mirror of https://github.com/garrytan/gstack.git
b6b3fbc5e3
generateGBrainContextLoad: 80 -> 115 tokens with explicit skip-header. generateGBrainSaveResults: 500-700 -> 161 tokens per skill with the skill metadata extracted into a typed skillSaveMap (slugPrefix + title + tag). Verbose prose (heredoc body, entity-stub instructions, throttle handling, backlink protocol) moved into a new doc: docs/gbrain-write-surfaces.md (Sections: §Context Load, §Save Template). The agent reads the doc on-demand only when actually saving — one Read call, cached by Claude's context. Net per-planning-skill overhead under un-suppression drops from ~1000 tokens (naive un-suppression) to ~275 tokens (compressed). Combined with the setup-time detection from prior commits, users WITHOUT gbrain pay zero overhead (block suppressed at gen-time) and users WITH gbrain pay ~275 tokens. The /investigate special-case (data-research routing in CONTEXT_LOAD) stays inline since it's skill-specific. docs/gbrain-write-surfaces.md also serves as the manual-probe reference for humans verifying live persistence + a topology summary covering trust-policy + .gbrain-source reads-only semantics. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| designs | ||
| evals | ||
| images | ||
| ADDING_A_HOST.md | ||
| ON_THE_LOC_CONTROVERSY.md | ||
| OPENCLAW.md | ||
| REMOTE_BROWSER_ACCESS.md | ||
| askuserquestion-split.md | ||
| domain-skills.md | ||
| explanation-diataxis-in-gstack.md | ||
| gbrain-sync-errors.md | ||
| gbrain-sync.md | ||
| gbrain-write-surfaces.md | ||
| howto-document-a-shipped-feature.md | ||
| howto-ios-testing-with-gstack.md | ||
| skills.md | ||
| tutorial-document-generate.md | ||