- Section carve optimization to eleven additional skills, expanding carved roster from 9 to 20 skills total
- SKILL_START_PROTO handshake emitted by runtime scripts with per-run session ID and random suffix
- Reduce prompt cost for every skill invocation by approximately half while maintaining identical behavior as verified by A/B evaluations
- Move shared preamble bash into two runtime scripts bin/gstack-skill-start and bin/gstack-skill-end that emit STATUS lines
- Emit one-time onboarding text only when its gate fires, as session-bound GSTACK_INSTRUCTION blocks instead of in every render
- Deepen office-hours skill carve to load heavy reference bodies on demand at the step that needs them instead of preloading
From gstack
Every skill invocation just got half the prompt bill. Same behavior, measured by A/B evals, locked by CI ceilings. Every gstack skill pays a fixed prompt cost before doing any work. This release cuts that cost across all 62 skills and pins the wins so they can't creep back. The shared preamble's bash moved into two runtime scripts (bin/gstack-skill-start, bin/gstack-skill-end) that echo the same STATUS lines the prose always interpreted. One-time onboarding text now appears only when its gate actually fires, emitted as session-bound instruction blocks instead of riding along in every render. Eleven more skills got the section carve and office-hours' existing carve went deeper, taking the carved roster from 9 to 20: heavy reference bodies load on demand at the step that needs them, never before. bin/gstack-skill-start / bin/gstack-skill-end: the preamble and telemetry runtime, replacing ~18KB of inline bash per tier-2+ skill. Emits a SKILL_START_PROTO: 1 handshake, STATUS lines, and gated one-time onboarding as GSTACK_INSTRUCTION blocks bound to a per-run session ID with a random suffix.