Plugins
Browse, filter, and install DeepSeek-Harness plugins.
92 plugins found
dsh-wrapped
rand0wn/dsh-wrapped
Registers /wrapped, which reads the session's own stats and renders a shareable dark SVG summary card — tool vs. thinking time, decode speed, and a tool/thinking-ratio verdict.
dsh-insight
863683348/dsh-insight
Plugin insight center: one answer to "哪些值得装" — plugin_guide matches needs to plugins, recipe installs whole environments, plugin_rank scores health (0-100), plugin_audit static-scans a local checkout for security, and plugin_verdict outputs install / caution / research / avoid.
dsh-plugin-gate
863683348/dsh-plugin-gate
Installation safety gate for DSH plugins: antivirus-style scan of install scripts, permissions, secrets and network callbacks on local directories or npm tarballs, returning a BLOCK/WARN/PASS verdict before "dsh plugin add".
better-auto-review
ericstonechina/better-auto-review
Codex-style auto-review for sandbox escalation: the auto-mode preset takes over the Claude-style Auto button and becomes the new-session default, keeping workspace-write, while a read-only spawn reviewer returns structured verdicts under per-turn budgets and a denial circuit breaker.
Aesthetics-OS
greatbeing/aesthetics-os
Bundles the Aesthetics-OS aesthetic-judgment skill as a runtime skill with a red-line routing section, plus 22 native tools backed by bundled Python scripts: a persistent propose→brief→evidence→measure→critique→verdict state machine that refuses unverified passes, a delivery gate, fingerprint-based reskin detection, and Euler color/texture/structure lenses. State machine needs only Python 3 stdlib; lenses need numpy+Pillow.
dsh-liuyao
hanqing404/dsh-liuyao
Six-line I Ching (Liu Yao) casting and reading for DeepSeek Harness: coin or yarrow casting, a full chart (eight palaces, stems-branches, six relatives and spirits, hidden lines, void, month/day influence, moving-line changes), a verdict and timing from the useful god, the Zhouyi text, plus a sidebar panel and three agent tools.
dsh-plugin-lab
oseas031/dsh-plugin-lab
Zero-restart acceptance lab for DSH plugins: boots a real cordis Loader and ToolsService in a subprocess, drives the mounted plugin through scenario scripts, and reports PASS/FAIL per check with an overall verdict.
dsh-TradingAgents (npm)
vicfei/dsh-tradingagents
Multi-agent investment committee for DSH - analyst, bull, bear, risk and PM debate where every claim carries an evidence tag, abstention (PASS) is a first-class verdict, Buffett/Munger/Lynch/Wood guest seats critique the debate itself, and zero-key market data (CBOE quote/K-line/options-IV + SEC 10-K + nasdaq news, Yahoo-free) feeds an auditable IC-MEMO - 6 to 10 model calls per session.
dsh-pmo-button (dsh-pmo-button)
suifei/dsh-pmo-button
Adds a persistent PMO reviewer subagent to a session: every turn is reviewed and the loop advances with whole-line STATUS: CONTINUE, DONE or NEED_HUMAN verdicts.
dsh-session-icon
masterltx/dsh-session-icon
Draws an icon in front of every session row in the DSH sidebar, decided from the session itself: keyword rules on the title first, then the session content (title, first user message and tool names), then an optional one-shot model verdict, then a workspace fallback. 445 Ant Design outlined icons are inlined for offline use, and the rules, colours, keywords and row indent are editable in a settings page.
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.
dsh-novel-mode
github-yousen/dsh-novel-mode
Writes a novel from one idea to a validated manuscript with a code-driven workflow: a JavaScript state machine runs the stages (constitution, outline, design, writing, validation, batch, export) and a 15-step per-chapter loop, PowerShell scripts validate each gate, and versioned checkpoints let a restart resume at the exact chapter. Nine subagent roles do the drafting and review. Needs PowerShell 7 (pwsh) and Python 3.7+; without pwsh the gates record a DEGRADED verdict and the run pauses.
dsh-pua-receipt
dingchenhui0618-arch/dsh-pua-receipt
Measured /pua for DeepSeek Harness: every pressure message gets a receipt comparing the last N completed model steps with the next N — tool calls, verification-class steps, repeated-call peak, failed calls and text volume — with a three-way verdict (changed approach / merely restated / no change) and a daily ranking of which sentence moved the work. Ships a conversation-view panel, a /pua command with list/status/receipts/rank/off, append-only local JSONL receipts (no tool arguments, content or session ids), 38 node:test tests and a zero-dependency build. Reports observed differences, not causality. Inspired by MichengAI/dsh-pua (independent code); it registers the same /pua command, so it cannot be installed alongside dsh-pua.
dsh-closeout
xinming-chenniang/dsh-closeout
Before closing a coding session or the DSH app itself, checks what would be lost — uncommitted work, unpushed commits, scratch files, missing handoff notes, pending restarts, broken profile bundles — and prints a three-level verdict; when a handoff is needed it writes the seven-section handoff file into the workspace ledger. Read-only by default.
dsh-stall-guard
kkwalking/dsh-stall-guard
Watches the turn endings of the models you select and asks a second model whether the turn was actually finished: if the assistant stopped after text with no tool call, a three-way verdict of continue, finished or uncertain is recorded and shown in a sidebar panel. In suggest mode it only reports; in auto-continue mode it calls agent.followup() once the turn is idle to send a continuation message, up to a per-turn limit. Single-step turns are always rechecked, watched models can be picked exactly or matched by case-insensitive regex, and the resume text is configurable.
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.
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.
dsh-claim-gate
xizhilang2012/dsh-claim-gate
A self-justification gate for outbound claims: a claim needs a checkable source (an http(s) URL plus a quote of at least 8 characters), every number in the text must appear in a quote, and a quote whose vocabulary overlap with the post is under 10% counts as an invalid citation; absolute wording is rejected when the only evidence is second-hand. All verdicts come from deterministic rules — no model call, no network. The guard subcommand refuses to run the publish command when the gate fails (fail-closed), explains what is wrong and how to fix it, and requires an --ack note on the second attempt stating what changed; after three attempts it stops and hands back to a human. Ships check / explain / fix / guard, with 30 tests.
dsh-gui-control
seetown/dsh-gui-control
Windows desktop control for DeepSeek Harness: accessibility-tree snapshots, click by control name, delivery verdicts, and repeatable task files.
ai-native-sdlc-dsh (sdlc)
hmydk/ai-native-sdlc-dsh
AI-native SDLC as a DeepSeek Harness bundle: task state machine and artifact chain, independent verification with structured verdicts, per-issue rework and re-verification, test freezing, RSI retrospectives, and a read-only dashboard.
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.
mindforge-guard-labs-dsh-evidence-check
veeduzyl-hue/mindforge-guard-labs-dsh-evidence-check
Deterministic review of user-declared synthetic AI-agent claims against structured events, snapshots, authorization, policy and coverage records; returns bounded verdicts with reasons and evidence references.
dsh-anti-blind-approval
dynastxu/dsh-anti-blind-approval
反盲批 / Anti Blind Approval — DeepSeek Harness approval guard: review workspace-write escalation requests with the session model, then gate the Allow button on a strict JSON verdict.
antigravity-executor
wuyu1327083461/antigravity-executor
Delegate coding tasks from DeepSeek Harness to the Google Antigravity desktop agent, and watch every turn live in a War Room dashboard: a five-stage lifecycle stepper, streaming tool-call timeline with clean/hanging/escape/destructive verdicts, dual-windo