mirror of https://github.com/garrytan/gstack.git
672b093ea2
Worked example: manually walked /plan-rollout against garrytan/gstack#1241 (fix(ask-user): keep question payloads compact) — 41 files, +661 / -282, regeneration-heavy. Verdict the skill should emit: "one PR." 39 of 41 files are deterministic regenerations of one source change in scripts/resolvers/preamble/generate-ask-user-format.ts; slicing them off would leave dependent fragments. Reader time: ~21 min (under cap). Findings (v1.1 todos) surfaced by the dogfood: 1. Deterministic-regeneration detector — merge build-output slices into their source slice automatically. 2. Regen-multiplier on reader-time so skim-only output isn't over-counted. 3. --explain mode — when verdict is "one PR," print the rejected slicing alternatives and the signals that rejected them. 4. Calibration loop — predicted vs actual reader-time on first ~10 real invocations to ground v2 heuristics in data. SYSTEM.md is explicitly called out as the WRONG primitive for catching build-output coupling — that needs a Makefile-style dependency, not a contract graph. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| BROWSER_SKILLS_V1.md | ||
| BUN_NATIVE_INFERENCE.md | ||
| CHROME_VS_CHROMIUM_EXPLORATION.md | ||
| CONDUCTOR_CHROME_SIDEBAR_INTEGRATION.md | ||
| CONDUCTOR_SESSION_API.md | ||
| DESIGN_SHOTGUN.md | ||
| DESIGN_TOOLS_V1.md | ||
| GCOMPACTION.md | ||
| GSTACK_BROWSER_V0.md | ||
| ML_PROMPT_INJECTION_KILLER.md | ||
| PACING_UPDATES_V0.md | ||
| PLAN_ROLLOUT_DOGFOOD.md | ||
| PLAN_TUNING_V0.md | ||
| PLAN_TUNING_V1.md | ||
| SELF_LEARNING_V0.md | ||
| SESSION_INTELLIGENCE.md | ||
| SIDEBAR_MESSAGE_FLOW.md | ||
| SLATE_HOST.md | ||
| SLOP_SCAN_FOR_REVIEW_SHIP.md | ||