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 ApexIQ/skillsmith --skill agno_best_practicesgit clone --depth 1 https://github.com/ApexIQ/skillsmithWrote 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/apexiq/skillsmith/agno_best_practices)<a href="https://agentmods.dev/skills/apexiq/skillsmith/agno_best_practices"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/agno_best_practices/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/apexiq/skillsmith/agno_best_practices"><img src="https://agentmods.dev/badge/skills/apexiq/skillsmith/agno_best_practices.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 | $0.00038 | $0.00572 |
| Opus 5 | $0.00019 | $0.00286 |
| Sonnet 5 | $0.00008 | $0.00114 |
| Haiku 4.5 | $0.00004 | $0.00057 |
Grade A, and why
agno-ai-best-practices 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 12d 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.
What it actually says
🧠 AI Agent Best Practices
Philosophy: Agents are powerful but unpredictable. Build with guardrails.
1. Core Architecture
| Pattern | Good | Bad |
|---|---|---|
| Agent Scope | ClassifierAgent, SummarizerAgent |
GodAgentThatDoesEverything |
| Tool Design | Typed args, descriptive docstrings | Magic strings, no types |
- One Agent = One Responsibility. Single-purpose agents are more reliable.
- Tools as First-Class Citizens:
- Tools should be well-typed Python/TS functions.
- LLMs read type hints and docstrings to understand how to use tools!
2. Agent Design
- System Prompts:
- Role: "You are a customer service assistant."
- Output Format: "Return JSON only. Schema:
{...}" - Constraints: "Never make up information. Say 'I don't know' if unsure."
- Memory:
- Short-term: Conversation history within a session.
- Long-term: Vector DB for RAG tasks (when needed).
3. Performance & Reliability
| Model Type | Use Case |
|---|---|
| Fast/Small (GPT-3.5, Gemma) | Classification, extraction, simple tasks. |
| Powerful (GPT-4, Claude) | Complex reasoning, coding, multi-step tasks. |
- Observability: Log all inputs, outputs, and tool calls.
- Error Handling: Agents should gracefully handle tool failures, not crash.
- Retries: Implement retry logic for transient API failures.
4. Deployment
- Statelessness: Agents fetch state, act, then save. No in-memory state.
- Async: Use async/await to prevent blocking during API calls.
- Cost Awareness: Log token usage. Optimize prompts to reduce costs.
Examples
- New agent: Define system prompt -> Create tools -> Wire to API -> Write tests with mocked responses.
Guidelines
- Mock LLM responses in tests to avoid costs and flakiness.
- Use
temperature=0in tests for deterministic outputs. - Always have a human-in-the-loop for high-stakes actions.
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.
- 12d ago First seen · 62 lines · 38 tokens per session scan A 1d2465993bbe
agno-ai-best-practices is a skill published in the GitHub repository ApexIQ/skillsmith (5 stars, last pushed 5mo ago), licensed MIT. It adds 38 tokens to every session and 572 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
recover-from-failure
How to recover when a tool call fails — diagnose, not blindly retry.
workspace-conventions
Reminders about how Dawn's workspace tools behave and what the path-jail allows.
dawn
Build AI agents and workflows with the Dawn framework — the TypeScript meta-framework for LangGraph. Use when creating, editing, or debugging a Dawn app (routes, tools, state, agents, workflows, testing, deployment).
cite-sources
How to attribute every factual claim to a corpus document.
synthesize-findings
How to merge researcher sub-answers into one cited report.
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.