444060c3eb
- Introduced `critic`, an independent adversarial reviewer for security and correctness. - Added `fable-orchestrator` to manage task routing and verification. - Implemented `gauntlet-critic` for fresh-context evaluation of gauntlet rounds. - Created `planner` for generating executable implementation plans with dependencies. - Developed `security-auditor` for application security reviews and audits. - Established `system-steward` to improve agent prompts and skills based on verified failures. - Added `dev-loop` skill for autonomous development loops over repositories. - Implemented `gauntlet-loop` skill for iterative quality benchmarking against reference standards. - Updated project settings to utilize the new orchestrator agent. - Created documentation for `GAUNTLET.md`, `PROGRESS.md`, and `REFERENCE_BAR.md` to track project status and quality benchmarks. - Added detailed prompting style guide to enhance understanding of prompt patterns and agentic loops.
1.2 KiB
1.2 KiB
Gauntlet board
Loop state for reference-benchmarked work. One row per part; one line per round. Move finished gauntlets to
docs/archive/. Statuses:not started·looping·parity — stopped·diminishing returns — stopped·budget exhausted·parked (decision-ready)·integrated.Seeded 2026-08-06 at the tier upgrade with the screens that already have design artifacts. Budgets are unset — owner sets them before a part's first round. Add rows as new screens reach implementation; the bar precedence guard in
REFERENCE_BAR.mdapplies to every round.
Parts
| Part | Bar (REFERENCE_BAR.md row) | Rounds | Last verdict | Biggest open gap | Budget left | Status |
|---|---|---|---|---|---|---|
| Auth screens 1–2 | Auth screens 1–2 | 0 | — | — | [set] | not started |
| Screen 06 — discount capture | Screen 06 — discount capture | 0 | — | — | [set] | not started |
| Screen 11 — printer setup | Screen 11 — printer setup | 0 | — | — | [set] | not started |
| P10 — prepaid booking / QR | P10 — prepaid booking / QR | 0 | — | — | [set] | not started |
Round history
- None yet.
Final verdicts
- None yet.