Plugins

The complete directory supports discovery. Quality dimensions are shown separately; automated analysis does not prove feature completeness. The plugin manager continues local inspection.

Reset all
Found 657 source candidates (configured-source coverage 15812 / 15812) · snapshot: 2026-09-19Search order: text relevance first + bounded quality evidence
oh-my-dsh-slimoh-my-dsh-slimCatalog AnalyzedMatch your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.2Evidence updated2026-09-19Public signals13 stars · 2180 downloadsdsh-graph#dsh-graph-hostdsh-graphCatalog AnalyzedGoal lifecycle management for dsh with an interactive kanban board: goals, criteria, attempts and reviews live in the workspace, driven by graph_* tools, with a two-lane board rendered in the conversation view.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.11.2Evidence updated2026-09-19Public signals10 stars · 2675 downloadsdsh-Kingdomdsh-kingdomCatalog AnalyzedAgent governance kingdom for DeepSeek Harness: territories, role bindings (bind/unbind/session with model/agent identity), and a plan→assign→execute→review task loop where Worker claims never auto-complete (Claim ≠ Fact), with a local GUI operations console.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact2.0.0Evidence updated2026-09-19Public signals15 stars · 1262 downloadsmy-dsh-plugins#dsh-task-reliabilitydsh-task-reliabilityCatalog AnalyzedTask reliability: auto-retry on model timeouts/failures, auto-continue unfinished tasks, completion verification, thinking-repeat interruption, resume after sleep or restart, autopilot mode and a remote trigger endpoint (npm: `dsh-task-reliability`).Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.8Evidence updated2026-09-20Public signals7 stars · 1659 downloadsdsh-tasks@weibaohui/dsh-tasksCatalog AnalyzedScheduled tasks: run a prompt on cron schedules, each run opens a new agent session to do the work, with workspace binding, manual run, session auto-naming, and a fullscreen task management page.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.4.5Evidence updated2026-09-20Public signals7 stars · 1637 downloadsAI-Novel-Writer#dsh-ai-novel-writer@ethanyoq/dsh-ai-novel-writerCatalog AnalyzedInstalls a dedicated AI novel-writing preset and workbench: revisioned local project assets, a compact side drawer, and native approval-gated single-file changes.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.0Evidence updated2026-09-18Public signals988 stars · 1210 downloadsdsh-crewdsh-crewCatalog AnalyzedRuns work as a crew of role agents: a product manager writes the PRD or DoD, waits for your confirmation, then starts architect, engineer, QA and reviewers whose tool sets are locked per role, and shares work through files on disk.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.10.0Evidence updated2026-09-20Public signals6 stars · 1747 downloadsdsh-novel-solodsh-novel-soloCatalog Analyzed"Single-Core Writing" plugin for DeepSeek Harness: Thoroughly tool-streamlined and output-hardened for quantized small models, suitable for running long-novel pipelines locally with on-device models.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.6Evidence updated2026-09-20Public signals6 stars · 1567 downloadsget-fableget-fableCatalog AnalyzedModular frontier execution discipline for DSH: evidence-first routing across 26 skills, Manus-style file planning, verification gates, fail-streak recovery, and an interactive web dashboard.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.9.1Evidence updated2026-09-20Public signals6 stars · 1483 downloadsdsh-subagent-profiledsh-subagent-profileCatalog AnalyzedDispatch subagents with named profiles (model, reasoning effort, and tool scope per task), safety checks, cost estimation with savings comparison, and a full dispatch decision ledger.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.1Evidence updated2026-09-20Public signals5 stars · 1555 downloadsdsh-pre-duediligencedsh-pre-duediligenceCatalog AnalyzedPre-visit due diligence and company research in DeepSeek Harness for customer background checks and risk briefs, with Qichacha MCP tool-call budget approval and entity confirmation.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.1.40Evidence updated2026-09-21Public signals2 stars · 5757 downloadsdsh-swarm-orchestratordsh-swarm-orchestratorCatalog AnalyzedRole-based AI swarms for DeepSeek Harness: an architect plans, parallel builders execute, reviewers gate quality, and an integrator ships. Per-role model pinning with fallback chains, review loops, evidence contracts, human-gated reviews, quota-aware pause/resume, and a live kanban + flow chart in the web GUI. 40 tests; installs from GitHub or npm.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.6.8Evidence updated2026-09-21Public signals3 stars · 3190 downloadsnovel-writernovel-writerCatalog AnalyzedInstalls a multi-agent novel-writing preset for DeepSeek Harness: one conductor agent dispatches five specialized subagents — world-building, plotting, character management, prose writing, and QA review.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.0.2Evidence updated2026-09-19Public signals27 stars · 60 downloadssandbase-harnesssandbaseai/sandbase-harnessCatalog AnalyzedConnects dsh to a local SandBase Harness runtime over stdio MCP for managing agents and sessions, streaming turns, inspecting artifacts and cancelling work.Workflow & AutomationGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency auditNot testedArtifactUnresolvedEvidence updated2026-09-27Public signals646 starsrecowork#recowork-dshrecowork-dshCatalog AnalyzedCreates and inspects RecoWork local-agent-project workspaces through two bounded DSH tools and a web workspace card.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.3.0Evidence updated2026-09-20Public signals5 stars · 963 downloadsgitee-ai-employeegitee-ai-employeeCatalog AnalyzedGitee/GitHub AI employee: @ the bot on an issue (Gitee or GitHub), it clones the repo, implements the fix on the branch you name, opens a PR to that branch, and can auto-merge and auto-close the issue. v1.2 adds security scanning: configure scan repos, audit with built-in/custom prompts, deduplicate, and file new findings as issues.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact1.2.8Evidence updated2026-09-21Public signals3 stars · 2121 downloadsdsh-tender-workbenchdsh-tender-workbenchCatalog AnalyzedTender search and bid intelligence in DeepSeek Harness with proposed project search, rule screening, human review and Excel/PDF exports using user-authorized Qichacha MCP.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit1 reported in bounded auditArtifact0.5.11Evidence updated2026-09-21Public signals2 stars · 3504 downloadsdsh-plugin-omoslimdsh-plugin-omoslimCatalog AnalyzedInstalls an Orchestrator agent preset that plans and dispatches to model-pinned specialist subagents (explorer, oracle, librarian, designer, fixer, council), with named model profiles switched via an omoslim CLI and a Web inspector button showing the current subagent models.Workflow & AutomationnpmGitHubCompatibilityDSH 0.1.6-alpha.2 · webDependency audit0 reported in bounded auditArtifact0.5.2Evidence updated2026-09-20Public signals5 stars · 860 downloads
Source candidateDescriptions are untrusted text imported from third-party catalogs and public sources reviewed by the RegistryLocal inspect / plan / confirm is still required before installation