Plugins
The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.
Found 1827 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
dsh-auto-reviewdsh-auto-reviewCatalog AnalyzedSecond-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.12.5dsh-redteam-mode#packages/redteam-bundledsh-redteam-modeCatalog AnalyzedRed-team engagement mode: send one target organization name and a planner session runs a five-role agent team (recon, asset triage, vulnerability discovery, exploitation, internal pivot) at up to three concurrent agents, preflight-checking skills and resources and asking for any missing key or VPS first; findings land in a local SQLite fact base with discovery timestamps, shown in a persistent right-side console (asset mapping with a discovery timeline, agent roster, session/tunnel state, five-stage attack chain, scoring targets, a report that spells out how each score was obtained — actions, exact commands, credential provenance, tunnel build commands — and a category-organised POC/EXP knowledge base); ships 13 native skills, 53 redteam_* tools and one-command self-update.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.9.2agent-feedback-loop#dsh-pluginagent-feedback-loop-dshCatalog AnalyzedFeeds every dsh prompt into the local agent-feedback-loop feedback-memory pipeline — captures dissatisfaction, reviews it offline into reflections, and attaches the compiled recurrence-rule context back to the turn, never blocking a prompt. Requires the agent-feedback-loop runtime; running agent-feedback-loop install afterwards wires existing dsh profiles automatically.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.9.0dsh-automode@log.li/dsh-automodeCatalog AnalyzedCC-style auto-approval for DeepSeek Harness: deterministic deny/allow rules plus a two-stage allow/reject classifier with a circuit breaker and denial guidance.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.15.3dsh-plugin-vet@jieai/dsh-plugin-vetCatalog AnalyzedPlugin trust pipeline for DeepSeek Harness: deterministic static scan with verdicts, opt-in runtime guard with honeypot lures, agent audit-protocol skill, and a browser shield status light. Alarm-only, never an enforcer.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.12dsh-authdsh-authCatalog AnalyzedCaddy forward_auth administrator login for DeepSeek Harness Web, with Argon2id passwords, revocable sessions, bilingual UI, and a native sidebar sign-out action.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.3hol-guardhashgraph-online/hol-guardCatalog AnalyzedOpen-source antivirus for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugins, and skills at runtime.Security & PermissionsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-login@islibaodong/dsh-loginCatalog AnalyzedMulti-user login gateway for the DSH web UI: the first visit creates the admin account, admins add and manage users in the GUI settings panel, ordinary users see only their own conversations, and unauthenticated visitors are redirected to /login.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.2dsh-pentesthowmp/dsh-pentestCatalog AnalyzedAuthorized pentest mode for DeepSeek Harness — exploration chain, assets and findings with a Web view.Security & PermissionsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-verification-receiptdsh-verification-receiptCatalog AnalyzedWrites local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0user-management@weibaohui/user-managementCatalog AnalyzedLogin gate for the dsh web UI: unauthenticated visitors get a login/register page and the first registrant becomes admin; includes user and role management plus login and access audit logs.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.9.5qiushi-dsh-evidence-auditqiushi-dsh-evidence-auditCatalog AnalyzedAppends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-mnemondsh-mnemonCatalog AnalyzedCross-agent, local-first persistent memory plugin for DeepSeek Harness (DSH), powered by Mnemon. It shares long-term memory across Mnemon-enabled agents and adds runtime memory, searchable project documents, semantic recall, knowledge graph, and a Sidebar UI.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.11MisakaNetmisakanetCatalog AnalyzedFailure-recovery memory: search and record failure-recovery lessons from real engineering sessions, with BM25 + semantic RAG retrieval and a lessons knowledge base.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact2.30.2ReMe#dsh@agentscope-ai/reme-dsh-pluginCatalog AnalyzedConnects DeepSeek Harness to ReMe's local-first, self-evolving personal knowledge base: automatically captures completed main-agent conversations as user-owned Markdown memory, searches conversations and source material through reme_search with BM25, optional embeddings, and wikilink expansion, and schedules daily memory consolidation.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0hindsight#coding-agents@vectorize-io/hindsight-coding-agentsCatalog AnalyzedHindsight, agent memory that learns: long-term project memory with auto recall and retain, knowledge pages, deep reflection, and per-repo memory banks.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.6.1dsh-mneme@modusensus/dsh-mnemeCatalog AnalyzedThe memory that dreams — cross-session memory for DeepSeek Harness: recalls you across sessions, auto-consolidates in its sleep (autoDream), freezes conflicting memories for your review, and keeps a replayable audit trail. Offline-first local semantic search over SQLite with human-editable Markdown mirrors, an entity graph, an interactive memory panel, plus an external API and CLI.MemorynpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.8.3dsh-yolo-modedsh-yolo-modeCatalog AnalyzedLLM auto-approval for sandbox escalation requests, with presets and a fail-closed fallback.Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.0Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation