Plugins

Design-Treue-QA für textbasierte Modelle: Ein `deepseek_vision`-Tool leiht sich ein Auge von jedem OpenAI-kompatiblen Vision-Pfad, damit das Modell beurteilen kann, ob eine Implementierung zu seinem Mock passt — ausgeliefert mit dem Benchmark hinter diesem Urteil (vier Fixtures, 23 injizierte Defekte, Rohtranskripte) und der Fragedisziplin, von der es abhängt.

Konfiguriert contextWindow für in dsh registrierte Modelle, damit lange Sitzungen nicht länger fälschlich als Kontextüberlauf eingestuft werden.

OMK — Observe. Measure. Know. Evidenzgestützte Wissensänderungen für KI-Anwendungen.

Ordnet lokal analysiertes System-Audio musikreaktiven Konversationseffekten, Rhythmusspiel-Bewertungen, Punkte- und Combo-Feedback sowie optionalen RGB-Spektrumbalken in DSH Web zu.

Dreistufiges Agenten-Gedächtnis-Harness: immer aktives L1 CLAUDE.md, L2-Index, L3-Detail-Skelett mit Vorlagen, ein Gate, das Schreibzugriffe auf geschützte Dateien ohne einmaliges Freigabe-Token blockiert, urteilsfreies Event-Logging, wöchentliche Destillation und eine TDD-Execution-Loop-Skill.

Startet 3 oder 5 Coding-Agent-Kandidaten in entkoppelten Git-Worktrees, validiert deren Patches mit Projektkommandos, rankt nur passende Kandidaten und verlangt eine separate Freigabe, bevor der Gewinner angewendet wird.

Feynman-Lernmodus-Plugin: Der Zyklus Lehren → Zurücklehren → Bewerten → Neu erklären wird als reichhaltige HTML-Lektionskarten dargestellt (Mermaid-Diagramme + Shiki-Code-Highlighting).

Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.

Ein unabhängiges Genehmigungs-Subagent urteilt über jede Sandbox-Eskalation, mit konfigurierbarem Modell und Audit-Log.

Automatic approval and review for tool calls that need approval: keyword buckets match red lines without context, then a judge model classifies what was requested and sends it to allow, reject or a human according to the matching row and risk level; a judgment that never ran always goes to a human, and rejections tell the model why.

Peak / off-peak rate badges for the model selector (every row) and the composer tool row, judged per provider by its own time zone and schedule; the live catalog is served from the host over a fenced route.

Commitment write-gate: operator-authored rules enforced before a tool call runs — a deterministic guard tier plus an LLM-judge tier, fail-closed by default, every block written to a contradictions log.

Self-learning habit engine for the DeepSeek Harness — detects user-correction signals, judges habits with a low-cost model on threshold, settles candidates behind a two-level human gate

Codex-style approval autopilot for DeepSeek Harness: ordered glob rules (allow/ask/deny) plus an AI risk judge (low/medium/high) mapped through a risk tolerance, as an approval answerer.

Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.

Destructive-command interception gate for dsh: parses shell semantics, judges risk against 41 built-in rules, and holds irreversible rm -rf, git reset --hard, and git push --force style commands at a confirmation gate.

Zweistufiger Modell-Router für DeepSeek Harness — LLM-Judge-Routing, Multi-Modell-Fallback-Ketten, Failover mit exponentiellem Backoff und Orchestrierung auf Aufgabenebene (DSH-Anpassung von pi-shift-router)

Cross-project experience recall for DeepSeek Harness: when the running work matches something your memory store already learned elsewhere, that lesson is injected before the next step. Runs fully locally, judged by a local small model.

DeepSeek Harness plugin bundle: grill_tree, a fixed-policy design-space search tool. Expands one decision per node, fans out independent proposers, has a separate judge prune the branches, beam-limits each depth, and ends with complete designs or an infea

DeepSeek Harness plugin for CVE impact retesting: fingerprint a target, judge it against a CVE's affected range, gather passive evidence, and report a verdict with confidence and limitations.

Resume screening plugin for HR in DeepSeek Harness: ingest up to 100k Word/PDF/Excel resumes into one searchable library with skills / coarse categories / ingest time, auto-ingest & de-dupe new resumes, then screen by plain-language criteria — rule pre-filter in the database plus LLM fine-judge on the shortlisted few, CSV export.

Shared toolkit for authoring DeepSeek Harness plugins, published as @perrylink/dsh-plugin-kit: a pluggable provider registry seam, fail-closed approval and session-event gates, shared sanitize/pricing/judge modules and a new-plugin skeleton.

Multi-role parallel argumentation for DeepSeek Harness: runs the real Codex and Claude CLIs in parallel, has the DSH model (Judge) write a third-party verdict back into the conversation, plus Obsidian-style single-agent direct chat and per-role model config.

DeepSeek Harness 插件：生成前注入「人味」风格约束 + AI 味检测报告（纯代码、零 token、结果可复现）。dsh plugin: human-flavor style injection + AI-flavor detection report, judged by code.