すべてのプロジェクト

jev-harness

dansya-arsana/jev-harness

Jev (TypeSafe) as the decision layer for Claude Code: permission gate, skill routing, conditional instructions, effort-tiered subagents, context packs. Tested PoC with evals.

Python
スター
2
フォーク
0

掲載理由

権限・スキル・振り分け・文脈選択の限定判断を Jev に任せ、決定的な方針と Claude の作業を分離する Claude Code ハーネス。

関連プロジェクト

  • jev-superpowers

    Systematic software development framework for AI coding agents upgraded with TypeSafe Jev System One typed decisions

    共通トピック: claude-code, coding-agents

  • agent-doc-search

    Point AI coding agents at the right docs in large codebases: local BM25 and a Jev search propose, a Jev check confirms.

    共通トピック: claude-code, coding-agents

  • jev-triage

    Millisecond-class test-failure triage for coding agents: RETRY / FIX_CODE / FIX_ENV, powered by TypeSafe Jev.

    共通トピック: claude-code, coding-agents