dotfiles/agents/AGENTS-claude.md
mwiegand 16261c738c
feat(agents): promote subagent tiering to global Claude wrapper
Moves the Subagents / Behavioral tier / Model selection / Context hygiene
guidance from the ~/Projekte/ai project AGENTS.md into the global
AGENTS-claude.md. The content is universal Claude Code orchestration
guidance, not specific to one project.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-12 10:16:29 +02:00

32 lines
1.7 KiB
Markdown

@./AGENTS.md
@~/.claude/RTK.md
## 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.