Overview
After working with the new lean ambient mode architecture (SessionStart classification rules + UserPromptSubmit preamble + router SKILL), there are remaining tweaks to refine. The core approach is solid but needs tuning based on real usage.
Current Architecture
- SessionStart hook injects ~30-line classification rules as
additionalContext (once per session)
- UserPromptSubmit hook injects one-sentence preamble per message triggering classification + router loading
- Router SKILL is a pure lookup table (~50 lines) mapping intent×depth to domain and orchestration skills
- Three-tier depth: QUICK (direct response), GUIDED (focused skills), ORCHESTRATED (full agent pipelines)
Areas for Potential Tweaks
Classification accuracy, depth calibration, edge cases, and router mappings may need adjustment after real-world usage. Specific areas to evaluate:
- Intent signal accuracy — are prompts being classified correctly?
- Depth boundaries — is the QUICK/GUIDED/ORCHESTRATED split calibrated right?
- Edge cases — ambiguous prompts, multi-intent messages, follow-ups
- Router skill mappings — are the right skills loading for each intent×depth?
- Preamble wording — is the one-sentence injection effective?
Tasks
References
Overview
After working with the new lean ambient mode architecture (SessionStart classification rules + UserPromptSubmit preamble + router SKILL), there are remaining tweaks to refine. The core approach is solid but needs tuning based on real usage.
Current Architecture
additionalContext(once per session)Areas for Potential Tweaks
Classification accuracy, depth calibration, edge cases, and router mappings may need adjustment after real-world usage. Specific areas to evaluate:
Tasks
References
scripts/hooks/session-start-classification— SessionStart hookscripts/hooks/preamble— UserPromptSubmit hookshared/skills/router/SKILL.md— router skillshared/skills/router/references/classification-rules.md— classification rules