Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

1906 plugins found

D

dsh-plugin-security

dushaobindoudou/dsh-plugin-security

Plugin security review for DeepSeek Harness: dependency advisories, contextual static evidence, a call-time gate for high-risk plugins, and reversible review-gated enforcement.

2last monthSecurity & PermissionsMIT
P

deep-blend

pearjelly/deep-blend

Create Blender product scenes in DSH with editable recipes, model imports, previews and PNG/MP4 delivery; includes workbench and agent configuration.

2last monthTools & CapabilitiesMIT
L

dsh-glm-web

lequait/dsh-glm-web

Unofficial Zhipu Qingyan (chatglm.cn) web provider — run DeepSeek Harness on web-app credits with a login token, streaming and prompt-bridged tool calls included.

22 months agoModels & ProvidersMIT
B

dsh-project-mcp

borgez/dsh-project-mcp

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

2yesterdayTools & CapabilitiesMIT
P

dsh-skill-intelligence

polinnizhong/dsh-skill-intelligence

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

2last monthSkillsMIT
C

dsh-image-gen

copylee711/dsh-image-gen

Image generation with a sidebar gallery page and three agent tools (paint_image, paint_images, edit_painting); preset providers include ModelScope, Google Gemini, OpenAI, SiliconFlow, Volcengine Seedream, Alibaba DashScope, xAI and Zhipu, plus any OpenAI-compatible endpoint, each with its own proxy setting.

228 days agoVision, Voice & MultimodalMIT
D

dsh-live-inspector

datit309/dsh-live-inspector

Real-time inspector of the files the agent reads and edits, with a file tree, in the DeepSeek Harness right sidebar: M/A/R badges, side-by-side diffs and live agent activity tracking.

22 months agoUI Enhancements
J

dsh-action-outbox

jimchen-g/dsh-action-outbox

Stages exact DSH tool calls without dispatch, presents complete canonical arguments in a durable Batch Review Inbox, invalidates approvals after edits or restarts, and commits only a matching SHA-256 digest plus single-use nonce through the normal DSH tool pipeline.

22 months agoSecurity & PermissionsMIT
S

euthyna

slow-stack/euthyna

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

28 days agoSecurity & PermissionsApache-2.0
S

KISS_Law-DSH

shaky77/kiss_law-dsh

English edition of Weiwen's Law (KISS's Law): the first and only domain-agnostic white-box causal adjudication middleware for AI agents. Unlike domain-specific causal-inference tooling (statistics/economics/ML) or evidence-gated agent firewalls, it adjudicates *every* tool call along a deterministic structural causal chain (R->S->D->H->M) before execution - across any domain, with no training or per-domain tuning. It blocks destructive and credential-file operations, escalates repeated boundary violations, cuts faulting links until verified-fixed, and gives risk verdicts on un-auditable execution; runs fully local with zero API cost.

215 days agoSecurity & PermissionsAGPL-3.0
M

dsh-approval-explain

martlet-tech/dsh-approval-explain

Adds an Explain button to the approval card: one model call returns exactly three lines reading the pending operation, covering what it does, which files or system state it reads, writes, modifies or executes, and a risky/attention/safe verdict with a one-sentence justification. It also renders the detail area for `write` and `edit` calls, which the shipped renderer leaves blank because it only reads a `command` field.

22 months agoSecurity & PermissionsMIT
Q

DSH-THEME-KAMI

quaner1234-cmd/dsh-theme-kami

Kami-inspired editorial skin for the DeepSeek Harness web UI, with a warm parchment canvas, ink-blue accent, serif typography and hairline borders in light and dark palettes.

22 months agoThemes & Appearance
C

dsh-inbox

chance722/dsh-inbox

Personal paste inbox for DeepSeek Harness (dsh): /inbox in the composer or the sidebar panel files links, images, text and credentials into a local vault, classifies them by local rules and then by a rate-capped model pass, and browses, searches and edits them from the panel; the assistant retrieves records on request in conversation, credential bodies stay encrypted at rest, and an optional WebDAV or S3 remote syncs records and attachment bytes. Windows only so far.

2last monthMemoryMIT
D

dsh-allow

dwjz/dsh-allow

Filesystem permissions for shell calls, granted per path and capability rather than per command name. The command line is parsed for the read, write, create, delete and execute effects it needs, a capability it lacks raises the approval card instead of a flat refusal, and the same rules are compiled into the macOS Seatbelt profile the process, its children and the code its arguments never showed all run under. An Approvals tab in the conversation reads the audit log back and shows which rule, automatic reviewer or person answered each call.

220 days agoSecurity & PermissionsMIT
7

dsh-jev-guard

7starsseeker/dsh-jev-guard

Pre-execution safety valve for DSH that judges with TypeSafe Jev: it hooks tools/pre-execute and decides every bash/pwsh call by first applying offline static rules, then by asking the Jev model — the System One model from TypeSafe, which returns a structured decision instead of prose — one yes-no question ("will this command irreversibly delete or overwrite real data?"), turning the answer into allow, revise, block or escalate; revise hands the model a safer rewrite, escalate offers a one-shot human token; exhausted credit or a missing API key degrades loudly instead of failing silent, and a missing key is requested in the conversation itself (`guard key set`, read from stdin); every verdict is appended to a shared audit log and the text people read is bilingual zh-CN/en.

27 days agoSecurity & PermissionsMIT
Y

dsh-pptx-editor

yunfeizhu/dsh-pptx-editor

Preview and edit attached PowerPoint presentations in the DSH sidebar through conversation or manual controls, with shared undo/redo and PPTX download.

23 days agoTools & CapabilitiesApache-2.0
M

dsh-plugin (dsh-model-capability-editor)

mzzsfy/dsh-plugin

Model capability editor: edit each model reasoning-effort levels and image-input (multimodal) declarations inline in the official model page, written back to settings.yaml as a whole group, with a floating entry as fallback when the anchor breaks.

2last monthModels & ProvidersMIT
D

dsh-prompt-studio

dsh-external/dsh-prompt-studio

Edit system-prompt sections with live preview.

23 months agoSessions & MessagesBSD-3-Clause
S

dsh-sidebar-plus

sailoumili/dsh-sidebar-plus

A file-view enhancement plugin that extends the official DSH sidebar, providing source view, in-place editing, line number display, search, and font zoom.

22 months agoUI EnhancementsMIT
V

dsh-peak-balance

vvilliam-qwq/dsh-peak-balance

Peak/off-peak billing clock with a provider-neutral account readout (DeepSeek balance, subscription plan windows, relay credits), per-turn spend measured from the provider's own counter, and a /hist token-history scene split per provider for dsh-tui

22 months agoUsage & BillingMIT
S

codebase-chat

shinzarou-eng/codebase-chat

Multi-language codebase intelligence for MCP-compatible IDEs, the CLI and DeepSeek Harness: chat, search, audit, refactor, and board-ready reports from local code.

22 months agoMCP & ConnectorsMIT
B

dsh-remote-file-system

better-er/dsh-remote-file-system

Model-visible SSH file tools read_remote, write_remote and edit_remote: read a remote UTF-8 file with line-numbered paging, create a new remote file (an existing target is refused, there is no overwrite branch), and apply literal replacements with unique-match checking — all addressed through a single "alias:path" field whose alias comes from ~/.ssh/config.

25 days agoTools & CapabilitiesMIT
H

dsh-cloud-workspaces

harryopo/dsh-cloud-workspaces

Cloud workspaces for DeepSeek Harness: pick "Cloud (SSH)" in the workspace chooser and the agent's bash/read/write/edit/glob/grep tools transparently run on your Linux server over SSH. Includes ssh_* agent tools, an SSH host settings card, jump-host suppo

22 months agoTools & CapabilitiesApache-2.0
M

commandcode-dash

momonaka/commandcode-dash

Unofficial DeepSeek Harness settings panel for Command Code: credits, usage windows, and model-catalog sync.

22 months agoUsage & BillingMIT