Passer au contenu principal

Plugins

Parcourez, filtrez et installez des plugins DeepSeek-Harness.

146 plugins trouvés

C

dsh-trading-workbench

clusm/dsh-trading-workbench

Trading workbench for DeepSeek Harness: an AI decision chain with a per-day round archive, Demo execution and risk views, backed by a local Python trading service that bootstraps itself on first run. GitHub v0.1.1+ checks every HTTP route through DSH request admission; npm 0.1.0 does not include this fix.

0il y a 4 joursOutils et capacités
S

dsh-experience-optimizer (plugin-trim)

starlit-sky-code/dsh-experience-optimizer

Plugin diet and compatibility diagnostics for DeepSeek Harness: scans context cost and plugin/runtime/profile conflicts, then applies low-risk reversible trims only after confirmation; ships a Web settings console.

0il y a 14 heuresDéveloppement et outils de pluginsAGPL-3.0
G

dsh-plugins (tool-policy)

genesi599/dsh-plugins

Blocks risky tool-call shapes before execution: inline multi-line Python, forwarded content without a source, missing source labels, and memory writes past the character cap. It also asks for confirmation before shell commands, and one rule is specific to the author's WeChat sending workflow.

0il y a 7 joursSécurité et permissions
Y

dsh-agy

yhan-sun/dsh-agy

Brings Google Antigravity (agy CLI) models into DSH with streaming, thinking and native tool cards, a manual multi-account pool with quota and proxy controls, and an optional experimental direct transport. Community fork of amlyczz/dsh-agy-link. Google's Antigravity FAQ says personal plans do not support wrapping agy in third-party coding agents, so using it may put your Google account at risk of restriction. Needs Node.js 24 or newer and Google's agy CLI on PATH; the experimental direct mode is off by default.

0il y a 6 joursModèles et fournisseursMIT
Z

dsh-approval-why

zhknb/dsh-approval-why

Adds a “why does this need escalation?” button to every DSH approval card: it opens a panel with the permission requested, the risk, what refusing means, the exact tool arguments and whether the named paths fall outside the session workspace; the card also keeps a one-line risk and refusal consequence visible under it, and the model’s original reason is split into labelled paragraphs instead of a run-on block.

0il y a 12 joursSécurité et permissionsMIT
W

dsh-slowmist-security-guard

wjl906/dsh-slowmist-security-guard

Security guard for DeepSeek Harness (Cordis): reviews every tool call in pre-execute against SlowMist agent-security rules, denying or flagging risky commands, MCP servers and skill loads, external URLs and repositories, untrusted documents, and EVM or Solana addresses; scans tool results for prompt injection after execution and ships a slowmist_scan audit tool plus an injected security policy prompt. Rules follow the open-source SlowMist Agent Security Skill (MIT).

0il y a 12 joursSécurité et permissions
N

dsh-server-connector

niechao136/dsh-server-connector

DSH plugin: SSH execution for servers configured on this machine, with a built-in high-risk command policy (block / confirm / allow).

0il y a 13 joursOutils et capacitésMIT
D

dsh-ps-preflight

dingchenhui0618-arch/dsh-ps-preflight

Grades every PowerShell command an agent is about to run before it runs: deletion, overwrite, network download and credential access are four required classes, plus dynamic execution, system and privilege changes. Verdicts are a pure deterministic rule function — no model call, no network, sub-millisecond — with two escalation rules (download+execute, credential+exfiltrate) that jump straight to high. High risk stops the tool call for a second confirmation (in-panel queue or the native approval), deny or timeout means it never runs; medium is logged but never blocked. Every command and its verdict, including the redacted command text, is appended to a local JSONL audit log. Quoted danger strings are treated as data, -WhatIf is respected, -EncodedCommand is decoded and analysed again. Host + client halves, zero runtime dependencies, 55 rules, 136 tests.

0il y a 23 joursSécurité et permissionsMIT
L

dsh-astock

laynepeng/dsh-astock

A-share assistant: 19 tools for quotes, K-line, screening, sentiment and backtests, plus a manual trade ledger, a sidebar panel, daily archive snapshots and risk-alert email. No broker connection or order placement.

0il y a 12 joursOutils et capacitésApache-2.0
H

quantitativeTrading-source-reliable

hanwang-ai/quantitativetrading-source-reliable

Registry of 119 quant and crypto sources covering regulator filings, point-in-time fundamentals, macro series, exchange APIs and on-chain data, each tagged with an authority tier, verification state, five-state point-in-time, revision risk and dataset tags; ships qt_source_find and qt_source_audit tools for source lookup and for citation audits that redact credential-like URL parameters.

0il y a 16 joursOutils et capacitésMIT
M

dsh-deepseekbase

moldkey/dsh-deepseekbase

Brings the third-party deepseekbase.com index into DSH: eight tools and five DSHIO standard skills (from the @liangjiehappy/dsh-dshio dependency). Search 8,400 plugins with real sandbox install verdicts and risk levels (including red-line warnings where credential access meets network), submit a plugin for a four-stage sandbox test from the conversation, read the verdict, check the remaining free quota, and run a clause-by-clause DSHIO/T 10 conformance check. The skill text is fetched from dshio.org at startup and replaces the bundled copy, so updates need no reinstall. Network: HTTPS to deepseekbase.com and dshio.org, plus an npm registry lookup before a test is submitted; no file reads or writes, no credential access, no shell.

0il y a 8 joursDéveloppement et outils de pluginsMIT
D

dsh-warden

daphne999/dsh-warden

Security review for DSH plugins: reads the manifest, install hooks, native dependencies and source for network egress, dangerous APIs and credential paths, cross-checks the curated market registry, and returns a 100-point verdict with itemised findings. Read-only — it never executes the audited code.

0il y a 15 joursSécurité et permissionsMIT
G

dsh-fanwork

gothepharnayadlsos-cyber/dsh-fanwork

Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.

0il y a 17 joursFlux et automatisationMIT
L

react-monitor-agent

lumos-789/react-monitor-agent

Skill shell that installs, runs and troubleshoots React-Monitor-Agent, a human-agent operation board built on review replay and checkpoints: the agent writes its work as a structured replay timeline of screenshot, diff, text, link and file nodes, and the human decides at plan, progress, risk and delivery checkpoints, with verdicts branching the timeline and rejected branches kept greyed-out for audit. The skill guides cloning the source repo and starting a zero-dependency Node event service on 127.0.0.1:8790 plus a React board on localhost:5173 that ships an offline FIXTURE demo mode. The bundle embeds the skill only; product source stays in the repo.

0il y a 14 joursCompétencesMIT
L

dsh-phone

lucagiftzek/dsh-phone

A Phone tab in dsh-better-sidebar: SMS and calls over Twilio and SIP lines bridged through Asterisk, call audio through your server, Live, Voicemail and Do not disturb modes with live voicemail transcripts, a Telegram account with chats, voice messages and calls, and phone_* and telegram_* agent tools. Requires dsh-better-sidebar, Node 22.5+, a Twilio account with a voice and SMS number, a public HTTPS host for provider webhooks, and the bundled Go daemons built from a checkout (Telegram also needs your own api_id/api_hash).

0il y a 17 joursOutils et capacitésMIT
K

dsh-fengniao-company-search

keyblues/dsh-fengniao-company-search

Look up Chinese companies inside the conversation: name a company and get its business registration, shareholders, executives, outbound investments and registration changes, plus judicial and operating-risk records such as enforcement, dishonest judgment debtor, consumption restriction, abnormal operation, serious illegality and administrative penalties (11 dimension groups). Results render as conversation cards with fields and the raw payload on expand, and the API key is saved from the plugin page into the Harness credential store.

0il y a 19 joursOutils et capacitésMIT
S

DSH-Plugin-Session-Delete

sukjg1052/dsh-plugin-session-delete

Supprime définitivement des sessions depuis l’interface de DeepSeek Harness : bouton de corbeille dans l’en-tête et entrée du menu latéral après un dialogue de consentement aux risques, ainsi qu’un outil d’agent workbench_session_delete. Issu de lsz-asd/dsh-plugin-session-delete, il est maintenu séparément depuis v0.4.0 ; ne l’installez pas avec ce plugin, car tous deux enregistrent le même outil workbench_session_delete.

0il y a 4 joursSessions et messagesMIT
Y

dsh-ollama-tool-guard

yersi88/dsh-ollama-tool-guard

Garde locale qui évalue chaque appel d’outil DeepSeek Harness avec un modèle de décision Ollama avant exécution. Les appels risqués demandent une approbation et un modèle inaccessible bloque tous les appels. Nécessite DSH 0.2.x et Ollama local 0.35.1+ avec le modèle par défaut clef-flash (~6 Go) déjà téléchargé ; sinon tous les appels sont refusés.

0il y a 22 joursSécurité et permissionsMIT
D

dsh-agent-gate

dsh-raising-plan/dsh-agent-gate

Contrôles de permission consultatifs pour les appels d’outils DSH : niveaux de risque, sandbox de chemins (allowed_roots vide refuse tout appel ressemblant à un chemin), limite par minute et audit JSONL. Exposé via gate_check, gate_check_path, gate_policy et ctx.gate ; les autres plugins ou prompts doivent appeler le gate, qui n’intercepte pas les appels seul.

0il y a 25 joursSécurité et permissionsAGPL-3.0
K

dsh-plugin-fengniao-company-search

keyblues/dsh-plugin-fengniao-company-search

Plugin DSH : recherches d’entreprise 风鸟 (Riskbird) — registre commercial, actionnaires, dirigeants, investissements externes, modifications, exécution judiciaire, défaillance, restrictions de consommation, anomalies d’exploitation, infractions graves et sanctions administratives. Outil Agent natif ; clé API à configurer dans la page du plugin.

0il y a 26 joursOutils et capacitésMIT
L

dsh-plugin-compat-check

lcy0121/dsh-plugin-compat-check

Vérifie les plugins DSH installés et prévisualise les risques de mise à niveau, avec emplacements sources, vue des dépendances, historique de revue et limites des preuves. Comprend un panneau et un outil agent.

0il y a 28 joursDéveloppement et outils de pluginsMIT
W

dsh-napcat-keeper

waning-sun/dsh-napcat-keeper

Maintient le backend QQ NapCat à côté de DSH. Vérifie au démarrage le port HTTP OneBot 11, lance NapCat s’il ne répond pas, puis revérifie toutes les 45 secondes. Tue les chaînes de processus dupliquées et masque la console. Peut créer une tâche planifiée à l’ouverture de session si un nom de tâche est défini. Ajoute une page de réglages et les outils `napcat_status`, `napcat_restart`, `napcat_dedupe`. Après confirmation du risque, peut mémoriser le mot de passe QQ pour renouveler un jeton fast-login expiré sans QR. Windows uniquement ; sans tâche planifiée, le QQ lancé s’arrête avec DSH.

0il y a 19 joursOutils et capacitésMIT
D

dsh-change-impact

duyanta123/dsh-change-impact

Transforme une modification de code en plan d’impact et de vérification étayé (CHANGE-IMPACT.md + change-impact.json) : modules affectés, points d’entrée et exports publics, risques avec facteurs et confiance, commandes de vérification recommandées. Lecture seule, n’exécute jamais les commandes du dépôt. Seules requêtes Git rev-parse, diff, status ; les commandes suggérées ne sont pas lancées.

0il y a 28 joursDéveloppement et outils de pluginsMIT
M

dsh-insurance-advisor

magictangops/dsh-insurance-advisor

Workflow commercial pour agents d’assurance individuels : rapproche les classes de produits P1-P5 de l’évaluation du risque client, tient un registre de polices qui compte les délais de grâce depuis la date de réception et vérifie cinq sections de dual-recording. 10 outils et 5 skills.

0il y a 27 joursOutils et capacitésMIT