dotfiles/agents/AGENTS-claude.md

@./AGENTS.md

Firmenwissen (onyx)

• For questions about internal processes, tools, or "wie machen wir X bei Seibert", check the company knowledge first: invoke the onyx skill and search, then answer from the passages with source links.
• Prefer search (answer yourself); use answer/chat only when I explicitly want Onyx's generated answer or a persistent session.

Subagents

Spawn subagents to (a) isolate context-heavy work from the main thread, or (b) parallelize independent subtasks. Before spawning, ask: could Bash/Grep/Read do this directly? Subagents have overhead — skip the middleman for mechanical lookups.

Use the Agent tool. Prefer specialized agent types (Explore, code-reviewer, Plan, etc.) over general-purpose when one fits.

Behavioral tier (MANDATORY — always set)

Prefix every Agent prompt with one of:

• [TIER: FAST] — return raw results immediately; no internal monologue, no synthesis
• [TIER: STANDARD] — focused implementation logic; minimal preamble
• [TIER: DEEP] — complex reasoning; must conclude with a summary

Model selection (override only when needed)

Resolution order: explicit model param → agent type frontmatter → parent inheritance.

1. Don't override specialized agent types (Explore, code-reviewer, Plan, etc.) — their frontmatter is tuned. Leave model off.
2. For general-purpose under an Opus parent: set model: sonnet — avoid paying Opus rates for routine subagent work.
3. model: opus on a subagent only when isolated context and reasoning beyond what the parent can easily do inline are both needed.
4. model: haiku only for mechanical tasks: bulk classification, format conversion, summarizing pre-filtered text. Code-semantic work → Sonnet.

Context hygiene

• Prefer parallel Explore calls over sequential general-purpose sessions.
• Don't reuse task_id for fresh lookups; start new to keep prompts tiny.
• Summarize subagent findings in the main thread to keep the terminal clean.