Plugins

Frische-Gate für die Test-, Typecheck-, Lint- und Build-Behauptungen des Agenten: Jeder Verifikationslauf wird zu einem Beleg in tools/post-execute, Dateibearbeitungen werden verfolgt, und bei agent/turn-stopping treibt eine Behauptung, deren jüngster Beleg veraltet, fehlgeschlagen oder unlesbar ist, einen weiteren Schritt an, der den Beleg und die seither bearbeiteten Dateien benennt.

Setzt einen Agenten-Turn fort, der endete, nachdem er seine nächste Aktion geschildert, aber kein Tool aufgerufen hatte: der Wächter spielt das Turn-Log bei agent/turn-stopping erneut ab, stellt einem Richter-Modell eine Wahr/Falsch-Frage und steuert denselben Turn zu einem weiteren Schritt.

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.

Führt Jev-(TypeSafe-System-One-)Bewertungen an den Agent-Loop-Gates von DeepSeek Harness aus: pre-step, pre-execute, post-execute und Turn-Stopp. Keine UI-Abhängigkeiten; in jede Harness-Komposition integrierbar.

Fängt das Ende eines Turns ab und erzwingt nach jedem abgeschlossenen Turn eine Runde aus Kritik und Verbesserung, bevor der Agent stoppt.