General-purpose coding policy for Baruch's AI agents
93
97%
Does it follow best practices?
Impact
93%
1.82xAverage score across 18 eval scenarios
Advisory
Suggest reviewing before use
go vet for Go, and the likeLSP tool here), so the agent reads diagnostics on the files it touches and clears them before handing work off# type: ignore, # pyright: basic, // @ts-nocheck, //nolint:all switch the engine off for a whole file and mask the same signal it exists to catchtsc --noEmit, clippy, go vet — as a gate at zero findingsrules/code-formatting.md CI Integration)rules/script-delegation.md)executionEnvironments with per-root extraPaths for Python path-insert bundles; tsc baseUrl/paths/project references for TS workspacesraise/throw, Optional/nullable misuse.tessl-plugin
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10
scenario-11
scenario-12
scenario-13
scenario-14
scenario-15
scenario-16
scenario-17
scenario-18
rules
skills
adopt-fork-pr
eval-curation
install-reviewer
migrate-to-plugin