Plugins
Parcourez, filtrez et installez des plugins DeepSeek-Harness.
327 plugins trouvés
dsh-model-tabs
lingtian303/dsh-model-tabs
Adds two-level tabs (provider and model family) to the composer model picker for large catalogs, with configurable family rules.
dsh-session-rules
lw0129a/dsh-session-rules
Workspace- and session-scoped rules for DeepSeek Harness · 按工作区/会话分层维护守则,会话里逐层勾选带入,默认关闭
guster
lumos-789/guster
Audits and evolves agent context at four scopes: a single repository, a group of related repos, a knowledge hub, or the whole machine. Discovers projects, instruction files, skills, tools, knowledge, state, evidence and credential references; reports drift, duplicate facts, broken pointers, budget overruns, unindexed knowledge, stale state and unregistered credentials; scores each scope on its own dimensions; and turns findings into reviewable migration plans that back up every file before moving it. The format contract is a versioned spec (CTX rules, markdownlint-style IDs) following open conventions — the AGENTS.md open format, llms.txt-shaped indexes, YAML front-matter note headers — now backed by published JSON Schema contracts (draft 2020-12) for the hub manifest and the plan JSON, plus an editor modeline that validates hub.yaml with zero configuration. The hub is declarative (schema 2, zones with light profiles, sections may live outside the hub root), a one-pass check command runs scan, doctor and score, and state writes are atomic and lock-protected; scoring stays honest about missing evidence — a waiver greens the gate, never the score. Ships a stdlib-only Python CLI plus two skills; credentials are referenced by path and never printed. Requires Python 3.9+ (stdlib only) and DSH 0.2.1-rc.2 or newer, below 0.3.0.
dsh-claim-gate
xizhilang2012/dsh-claim-gate
A self-justification gate for outbound claims: a claim needs a checkable source (an http(s) URL plus a quote of at least 8 characters), every number in the text must appear in a quote, and a quote whose vocabulary overlap with the post is under 10% counts as an invalid citation; absolute wording is rejected when the only evidence is second-hand. All verdicts come from deterministic rules — no model call, no network. The guard subcommand refuses to run the publish command when the gate fails (fail-closed), explains what is wrong and how to fix it, and requires an --ack note on the second attempt stating what changed; after three attempts it stops and hands back to a human. Ships check / explain / fix / guard, with 30 tests.
dsh-ai-nav
naturalth2012/dsh-ai-nav
Hao123-style AI navigation page: 95 verified entries across 8 categories, a search box matching names, aliases and pinyin initials, per-site in-site search, bookmark HTML import, a favicon proxy that keeps the page free of third-party requests, and an offline rules-based recommender that suggests a complementary tool stack for a stated need.
dsh-obsidian-quote (harness-plugin)
kleinklein0824/dsh-obsidian-quote
Adds a knowledge-base sidebar backed by the separately installed local Obsidian Quote service: select registered vaults or folders, retrieve read-only note excerpts and cited context, extract rules, generate project convention briefs, and view shared citation statistics.
dsh-agent-team-playbook
elfgzp/dsh-agent-team-playbook
Injects the non-obvious operating rules of Agent Teams into the Lead session through one ordered system-prompt section: plan the roster before spawning, roster slots are never released, write scopes are advisory, and wait_agent short-circuits when no peer is running.
dsh-workspace-rules
winson-young/dsh-workspace-rules
A settings page that edits the current project's CLAUDE.local.md, the private per-project instruction file DSH's built-in loader reads at the start of a session; the file stays out of git.
dsh-whale-whispers
heiyedehen/dsh-whale-whispers
Quote books in the conversation header: one markdown file per chat, with search, a random pick, line and favourite counts, a keep button under every reply, and a trash with restore. The agent gets four tools (append, list, remove, merge) and a system-prompt guide, so by default it may save up to a line or two per chat on its own; capture rules can be set per chat or globally. Local-only. Needs DSH 0.2.1+ (below 0.3).
dsh-optimization-2027
shiliuyu316/dsh-optimization-2027
Five-tier reasoning protocol injected into the system prompt — off / light / standard / deep / multi-agent, 0 / 3 / 9 / 17 / 19 rules — with the tokens each tier adds per request shown beside it. Alongside it: a claim ledger that marks a load-bearing claim with no evidence or check as unsupported, read-only analyst briefs, JSON-declared custom tools that work in the same turn, one persistent PowerShell session, and re-injection of host context after a configurable message gap. Tier 0 injects nothing and mounts no tools. A derivative of husongan/dsh-deepseek-2027 (MIT); do not install both — each injects its own reasoning-protocol section into the system prompt.
dsh-prompt-balance
penghao73551/dsh-prompt-balance
Measures what your assembled system prompt is actually made of - rules, identity, workspace policy, tool descriptions - in bytes and percentages, then moves the operating protocol ahead of the rule block so the model reads who it works for before it reads the prohibitions. Config-driven via ~/.dsh/prompt-balance.json; two hooks, no build step, no dependencies.
dsh-better-sandbox
rkfg/dsh-better-sandbox
Sandbox rules for DeepSeek Harness: extra writable roots, write-protected path names with a narrow escalation level for them, read-protected paths.
dsh-her
aicivilization/dsh-her
A desktop companion for DSH: she lives on your real desktop, in the wallpaper or in dsh's own page, talks by voice, speaks first and remembers you. Several characters, each with her own look and scene rules.
dsh-auto-approval-frame
flyhai/dsh-auto-approval-frame
Automatic approval and audit frame for DSH tool calls: a four-outcome rule table (deny, ask, AI review, allow) over commands, file access, network and tool scope, with security rules, rule-based auto-approve/auto-deny, AI fast/deep review, human approval, permission tiers, workspace boundaries, secret redaction and placeholder restore, a hash-chained audit trail and a simulator. Target files are inspected by metadata only.
doran-design
doran1110/doran-design
Registers a web-design skill and a compact system-prompt rule set for a three-layer shadcn/ui, Canvas UI and ThreeUI workflow, with Radix UI Colors and strict interface rules.
dsh-pitfall-memory
baizhu66018/dsh-pitfall-memory
Failure memory for DeepSeek Harness. Captures tool failures as they happen, classifies them with 16 built-in rules into lessons pairing a symptom with a fix, adds session/daily/weekly summaries, and injects a short briefing into later sessions through systemPrompt context. Ships 5 pitfall_ tools and a web settings page.
dsh-recollect
kirkchinese/dsh-recollect
Mémoire compatible avec Claude Code pour tous les modèles DeepSeek Harness : instructions CLAUDE.md/AGENTS.md en couches avec @import et règles, MEMORY.md persistante avec guide complet de rédaction, actualisation à la reprise et à la compaction, rappel facultatif.
dsh-remote-server-manager
cnhuashao/dsh-remote-server-manager
Gestionnaire de serveurs Linux distants dans l'interface Web Harness : parcourir et modifier les fichiers, examiner l'état de l'hôte, démarrer/arrêter/redémarrer des conteneurs Docker, consulter les images, configurer des miroirs de registre Docker, gérer les règles firewalld/ufw, changer de sources apt et détecter des outils développeur ou les installer/mettre à niveau avec apt.
dsh-flowforge
r-roker315/dsh-flowforge
Créateur DIY de flux de travail DSH : composez des chaînes de prompts multi-étapes avec validation autonome, règles de saut imposées par le moteur, exécution pilotée par agent et panneau de suivi en direct.
dsh-tools-manager
1497105876/dsh-tools-manager
Liste de blocage d’outils deny-only par préréglage d’agent. Désactiver un outil dans Paramètres le retire du schéma de ce mode et rejette ses appels. Rien ne peut être activé ni ajouté à une liste d’autorisation ; les outils non bloqués restent intacts. Chaque ligne détaille son outil et les règles résident dans un fichier JSON unique hors du profil.
dsh-rules
xulei666a/dsh-rules
Couche unifiée de règles et consignes pour DeepSeek Harness. Centralise les consignes de chaque agent dans une bibliothèque locale, distingue default (toujours actif) de local (domaine de tâche) et synchronise l’ensemble effectif dans la section gérée de AGENTS.md. Ajoute routage sémantique, arbre de classification et page de gestion/panneau latéral droit. L’assistant du panneau peut réunir les consignes existantes, calibrer et reclasser les règles en attente, puis signaler un registre de problèmes par responsable. Pour les copies : clic droit pour déplacer/copier, copie de dossier et accès à l’origine. Suit aussi les points de décision avec conflits de branches et le choix de branche par session.
dsh-mnemos-continuity
xthingillu-sketch/dsh-mnemos-continuity
Continuité entre modèles pour DeepSeek Harness : mémoire, skills et règles résident dans des fichiers locaux afin que le jugement survive aux changements de session et de modèle. Il ne s’agit pas de stocker davantage, mais de bien utiliser la mémoire après le changement.
dsh-security-judge
youchen-yc/dsh-security-judge
Outil de jugement pour la revue défensive de sécurité du code dans DeepSeek Harness : détecte les sessions qui écrivent du code, les examine selon Code Security Defense Architecture Rules, recommande une ou plusieurs architectures nécessaires, vérifie leurs conflits et apprend à l’IA de session après des échecs répétés. Si vous lui accordez l’autorité de revue dans le panneau, il bloque la fin de tâche jusqu’à validation ; sans cette autorisation, il observe uniquement.
dsh-mnemo
cwqxxx/dsh-mnemo
Mémoire à long terme intersessions pour DeepSeek Harness : injecte les règles épinglées à chaque tour et rappelle le reste selon des mots-clés pondérés par IDF. Déduplication par fact-key, stockage JSON simple et édition/suppression des entrées dans les paramètres.