949e169fb3
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01AS7hf1w8XCi63QduxCUrVn
45 lines
2.4 KiB
Markdown
45 lines
2.4 KiB
Markdown
@./AGENTS.md
|
|
|
|
## Firmenwissen (onyx & thicket)
|
|
|
|
- For questions about internal processes, tools, or "wie machen wir X
|
|
bei Seibert", check the company knowledge first (skill `onyx`).
|
|
- **Default to onyx for any "find internal docs on topic X" research**
|
|
(products, services, systems, teams) — its semantic index regularly
|
|
surfaces Confluence pages that direct CQL/JQL text search misses
|
|
(unexpected spaces, differently worded titles). Use direct
|
|
Confluence CQL only for precise lookups where space or title is
|
|
already known.
|
|
- **Thicket direct only for people lookups** (role, team, email) —
|
|
its other sections are thin, use onyx there.
|
|
- Default mode `answer`; `search` only when you need the source text
|
|
itself — always cite source links.
|
|
|
|
## 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.
|