Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
29 plugins trouvés
dsh-design-qa
sunxin-ai/dsh-design-qa
QA de fidélité de conception pour les modèles texte uniquement : un outil `deepseek_vision` emprunte un œil à n’importe quelle route vision compatible OpenAI, afin que le modèle puisse juger si une implémentation correspond à sa maquette — livré avec le benchmark derrière ce jugement (quatre fixtures, 23 défauts injectés, transcriptions brutes) et la discipline de questionnement dont il dépend.
dsh-model-context-catalog
howillmakeit/dsh-model-context-catalog
Configurez contextWindow pour les modèles enregistrés dans dsh, afin que les longues sessions ne soient plus considérées à tort comme un débordement de contexte.
oh-my-knowledge
lizhiyao/oh-my-knowledge
OMK — Observer. Mesurer. Savoir. Modifications de connaissances étayées par des preuves pour les applications IA.
dsh-bgm
skymecode/dsh-bgm
Associe l'audio système analysé localement à des effets de conversation réactifs à la musique, des jugements de jeu de rythme, un retour de score et de combo, et des barres de spectre RGB optionnelles dans DSH Web.
l123-harness
reatcat/l123-harness
Harnais de mémoire d’agent à trois niveaux : CLAUDE.md L1 toujours actif, index L2, squelette détaillé L3 avec modèles, une passerelle qui bloque les écritures dans les fichiers protégés sans jeton d’approbation à usage unique, journalisation d’événements sans jugement, distillation hebdomadaire et une compétence de boucle d’exécution TDD.
dsh-llm-verifier
web0926/dsh-llm-verifier
Lance 3 ou 5 candidats coding-agent dans des Git worktrees détachés, valide leurs patches via les commandes du projet, ne classe que les candidats réussis et exige une approbation séparée avant d'appliquer le gagnant.
dsh-learn-everything
cendaifeng/dsh-learn-everything
Plugin de mode d'apprentissage Feynman : boucle enseigner → reformuler → évaluer → réexpliquer, rendue en fiches de cours HTML riches (diagrammes mermaid + coloration syntaxique shiki).
dsh-loop-continue
yunxiyang/dsh-loop-continue
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.
dsh-agent-approval
moonlitdropofblood/dsh-agent-approval
Un sous-agent d'approbation indépendant juge chaque escalade de sandbox, avec un modèle configurable et un journal d'audit.
dsh-auto-approve
dnalec/dsh-auto-approve
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.
dsh-peakrate
log-li/dsh-peakrate
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.
dsh-write-gate
couldbeme/dsh-write-gate
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.
dsh-habit
max-null/dsh-habit
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
dsh-codex-approval
040822/dsh-codex-approval
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.
dsh-auto-classifier
pakiknowledge/dsh-auto-classifier
Autonomous permission classifier for the auto preset: tool-scoped allow/deny rules, an LLM semantic judge, and git checkpointing for unattended sessions.
safety-net
johnxu22786/safety-net
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.
dsh-shift-router
green-dalii/dsh-shift-router
Routeur de modèles à deux niveaux pour DeepSeek Harness — routage par LLM-Judge, chaînes de repli multi-modèles, bascule avec backoff exponentiel, et orchestration au niveau tâche (adaptation DSH de pi-shift-router).
dsh-experience-recall
overdustd7/dsh-experience-recall
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.
dsh-grill-tree
qiz029/dsh-grill-tree
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
dsh-plugin-cvescout
whisper-cao/dsh-plugin-cvescout
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.
dsh-resume-screening
wangzhanchao883/dsh-resume-screening
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.
dsh-plugin-kit
perrylink/dsh-plugin-kit
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.
dsh-multi-role-debate (dsh-multi-role-debate)
jiang12345-code/dsh-multi-role-debate
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.
dsh-humanizer
liuwenji007/dsh-humanizer
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.