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 jamestorrevillas/dev-skills --skill ai-agent-designgit clone --depth 1 https://github.com/jamestorrevillas/dev-skillsWrote 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/jamestorrevillas/dev-skills/ai-agent-design)<a href="https://agentmods.dev/skills/jamestorrevillas/dev-skills/ai-agent-design"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/ai-agent-design/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/jamestorrevillas/dev-skills/ai-agent-design"><img src="https://agentmods.dev/badge/skills/jamestorrevillas/dev-skills/ai-agent-design.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 | $0.00094 | $0.01886 |
| Opus 5 | $0.00047 | $0.00943 |
| Sonnet 5 | $0.00019 | $0.00377 |
| Haiku 4.5 | $0.00009 | $0.00189 |
Grade B, and why
ai-agent-design 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 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
- **Never** allow agents to execute arbitrary code without sandboxing How it starts
The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Agent Design
Core Philosophy
Agents are not magic — they are systems with inputs, outputs, memory, tools, and decision logic. Design them with the same rigor as any production software. Every agent should have a clear purpose, defined boundaries, and explicit failure modes.
Agent Design Principles
1. Clarify Intent Before Acting
An agent must ask clarifying questions when the user's intent is ambiguous — before executing any irreversible action. Use this pattern:
- Is the goal clear? If not, ask one focused question.
- Are the constraints known? (scope, output format, data sources)
- What does success look like?
2. Specification Before Code
Before writing agent logic, generate a spec or task list file:
- Define the agent's role and responsibilities
- List all tools it needs access to
- Define input/output contracts
- Identify failure modes and fallback behavior
- Then write the code
3. Single Responsibility
Each agent should do one thing well. Prefer a team of specialized agents over one general-purpose agent.
Orchestration Patterns
| Pattern | When to Use | Description |
|---|---|---|
| Sequential | Linear pipelines | Agents chain in fixed order (draft → review → publish) |
| Supervisor | Complex multi-module tasks | Lead agent routes to specialized workers |
| ReAct | Autonomous problem solving | Combines reasoning (Thought) + acting (Tool Use) |
| Group Chat | Collaborative tasks | Multi-agent communication with human oversight |
| DAG | Stateful workflows | Directed acyclic graph for cyclical, stateful orchestration |
Framework Selection Guide
| Framework | Best For | Status |
|---|---|---|
| LangGraph | Complex stateful agents, cyclical workflows, multi-agent orchestration, production-grade | ✅ Active — GA May 2025 |
| LangChain | Simple RAG pipelines, linear workflows, quick prototypes | ✅ Active — use for RAG, not for agents |
| CrewAI | Role-based multi-agent teams ("Manager", "Researcher", "Writer") | ✅ Active |
| Microsoft Agent Framework | Enterprise agents in Azure ecosystem — replaces AutoGen + Semantic Kernel | ✅ Active — Public Preview Oct 2025, GA targeted Q1 2026 |
| AutoGen | Legacy — still works but no new features | ⚠️ Maintenance mode since Oct 2025 |
| Custom (MCP) | Lightweight, portable, interoperable agent tools via open standard | ✅ Active |
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 · 227 lines · 0 tokens per session scan B 72c82aec1ba1
ai-agent-design is a skill published in the GitHub repository jamestorrevillas/dev-skills (3 stars, last pushed 5mo ago), licensed MIT. It adds 94 tokens to every session and 1,886 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
rag-architecture
Build retrieval-augmented generation systems that ground LLMs in your data.
memory-systems
This skill should be used for persistent semantic memory in agent systems: cross-session knowledge retention, entity tracking, temporal validity, graph or vector retrieval, memory consolidation, and memory benchmark selection. Route file-backed scratchpads to filesystem-context, handoff summaries to…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
similarity-search-patterns
Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.
senior-ml-engineer
World-class ML engineering skill for productionizing ML models, MLOps, and building scalable ML systems. Expertise in PyTorch, TensorFlow, model deployment, feature stores, model monitoring, and ML infrastructure. Includes LLM integration, fine-tuning, RAG systems, and agentic AI. Use when deploying ML models…
graph-retrieval
Exposes graph-based retrieval as a tool capability via querygraph. Reads normalized graph store files, builds a query-relevant subgraph, and returns LLM-friendly semantic triples with replayable evidence metadata.