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.
npx skills add hoangatg/ai-agent-toolkit --skill ai-agents-architectgit clone --depth 1 https://github.com/hoangatg/ai-agent-toolkitWrote 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/skills/hoangatg/ai-agent-toolkit/ai-agents-architect)<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/ai-agents-architect"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/ai-agents-architect/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.
<a href="https://agentmods.dev/skills/hoangatg/ai-agent-toolkit/ai-agents-architect"><img src="https://agentmods.dev/badge/skills/hoangatg/ai-agent-toolkit/ai-agents-architect.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00037 | $0.01128 |
| Opus 5 | $0.00018 | $0.00564 |
| Sonnet 5 | $0.00007 | $0.00226 |
| Haiku 4.5 | $0.00004 | $0.00113 |
Grade A, and why
ai-agents-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 10d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agents Architect
Design systems where AI acts, not just responds.
1. Agent Architecture Patterns
Single Agent
User → Agent → [Think → Act → Observe] → Response
Multi-Agent
User → Orchestrator → [Agent A, Agent B, Agent C] → Merge → Response
Pattern Selection
| Pattern | When to Use |
|---|---|
| Single agent | Well-scoped tasks, clear tool set |
| Sequential chain | Pipeline workflows (A → B → C) |
| Parallel fan-out | Independent subtasks, merge results |
| Hierarchical | Complex tasks, manager + workers |
| Debate/consensus | Critical decisions, multiple perspectives |
2. Core Agent Components
| Component | Purpose | Design Question |
|---|---|---|
| Planner | Break task into steps | How complex is decomposition? |
| Memory | Short-term + long-term context | What needs persisting? |
| Tools | External capabilities | What actions can agent take? |
| Evaluator | Assess quality/progress | How to know if done? |
| Guardrails | Safety and boundaries | What should agent NOT do? |
3. Tool Design for Agents
Principles
| Principle | Application |
|---|---|
| Clear naming | search_documents not do_thing |
| Typed inputs | Schema with validation |
| Bounded scope | One action per tool |
| Error messages | Actionable, not cryptic |
| Idempotent | Safe to retry |
Tool Categories
| Category | Examples |
|---|---|
| Read | Search, fetch, query database |
| Write | Create file, send email, update DB |
| Transform | Parse, convert, calculate |
| Communicate | Notify, ask user, delegate |
4. Memory Architecture
Memory Types
| Type | Duration | Use Case |
|---|---|---|
| Working | Current task | Conversation context |
| Episodic | Past interactions | Learning from history |
| Semantic | Permanent knowledge | Domain expertise |
| Procedural | Learned workflows | Repeated task patterns |
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.
- 10d ago First seen · 174 lines · 37 tokens per session scan A 88a3d6ad5233
ai-agents-architect is a skill published in the GitHub repository hoangatg/ai-agent-toolkit (1 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 1,128 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.
Other skills, from other repositories
opencode
Delegate coding tasks to the OpenCode CLI for feature work, refactoring, PR review, and autonomous-style runs. Requires opencode installed where the agent can execute shell commands.
codex
Delegate coding tasks to the OpenAI Codex CLI for features, refactoring, PR reviews, and batch fixes. Requires the codex CLI and typically a git repository.
deepnote
DeepNote knowledge base: persistent interlinked markdown wiki with ingest, query, lint, link graph and history.
golang-patterns
Idiomatic Go patterns, best practices, and conventions for building robust, efficient, and maintainable Go applications.
clickhouse-io
ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.
springboot-patterns
Spring Boot architecture patterns, REST API design, layered services, data access, caching, async processing, and logging. Use for Java Spring Boot backend work.