system with clear boundaries, responsibilities, and control over autonomous actions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Good fit Use it when planning agent workflows, choosing agent patterns, defining capabilities, or designing multi-agent systems and tool ecosystems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/agent-design-architecture
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.

Any agent
npx skills add majiayu000/claude-skill-registry --skill agent-design-architecture
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

Made for: Claude Code, Codex.

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 Agent Design Architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-architecture/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-architecture)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-architecture/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Agent Design Architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/agent-design-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/agent-design-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,403 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00062 $0.03403
Opus 5 $0.00031 $0.01702
Sonnet 5 $0.00012 $0.00681
Haiku 4.5 $0.00006 $0.00340

Measured 9d ago against content hash a521a547b757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Agent Design Architecture 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 9d 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.

skills/agent/agent-design-architecture/SKILL.md · 481 lines

How it starts

The opening of the file, as written. The whole thing — 481 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Design Architecture

Effective agent systems require thoughtful architecture that balances capability, safety, and maintainability. This skill guides designing agent systems from first principles.

Agent Fundamentals

What Makes an Effective Agent

An agent is a system that:

  • Perceives its environment (through tools, data, human input)
  • Reasons about goals and available actions
  • Acts to change state toward objectives
  • Reflects on outcomes to improve future actions
  • Communicates intent and reasoning to humans

Key distinction from simple chatbots:

  • Agents have goals beyond responding conversationally
  • Agents persist across multiple interactions
  • Agents compose multiple tools into workflows
  • Agents reason about outcomes and adapt
  • Agents operate with bounded autonomy (within constraints)

Agent Architecture Patterns

Pattern 1: Tool-Using Agent (Simplest)

User Request → Model Reasoning → Tool Selection → Tool Execution → Result → Response

When to use: Single-step tasks, straightforward tool selection Example: "Find the latest sales data and summarize" Complexity: Low | Autonomy: Low

Design considerations:

  • Clear tool descriptions for LLM selection
  • Explicit constraints on tool combinations
  • Fallback handling for tool failures

Pattern 2: Agentic Loop (Iterative)

Goal → Reasoning → Action Selection → Execute → Observe → Success?
                      ↑_____No_________↓
                    Reflect & Replan

When to use: Complex, multi-step tasks; planning required Example: "Analyze customer complaints, identify patterns, propose solutions" Complexity: Medium | Autonomy: Medium

Design considerations:

  • Loop termination criteria (max iterations, goal achieved, resource exhausted)
  • State tracking between iterations
  • Reflection mechanism (what worked, what didn't)
  • Tool selection constraints per iteration

Pattern 3: Planning Agent (Explicit Reasoning)

Goal → Decompose → Create Plan → Execute Step → Verify → Adapt Plan

Read the full file on GitHub · 481 lines

Files

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.

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. 9d ago First seen · 481 lines · 62 tokens per session scan A a521a547b757

Subscribe to this mod's changes

Agent Design Architecture is a skill published in the GitHub repository majiayu000/claude-skill-registry (606 stars, last pushed today), licensed MIT. It adds 62 tokens to every session and 3,403 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 2026-09-03.