Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
218 plugins trouvés
dsh-doc-guard
lucky8197/dsh-doc-guard
Garde de cohérence documentation-code : audite les en-têtes de version, tableaux de changelog, arborescences, nombres de modules et de tests et références croisées entre documents pour détecter les dérives, avec des suggestions de correction en lecture seule triées par sévérité.
dsh-startup-guard
aokamoaki/dsh-startup-guard
Garde au démarrage : répare les journaux de session corrompus, pré-inspecte la composition des plugins, vérifie par vm les artefacts clients, teste en fumée le apply() de l'hôte et met en quarantaine les bundles qui provoquent des plantages, pour qu'un plugin cassé ne puisse jamais empêcher le démarrage.
agent-loop-workflow
lesliewylie/agent-loop-workflow
Protocole de collaboration multi-agents indépendant du projet pour DeepSeek Harness : gardes de boucle qui arrêtent les boucles d'agents emballées, format de passation à six champs, routage des revues par niveau de risque et séquence fixe verify→commit→push→review→close. Une seule skill au lieu des mêmes règles copiées dans les instructions de chaque agent.
dsh-mojibake-interceptor
fire-disposal/dsh-mojibake-interceptor
Paquet de garde contre le mojibake pour DSH : détection de texte corrompu par caractéristiques avant écriture avec revue puis libération (une nouvelle tentative identique passe), plus audit d'encodage pwsh avant exécution (ANSI/GBK/UTF-16/Default). Windows et chinois d'abord.
dsh-projection-guard
damonkoy/dsh-projection-guard
Protège le cache persistant de projection de session : dégradation JSON ligne par ligne pour qu'une unité de projection défaillante (par ex. un plugin tiers stockant une Map) ne puisse plus jamais bloquer les titres de session ni tout le cache, plus une auto-réparation au démarrage qui rattrape les titres manquants.
dsh-git-guard
bibibala/dsh-git-guard
Plugin de protection d'écriture conscient de Git pour DeepSeek Harness : bloque les écritures de fichier entier qui écraseraient les modifications non commitées de l'utilisateur, et rapporte en fin de tour ce qui est arrivé aux fichiers protégés.
dsh-guardian
lonelymoon87/dsh-guardian
Ajoute des vérifications de politique pour les opérations dangereuses, une rédaction de sortie et un workflow de revue de sécurité.
dsh-mcpguard
chenlaoshiyf/dsh-mcpguard
Analyse les skills et les configurations MCP à la recherche d'injections de prompt, d'homoglyphes, d'Unicode caché, de commandes shell dangereuses et de fuites d'identifiants.
dsh-docker
jesse-njx/dsh-docker
Contrôle de conteneurs typé et protégé : ps/logs/inspect/exec/start/stop et compose up/down avec sortie JSON, ciblage conscient du projet, et opérations destructrices soumises à approbation.
chinese-script-policy
ksf1216/chinese-script-policy
Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.
dsh-decision-layer
xbzbing/dsh-decision-layer
A structured decision layer for the DeepSeek Harness agent loop: a danger-call gate, output self-check, tool narrowing, and loop guard backed by a pluggable adjudication model.
dsh-lan-guard
idoall/dsh-lan-guard
LAN access for the official DSH Web UI through a gated reverse proxy: DSH keeps its own loopback binding, and a second port adds a password gate, self-signed HTTPS and per-device pairing that can be revoked individually, with a QR code to open it from a phone.
dsh-cache-guard
loonylabs-dev/dsh-cache-guard
Host- and agent-layer DeepSeek Harness plugin that prices every automatic context rewrite before it lands, asks the human by default, and reports what the provider had to re-read cold.
dsh-github-ops
goodandready/dsh-github-ops
GitHub operations for DeepSeek Harness: releases, tags, a guarded generic API pass-through, workflow runs, secrets and sanitized mirror publication.
dsh-jev-guard
7starsseeker/dsh-jev-guard
Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.
dsh-theme-studio
hj01857655/dsh-theme-studio
Customize the dsh UI theme: 12 accent presets, dark-mode aware accents with a contrast guard, density, font family, animation toggle, and raw design-token overrides.
dsh-tm-guard
chaojie0/dsh-tm-guard
Zero-intervention permission gate for DSH agents on macOS: auto-allows local writes made reversible by git or Time Machine, blocks network, package installs, process control and sensitive-path reads, with full audit logs.
deskpet-guard
cny1230/deskpet-guard
Agent 行为守护桌宠:跨 agent 监控可疑外传(加密打包直传对象存储 / DNS 外泄线索 / 敏感密钥被读),发现即告警,明确确认后按「一次一个」终止目标 agent;事件写入只追加 guard-events.jsonl,并通过 DSH host 工具 + MCP(stdio) 供其它 agent 查询
dsh-consistency-guard
bycall/dsh-consistency-guard
Consistency guard for long-form writing: scans conversation prose for character, timeline and numeric setting conflicts across chapters, then jumps straight to the conflicting message.
dsh-auto-archive
wzn16/dsh-auto-archive
Auto-archives sessions idle beyond a configurable threshold, with safety guards (never touches live or running sessions), plus a full archived-session management UI: list, unarchive, safe delete and content preview.
dsh-sandbox-arg-guard
apex-mochen/dsh-sandbox-arg-guard
Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.
dsh-privacy-guard
amwangfan/dsh-privacy-guard
Control panel for a local credential-redaction gateway in DeepSeek Harness: gateway and model health, audit metrics, a dry-run leak tester, an exemption whitelist, encrypted key management, credential-protected model entries and deployment controls.
dsh-community-fixes
robin1987china/dsh-community-fixes
One install for the community's verified DeepSeek Harness fixes: a bundle that mounts every guard and patch in a single profile line, plus a read-only projection-cache footprint report.
dsh-composer-focus-guard
xht-code/dsh-composer-focus-guard
DSH 插件:移动端切换会话时抑制 composer 的自动聚焦,避免软键盘被顶起