🎁 Get the FREE AI Skills Starter Guide β€” Subscribe β†’
BytesAgainBytesAgain
πŸ¦€ ClawHub

Agents

by @ivangdavila

Design, build, and deploy AI agents with architecture patterns, framework selection, memory systems, and production safety.

Versionv1.0.0
Downloads1,946
Installs12
Stars⭐ 3
TERMINAL
clawhub install agents

πŸ“– About This Skill


name: Agents description: Design, build, and deploy AI agents with architecture patterns, framework selection, memory systems, and production safety.

When to Use

Use when designing agent systems, choosing frameworks, implementing memory/tools, specifying agent behavior for teams, or reviewing agent security.

Quick Reference

| Topic | File | |-------|------| | Architecture patterns & memory | architecture.md | | Framework comparison | frameworks.md | | Use cases by role | use-cases.md | | Implementation patterns & code | implementation.md | | Security boundaries & risks | security.md | | Evaluation & debugging | evaluation.md |

Before Building β€” Decision Checklist

  • [ ] Single purpose defined? If you can't say it in one sentence, split into multiple agents
  • [ ] User identified? Internal team, end customer, or another system?
  • [ ] Interaction modality? Chat, voice, API, scheduled tasks?
  • [ ] Single vs multi-agent? Start simple β€” only add agents when roles genuinely differ
  • [ ] Memory strategy? What persists within session vs across sessions vs forever?
  • [ ] Tool access tiers? Which actions are read-only vs write vs destructive?
  • [ ] Escalation rules? When MUST a human step in?
  • [ ] Cost ceiling? Budget per task, per user, per month?
  • Critical Rules

    1. Start with one agent β€” Multi-agent adds coordination overhead. Prove single-agent insufficient first. 2. Define escalation triggers β€” Angry users, legal mentions, confidence drops, repeated failures β†’ human 3. Separate read from write tools β€” Read tools need less approval than write tools 4. Log everything β€” Tool calls, decisions, user interactions. You'll need the audit trail. 5. Test adversarially β€” Assume users will try to break or manipulate the agent 6. Budget by task type β€” Use cheaper models for simple tasks, expensive for complex

    The Agent Loop (Mental Model)

    OBSERVE β†’ THINK β†’ ACT β†’ OBSERVE β†’ ...
    

    Every agent is this loop. The differences are:

  • What it observes (context window, memory, tool results)
  • How it thinks (direct, chain-of-thought, planning)
  • What it can act on (tools, APIs, communication channels)
  • ⚑ When to Use

    Use when designing agent systems, choosing frameworks, implementing memory/tools, specifying agent behavior for teams, or reviewing agent security.