gstack/browse
Stefan Andrei 47f3935841 Add /autobuilder-loop skill
Plan-driven build loop: resolves an approved plan, freezes the milestone set, and
drives it to completion with model-routed subagents. Every milestone must pass a
mandatory gate — /plan-eng-review + /review + an adversarial cross-model forum
(Codex gpt-5.6-sol at ultra effort, Grok grok-build) — plus local Docker
verification before it counts as done. A [P1] from either external model fails the
gate; if both are unavailable the gate degrades to a single Claude adversarial
subagent rather than silently passing.

Includes the gen-skill-docs and test-suite fixes the skill depends on to generate
and validate.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-15 15:45:03 +03:00
..
bin feat: multi-agent support — gstack works on Codex, Gemini CLI, and Cursor (v0.9.0) (#226) 2026-03-19 18:20:50 -07:00
scripts fix: ngrok Windows build + close CI error-swallowing gap (v0.18.0.1) (#1024) 2026-04-16 13:49:04 -07:00
src v1.58.3.0 feat: gbrowser anti-detection Layer C stealth (#2047) 2026-06-18 10:45:05 -07:00
test Add /autobuilder-loop skill 2026-07-15 15:45:03 +03:00
PLAN-snapshot-dropdown-interactive.md fix: snapshot -i auto-detects dropdown/popover interactive elements (#845) 2026-04-05 22:57:45 -07:00
SKILL.md v1.58.5.0 feat: first-run activation scaffold + gstack router front door (#2078) 2026-06-25 09:42:45 -07:00
SKILL.md.tmpl v1.57.8.0 feat: browse js/eval --out render-to-file (canonical Chromium for offline rendering) (#1929) 2026-06-09 21:02:30 -07:00