プラグイン

エージェントのテスト・型チェック・lint・ビルド主張の鮮度ゲート：検証実行が tools/post-execute でレシートになり、ファイル編集を追跡。agent/turn-stopping 時に最新レシートが古い/失敗/判読不能な主張は、レシートと編集済みファイルを名指ししてもう 1 ステップ促す。

次の行動を語っただけでツールを呼ばずに終わったエージェントターンを再開します：ガードが agent/turn-stopping でターンログを再生し、判定モデルに真偽の質問を 1 つ投げ、同じターンをもう 1 ステップ実行するよう誘導します。

Blocks the end of a turn while temporary files from that turn are still lying around: it registers a listener on the serial agent/turn-stopping hook and, if anything is left, steers the model with the file list and two ways out — delete them, or justify each one and move it somewhere deliberate. Candidates come from two narrow temp-file sources, plus a backup-retention channel that is on by default and flags excess .bak copies of files touched this turn. The first is the .agent-tmp/ convention directory under the session cwd: whatever is left in it is reported outright, because that directory exists only for throwaway files. The second is the paths this turn actually wrote, captured through the fs/write-intent hook; those are reported only when they sit under that cwd, fall outside .git, node_modules, .tmp-sessions and out, match a temp-file pattern, and the file is still present — which is what keeps junk already sitting in the workspace from being resurrected as a complaint about this turn. One steer per turn, subagent sessions skipped, nothing deleted by the plugin in the default steer mode (only the opt-in mode: prune deletes backups), and the check is readdir plus stat only.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

DeepSeek Harness の agent-loop ゲート（pre-step、pre-execute、post-execute、ターン停止時）で Jev（TypeSafe System One）の判定を実行します。UI 依存はなく、任意の Harness 構成に組み込めます。

ターン終了をインターセプトし、エージェントが停止する前に、完了した各ターンについて批評と改善を1回行わせます。