Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

60 plugins found

P

dsh-auto-review

perrylink/dsh-auto-review

Second-model auto-review on the approval answerer chain: a read-only reviewer subagent returns structured allow/deny verdicts with reasons, fail-closed by default.

254yesterdaySecurity & PermissionsApache-2.0
J

Awesome-Gaussian-Skills

jaccen/awesome-gaussian-skills

3D Gaussian Splatting / NeRF / computer-graphics research skills — 18 AI skills (paper reader, method compare, experiment planner, code reviewer, training debugger, visualizer, MCP renderer…) over a curated 1011-method catalog, plus a stdio MCP server for agent-driven 3DGS rendering.

1902 days agoSkillsApache-2.0
A

dsh-ultramath

andiii208/dsh-ultramath

Multi-agent workflow for math-modeling contests: the "UltraMath" preset runs a problem from reading through framework, derivation, coding, verification, paper and review, plus 4 single-stage role presets (mathematician, engineer, writer, reviewer) and 33 model-library skill docs.

443 months agoSkillsMIT
K

ARK (dsh)

kaust-ark/ark

Runs experiments and writes a paper in one persistent DSH session, with a separate reviewer that checks the rendered manuscript against sources and measurements.

382 days agoWorkflow & AutomationApache-2.0
N

dsh-decision-review

ninetyhe-90/dsh-decision-review

Lets the primary model ask an independent reviewer model to review a decision it has already made, with off, shadow and advisory modes. Requires your own service implementing POST /v1/decision.

3322 days agoTools & CapabilitiesMIT
Z

lunheng-article-pipeline-dsh

zuoyunlai/lunheng-article-pipeline-dsh

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 26-check M-gate (25 scripted checks plus one human checkpoint), a G0-G16 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 36 zero-dependency verification scripts, with five-language READMEs.

283 days agoSkillsMIT
Y

dsh-expert-team

yangdcm/dsh-expert-team

Role-based multi-agent team for DeepSeek Harness — your digital workforce. One goal assembles a team of product, architect, frontend, backend, reviewer and QA roles that deliver through a nine-phase gated pipeline, plus a persistent team you can keep directing across sessions. Zero runtime dependencies, no build step.

2016 days agoWorkflow & AutomationMIT
7

dsh-skill-7d-code-reviewer

7dgroup-ai/dsh-skill-7d-code-reviewer

Template-driven code review skill: five-step review flow, critical/medium/minor severity grading, four-dimension scoring (quality, security, performance, maintainability), dual text and HTML report output, and an on-demand reference knowledge base.

142 months agoSkillsMIT
B

dsh-answer-reviewer

bycall/dsh-answer-reviewer

Agentic answer reviewer for DeepSeek Harness: each final assistant turn is re-reviewed by a separate LLM graded 1-100; below-threshold scores steer the agent back with concrete feedback. The score is shown as a chip on the answer's action row (green pass / red needs-work, with retry count and reason on hover). Live gate config from the Reviewer 配置 tab in the conversation view ring above the composer (对话 / 轨迹 / 记忆系统 / Reviewer 配置), from a 127.0.0.1 HTTP server, or from an optional right-sidebar tab via dsh-better-sidebar.

134 days agoMemoryMIT
L

dsh-swarm-orchestrator

linkbag/dsh-swarm-orchestrator

Role-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.

1316 days agoWorkflow & AutomationMIT
T

dsh-approve-for-me

timeance/dsh-approve-for-me

Rule-gated automatic approval for DeepSeek Harness sandbox escalations with an optional LLM reviewer and native human fallback.

123 months agoSecurity & PermissionsMIT
D

dsh-egm

dryw/dsh-egm

Design-review gate for DeepSeek Harness, a DSH port of Google's Elephant-Goldfish Model: a context-rich Elephant session drafts the design, then fresh, zero-context, read-only Goldfish reviewers stress-test it before implementation. Registers the `egm` plugin id; install one EGM bundle per profile.

116 days agoWorkflow & AutomationApache-2.0
M

dsh-switchman

mrzturn/dsh-switchman

Sessions and messages (`session`): built to defuse the three ways a long agent session fails. 1) The context window fills up — the session gets dull, forgets earlier agreements, or dies mid-task. The plugin manages the context watermark end to end: automatic folding at idle boundaries with a persisted fold ledger and deterministic rebuild (the serialized prefix stays byte-identical between folds, so the provider prompt-prefix cache keeps hitting), a protected recent tail, three escalating watermark tiers, and an automatic write-handover-doc-then-compact at the top tier that never abandons running subagents — the main session never explodes, and token spend tracks the work instead of the chat length. 2) File edits fail in loops — a missed anchor burns turn after turn. A listener rewrites native `edit` / `str_replace_editor` misses into self-contained corrective feedback: per-match excerpts of the file's exact text, the failure class (whitespace drift, multi-hit, zero-hit…), the correct retry recipe, and a loop-guard that orders a strategy switch after three same-class failures — the model fixes itself on the next try instead of guessing. 3) One model in one burnt-out context loses perspective — advantage-based delegation dispatches across six model pools (economy/mechanical/main/hard/vision/review, optional intent routing) only when it wins: a pristine child context that has not spent a token on your history, an independent model/effort lane, parallelism, blast-radius isolation; detail-bearing edits are still done directly. When two of three structural constraint tags fire in a turn, an Agent Team assembles autonomously; otherwise plain subagent dispatch stays the default, and tiered verification routes larger or core changes to independent reviewers. Also: per-scope output-language preferences, token tracking (no bill calculation), read-only MySQL/Redis checks plus commit-message and requirements-doc skills, and an offline session-log repair tool. Every capability above serves the live session and its messages. Its HTTP routes have no DSH access check, so a web page open in your browser could call them.

1017 hours agoSessions & MessagesMIT
L

dsh-approval-llm

letter2025/dsh-approval-llm

Model-based permission approval: an approval-request answerer backed by a separate reviewer model.

86 days agoSecurity & PermissionsMIT
J

dsh-swarm

joekytc/dsh-swarm

A governed swarm of six specialist DSH agents — orchestrator, planner, knowledge-base bridge, developer and two reviewers — turns a requirement into a strict phase pipeline where every delivery must prove itself with structured evidence before the next phase may start; reviewers are read-only, code merges only after a review pass, and an append-only event log gives full replay and audit on a live kanban board. Its design draws inspiration from the Hermes Agent kanban.

7last monthWorkflow & AutomationMIT
M

dsh-company

makooslee/dsh-company

Multi-agent agent team of employee AI subagents for DeepSeek Harness — dsh-company: employee management, CEO bidding, n8n workflow orchestration, drag and drop canvas. DeepSeek Harness plugin with seven built-in roles (project director, product manager, tech lead, engineer, data analyst, QA, reviewer), each with its own persona, model and tool whitelist. Broadcast a mission and the employees bid for it themselves — the first line of their answer must be 【accept】 or 【decline】 — so accepted work runs in parallel instead of down a pipeline. The workflow canvas wires employee nodes with the start node, references each upstream result with {{input}}, and runs the graph in topological layers: parallel across employees, serial per employee, downstream skipped when upstream fails. Ships a web panel for the employee management tab, the mission board and each employee's transcript, the /dsh-company slash command, a live mirror into the built-in agent-team panel, deletable missions, and a private memory directory per employee.

64 days agoWorkflow & AutomationMIT
S

dsh-crew

stuarthu/dsh-crew

Runs 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.

6last monthWorkflow & AutomationMIT
S

dsh-auto

simon300000/dsh-auto

Adds an Auto Approve permission preset to the Web UI, using a fresh restricted Reviewer Agent to allow or deny each approval request.

62 months agoSecurity & PermissionsMIT
B

dsh-superagent-ptc

bioaievolu/dsh-superagent-ptc

SuperAgent PTC: long-task supervision for DeepSeek Harness. Versioned goal anchors, bounded delegation (Mandate), independent read-only Reviewer acceptance, typed evidence gates and crash-safe proof/recovery. Native PTC execution, preset-first, no second

42 days agoWorkflow & AutomationMIT
L

dsh-advisor-plugin

leeyoung1/dsh-advisor-plugin

Pairs the running executor with a stronger reviewer model through zero-parameter advisor() calls and step-based patrol checks, returning plan, correction, or stop guidance.

42 months agoWorkflow & AutomationMIT
O

dsh-video-preview

orderg-x/dsh-video-preview

Plays local video and audio inside the conversation. Media files the model writes during a turn - screen recordings, transcodes, voiceovers - get a player under its final reply automatically when their paths appear in its commands, the command output or the reply; the play_video tool plays any other file. Video shows as compact cards with a hover preview, audio as a slim seek bar, streamed over HTTP Range so long files seek instead of loading into memory. Also registers a sidebar media preview renderer, since the built-in previewer treats mp4 as unviewable. The look_video tool lets the model see a video itself: a hidden local Chrome or Edge grabs frames into a time-labelled contact sheet (or big frames at given times, or a short range frame by frame), checks the audio (silence, too quiet, clipping, one channel only) and the picture (black or frozen frames), and reads MP4 / MOV headers for phone compatibility (codec, HDR, faststart and more), with ffmpeg fixes.

310 days agoUI EnhancementsMIT
K

dsh-captain

kanonouta/dsh-captain

GPT plans dependency DAGs, DeepSeek workers execute tasks with adaptive parallelism, and an optional GPT reviewer audits incremental Git diffs and drives repair rounds.

33 months agoWorkflow & AutomationMIT
P

dsh-deliver-studio

passenfall/dsh-deliver-studio

HTML deliverable workbench in the file preview: viewport presets (desktop, laptop, tablet, mobile, A4), click-to-annotate elements with a notes/QA panel that docks to any edge or floats and sends the notes to the agent as one message, delivery QA grouped by category (figure/table numbering, orphans, clipping, overflow, page whitespace, WCAG contrast, images, dead anchors, banned words), PDF export through a local Chromium-based browser, and export of a self-contained annotated HTML that reviewers open in a browser to reply; also provides the `deliver_qa` and `deliver_export_pdf` tools and a `/deliver` command.

212 days agoTools & CapabilitiesMIT
A

dsh-orchestrator2 (dsh-orchestrator2)

anglezhang-zhangjiao/dsh-orchestrator2

Agent preset: one session runs a three-phase auto-development pipeline — interactive design with parallel research subagents, goal-driven development with reviewer/developer subagents and per-package budget ledgers, then an acceptance fix loop.

2last monthWorkflow & Automation