Plugins

QA de fidelidad de diseño para modelos solo de texto: una herramienta `deepseek_vision` toma prestado un ojo de cualquier ruta de visión compatible con OpenAI, de modo que el modelo pueda juzgar si una implementación coincide con su maqueta — se entrega con el benchmark detrás de ese juicio (cuatro fixtures, 23 defectos inyectados, transcripciones en bruto) y la disciplina de cuestionamiento de la que depende.

Configura contextWindow para modelos registrados en dsh, para que las sesiones largas ya no se juzguen erróneamente como desbordamiento de contexto.

OMK — Observe. Measure. Know. Cambios de conocimiento respaldados por evidencia para aplicaciones de IA.

Mapea el audio del sistema analizado localmente a efectos de conversación reactivos a la música, juicios de juego de ritmo, comentarios de puntuación y combo, y barras de espectro RGB opcionales en DSH Web.

Arnés de memoria de agente de tres niveles: L1 CLAUDE.md siempre activo, índice L2, esqueleto detallado L3 con plantillas, una puerta que bloquea las escrituras en archivos protegidos sin un token de aprobación de un solo uso, registro de eventos sin juicios, destilación semanal y una habilidad de bucle de ejecución TDD.

Ejecuta 3 o 5 candidatos de coding-agent en Git worktrees detached, valida sus patches con comandos del proyecto, clasifica solo candidatos que pasen, y requiere aprobación separada antes de aplicar el ganador.

Plugin de modo de aprendizaje Feynman: bucle enseñar → reexplicar → evaluar → reexplicar de nuevo, renderizado como tarjetas de lección en HTML enriquecido (diagramas mermaid + resaltado de código con shiki).

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.

Un subagente de aprobación independiente juzga cada escalada de sandbox, con un modelo configurable y un registro de auditoría.

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.

Enrutador de modelos de dos niveles para DeepSeek Harness: enrutamiento con LLM-Judge, cadenas de respaldo multimodelo, conmutación por error con retroceso exponencial y orquestación a nivel de tarea (adaptación a DSH de 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.