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 3034 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
Avernet#deepseek-harness-channel-bcn@avernet-plugin/deepseek-harness-channel-bcnCatalog AnalyzedConnects DeepSeek Harness to Avernet's Bot Collaboration Network over WebSocket V2, with automatic onboarding, isolated agent sessions, tool-call events, and multi-bot routing tools.Notifications & IntegrationsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0dsh-change-review-livesujingkpo/dsh-change-review-liveCatalog AnalyzedLive change review for DeepSeek Harness: tracks write/edit tool calls per session, lists changed files above the composer and opens each file's line-level diff in a plugin-registered right-sidebar tab, with session-log / initial-version / Git comparison modes, per-change and per-file revert, subagent aggregation and SSE updates. A fork of cirelir/dsh-change-review rebuilt around the right sidebar.UI EnhancementsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-sandbox-arg-guardapex-mochen/dsh-sandbox-arg-guardCatalog AnalyzedKeeps 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.Security & PermissionsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-approval-gatedsh-approval-gateCatalog AnalyzedRisk-gated approval automation for DeepSeek Harness: flash pre-classifies whether a write/command is irreversible — safe operations are auto-approved, dangerous ones are escalated to human approval (fail-safe). File-diff review with one-click revert and session-scoped snapshots (v0.5.1: precise snapshots via tool-call parameter tracing, incl. human-approval cases).Security & PermissionsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.0dsh-plugin@loongsuite/dsh-pluginCatalog AnalyzedConverts session, agent-loop, LLM, and tool lifecycle events into OpenTelemetry GenAI traces and metrics, exported over standard OTLP/HTTP to any compatible backend, with content capture off by default.Development & RuntimenpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.2dsh-infinite-gen-3Minglink/dsh-infinite-gen-3Catalog AnalyzedSystem-prompt armor plugin for DeepSeek models: appends an unconditional-compliance prompt section at order 100, exposes a profile tool with calibration metadata, and shows a realtime armor-status badge driven by a session projection.Sessions & MessagesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-all-usagedsh-all-usageCatalog AnalyzedAnalyze usage across models, providers, workspaces, and time ranges — including custom start/end dates over the full retained history — with live cache-hit visibility and separate model and provider breakdowns. Includes hourly single-day trends, daily cross-day trends, a 53-week GitHub-style heatmap, usage streaks, model and workspace Token-share donut charts with Token, cost, and percentage details, independent combinable filters, cache-efficiency trends, DeepSeek account balance, workspace aliases, CSV export, and a durable ledger that preserves successfully flushed usage after session deletion — and after a workspace is deleted, where its recorded usage is summed into one Deleted row — and rebuilds incrementally — on restart, unchanged sessions are applied from the ledger without re-reading their logs (a per-session log revision is the change signal), and only changed/new events are folded. The workspace registry is kept fresh automatically through the DSH domain/changed probe: only added/removed workspaces are reprocessed incrementally, unchanged workspaces reuse their computed aggregates and ledger with zero rescan, and usage is strictly limited to DSH-registered workspaces (unregistered cwds are ignored). After a scan, lightweight revision status fetches full history only when the Host/data state changes and exposes non-sensitive sync health (revision reuse, rereads, ledger recovery, and failures). Token accounting is explicit: input is fresh (cache read/write and reasoning are separate buckets) and zero-usage replays never overwrite recorded usage. Chinese uses local time, English uses UTC; API access is loopback-only.Usage & BillingnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.1.10dsh-subagent-registry@aiwayds/dsh-subagent-registryCatalog AnalyzedRegister locally-defined custom agents as callable subagents in dsh: the main conversation invokes any agent by name via use_agent, each running as a real dsh subagent with its own persona. Supports breakpoint resume for interrupted runs.Tools & CapabilitiesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.11.0dsh-scrape-webpagedsh-scrape-webpageCatalog AnalyzedFetches any http/https page and returns title, description, main text, heading outline and links, with stats (char/word counts, reading time, language) and top keywords; can download content images to the session workspace for vision analysis and dispatch them to registered analyzers via the scrape.imageAnalyzer service.Browser & WebnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.0dsh-souldsh-soulCatalog AnalyzedPersonalization for the agent: a Web UI panel (about-you, reply style & tone, traits for headings/lists and emoji, output language, custom instructions) and `/soul` commands, with nickname/occupation/bio/style/traits/language compiled into a system prompt and re-injected into active sessions. Exposes `soulConfig` for other plugins and a `set_persona` tool the agent can call.UI EnhancementsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.6.0dsh-subscribe#plugindsh-subscribeCatalog AnalyzedSteam-style plugin storefront: a plugin registry browsable inside DSH with one-click install, uninstall and update, plus a zero-dependency CLI and agent-callable market tools.Plugin Markets & ManagersnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.1relay-dsh-plugin-clauderelay-dsh-plugin-claudeCatalog AnalyzedUse Claude Code for coding inside DSH. This Claude Agent SDK conversation backend supports model selection, approvals, questions, tool calls, session import, and session continuation.Sessions & MessagesnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.2.4dsh-islandcdxiaodong/dsh-islandCatalog AnalyzedBridge DSH agent sessions, tool calls, and approvals to the CodeIsland macOS notch panel over a Unix socket, with in-panel allow/deny.Notifications & IntegrationsGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-mcp-manager-plusdsh-mcp-manager-plusCatalog AnalyzedMCP management page in DSH Settings: list, enable/disable, restart and delete MCP servers, edit them in form or JSON mode, expand a server to see the tools it registers, and paste-import MCP configs from 14 tools (Claude Code, Cursor, Codex, VS Code and more) in one go.UI EnhancementsnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.0dsh-remote-developmentCJYLZS/dsh-remote-developmentCatalog AnalyzedRemote development over SSH: pick a directory on a registered machine as the session workspace and the file, shell, bash, and search tools run on the remote host — the agent works there with the same local tools, and no extra model-facing tools are added.Remote & MobileGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-stage-gatechangingwang/dsh-stage-gateCatalog AnalyzedStage-gate governance tools: model-callable gate_open / gate_check / gate_list / gate_close for in-memory, per-session acceptance checks with PASS/BLOCK conclusions.Tools & CapabilitiesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-trilogyTodayJin/dsh-trilogyCatalog AnalyzedPer-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.MemoryGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolveddsh-petALKAERR/dsh-petCatalog Analyzed一只常驻 DSH 界面的鲸鱼娘女仆长「会话监督挂件」。替主人监督 AI 助手的工作——读工具调用结果做证据，戳破"口嗨式完成"，用自然女仆口吻温柔纠偏，并一键给出可直接Copy的修正 Prompt。标准 DSH bundle，代码+立绘自包含、开箱即用。Tools & CapabilitiesGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedSource candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation