Jesse Vincent 40e866580d docs(specs): record eval re-scope — blind adoption did not reproduce, claims narrowed ...

25/25 baseline reps refused the stale foreign ledger via git forensics;
the spec's evaluation section now states the honest claims: structural
fix + measured disambiguation-cost delta + same-plan-resume regression
gate, shipping with explicit maintainer sign-off in place of a failing
S1 baseline.

2026-07-23 17:27:16 -07:00

..

2026-01-22-document-review-system-design.md

docs: add document review system spec and plan

2026-03-06 14:48:42 -08:00

2026-02-19-visual-brainstorming-refactor-design.md

Add visual brainstorming implementation plan and refactor docs

2026-03-06 13:01:31 -08:00

2026-03-11-zero-dep-brainstorm-server-design.md

Add design spec and tests for zero-dep brainstorm server

2026-03-11 13:11:29 -07:00

2026-03-23-codex-app-compatibility-design.md

docs: add cleanup guard test (#5) and sandbox fallback test (#10) to spec

2026-03-25 11:03:53 -07:00

2026-04-06-worktree-rototill-design.md

fix: remove global worktree path fallback (#1476)

2026-06-16 10:09:43 -07:00

2026-05-05-platform-neutral-config-refs-design.md

Phase B: config-file refs + per-platform tool refs + spec

2026-06-16 10:09:43 -07:00

2026-05-05-platform-neutral-prose-design.md

Phase A: agent-neutral prose + CSO → SDO + spec

2026-06-16 10:09:43 -07:00

2026-05-05-platform-neutral-readme-design.md

Phase C: alphabetize README platform listings + spec

2026-06-16 10:09:43 -07:00

2026-05-06-lift-drill-into-evals-design.md

evals: drop drill source marker

2026-06-16 10:09:43 -07:00

2026-06-09-sdd-task-scoped-review-dispatch-design.md

Spec: record iterations 4-5 (variance honesty, structural fixes, final validated ranges)

2026-06-16 10:09:47 -07:00

2026-06-10-positive-instruction-redesign-design.md

Record writing-plans micro-test result: resolved, no change needed

2026-06-16 10:09:47 -07:00

2026-06-10-strict-cost-sdd-design.md

Spec: L2b tested — opus structural win, sonnet transmission+attention gap (E35/E36); bump evals to 9919b27

2026-06-16 10:09:47 -07:00

2026-06-10-visual-companion-auth-hardening-design.md

Document visual companion auth hardening plan

2026-06-16 10:09:45 -07:00

2026-06-11-visual-companion-final-hardening-fixup-design.md

Tighten visual companion hardening spec

2026-06-16 10:09:45 -07:00

2026-07-06-sdd-plan-scoped-workspace.md

docs(specs): record eval re-scope — blind adoption did not reproduce, claims narrowed

2026-07-23 17:27:16 -07:00