neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
Claude Code 插件市場。審計:基於清單的審計/修復管線,強制先行規劃與 TDD 閘門——確定性掛鉤,而非提示建議——代幣支出歸屬於各階段。
AI 翻譯
Claude Code plugin marketplace. audit: a manifest-driven audit/fix pipeline with enforced plan-first and TDD gates — deterministic hooks, not prompt suggestions — token spend attributed to phases and
開發工具Python · JavaScriptGitHub @AleksandarBisevac上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
Claude 程式碼插件市場。審計:基於清單的審計/修復流水線,強制先行計畫與 TDD 閘門——確定性掛鉤,而非提示建議——代幣消耗歸屬於階段與任務,並提供可分享的 HTML 報告。零相依性。
AI 翻譯
Claude Code plugin marketplace. audit: a manifest-driven audit/fix pipeline with enforced plan-first and TDD gates — deterministic hooks, not prompt suggestions — token spend attributed to phases and tasks, and a shareable HTML report. Zero dependencies.
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
A Claude Code plugin marketplace with one theme:
enforced engineering discipline — plan gates, test gates, sign-off gates,
secret guards. The guards are deterministic hooks; the pipeline they govern is an
orchestrator prompt — which is which, row by row.
A coding agent already reads your code, drafts a plan and edits files across a
session — this is what a plan file and a hook add on top of that:檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
A Claude Code plugin marketplace with one theme:
enforced engineering discipline — plan gates, test gates, sign-off gates,
secret guards. The guards are deterministic hooks; the pipeline they govern is an
orchestrator prompt — which is which, row by row.
A coding agent already reads your code, drafts a plan and edits files across a
session — this is what a plan file and a hook add on top of that:檢視完整 README ↗