rootnode-domain-agentic-contextlisted

Specialized agentic and context engineering prompt methodology for Claude. Use when designing AI agents — system prompts, tool definitions, context window architectures, failure mode planning, multi-agent coordination, agent evaluation. Trigger on: "design an agent," "build a system prompt for an agent," "architect an agent's context," "design tool definitions," "agent system prompt," "context window architecture," "tool interface design," "evaluate agent behavior," "multi-agent coordination," "context engineering for agents," "ACI design." Provides 12 tested approaches for agent architecture (designing agents, not using them). Do NOT use for evaluating or scoring individual non-agent prompts (use rootnode-prompt-validation if available). Do NOT use for general software architecture that hosts agents (use standard technical reasoning for that).
drayline/rootnode-skills · ★ 40 · AI & Automation · score 76

Install: claude install-skill drayline/rootnode-skills

# Agentic & Context Engineering — Prompt Methodology > **Calibration:** Tier 1 (Model-compatible) - runs cleanly on the current dual-primary tier (Opus 5, Sonnet 5) as well as Haiku 4.5 with extended thinking. Structured retrieval, rule evaluation, or template lookup - output shape does not depend on model class. Correct-shape output also on Opus 4.8 (fallback-graceful) and Sonnet 4.6 (legacy-graceful). See repository README for model compatibility. Specialized approaches for designing AI agent systems: the system prompts agents follow, the tool definitions they consume, the context architectures they operate within, the failure modes they encounter, and the evaluation criteria that measure their performance. **This Skill is about designing agents, not using them.** Use it when the task is authoring an agent's behavioral instructions, tool interfaces, or context management strategy. Do not use it for the software infrastructure that hosts agents (servers, APIs, deployment) — standard technical approaches cover that. ## v4.0 update — refusal & fallback semantics (Opus 5, Fable 5) When designing agents that build on Opus 5 or Fable 5, account for safety-classifier refusals as a first-class signal — not an error condition. **Refusal categories** (from Anthropic's refusals-and-fallback page): - `cyber` — could enable cyber harm (malware, exploits). Benign cybersecurity work can also trigger. - `bio` — biological harm risk. Benign life-sciences work can also trigger. - `fron