jpmschweitzerandClaude Opus 4.6
465f2bdf98
Introduces 5 rules files following Anthropic's recommended pattern for splitting large CLAUDE.md files. Rules auto-load every session and separate CLI reference material from core project identity. - tea-cli.md: Gitea CLI reference, PR creation, protected branches - git-safety.md: staging rules, commit conventions (from git-commit skill) - project-structure.md: full annotated directory tree - team-patterns.md: model selection, large content push pattern - local-services.md: Gitea/Qdrant/Ollama endpoints Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
20 lines
1.0 KiB
Markdown
20 lines
1.0 KiB
Markdown
# Team Patterns
|
|
|
|
## Model selection
|
|
|
|
Default model is Opus 4.6 (200K context). For heavy sessions (workshops,
|
|
sprint planning, large reviews), switch to extended context on-demand:
|
|
|
|
- `/model sonnet[1m]` — Sonnet 4.6 with 1M context window
|
|
- `/model opus[1m]` — Opus 4.6 with 1M context window
|
|
- Cost: 2x input + 1.5x output for tokens beyond 200K (Tier 4 required)
|
|
|
|
## Large content pushes
|
|
|
|
When producing many files (wiki pages, content batches, bulk docs):
|
|
1. **Lore librarian** agent (read-only): ingests all source material, answers focused context queries from writers, tracks cross-file consistency
|
|
2. **Multiple writer** agents (parallel, by domain): each gets a task slice, writes directly to disk using the Write tool — one file at a time, write often, no text accumulation
|
|
3. **Reviewer** agents (blocked until writing done): check voice consistency, attribute uniformity, style
|
|
|
|
Key: writers use Write tool directly (no transcription bottleneck), librarian catches contradictions early, split work by domain not volume.
|