kibin/LexAI
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 1 Wiki Activity

Add new agents and skills for enhanced project orchestration and review processes

Browse Source 
- 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.
This commit is contained in:
john kevin asprec
2026-08-08 16:49:07 +08:00
parent 6aee260533
commit 444060c3eb
85 changed files with 2717 additions and 171 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
_to_delete/replaced-20260806-fableflip/docs/GAUNTLET.md Normal file
View File

@@ -0,0 +1,23 @@
# 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`.
>
> Parts mirror `REFERENCE_BAR.md` (2026-08-06). **The bar is not yet concrete and budgets are unset** — both are parked decision-ready in `PROGRESS.md`; no gauntlet starts until they're resolved. Exception: "Replace reliability" can start once the owner approves the site matrix (its bar is behavioral).
## Parts
| Part | Bar (REFERENCE_BAR.md row) | Rounds | Last verdict | Biggest open gap | Budget left | Status |
| --- | --- | --- | --- | --- | --- | --- |
| Floating toolbar + result modal | Floating toolbar + result modal | 0 | — | — | [set] | not started — awaiting bar artifacts |
| Options page | Options page | 0 | — | — | [set] | not started — awaiting bar artifacts |
| Popup + Prompt Builder | Popup + Prompt Builder | 0 | — | — | [set] | not started — awaiting bar artifacts |
| Replace reliability | Replace reliability (behavioral) | 0 | — | — | [set] | not started — awaiting site-matrix approval |
| Store listing | Store listing | 0 | — | — | [set] | not started — blocked by T-01 |
## Round history
- _None yet._
## Final verdicts
- _None yet._