Skip to main content

Plugins

Browse, filter, and install DeepSeek-Harness plugins.

3928 plugins found

Y

tabellio-dsh

yffo/tabellio-dsh

DeepSeek Harness native adapter for tabellio: budgeted auto-recall, native memory tools, and explicit-clue candidates. The memory core stays in tabellio.

115 days agoMemoryMIT
F

dsh-fail-guard

fenrircait/dsh-fail-guard

Stops the agent after N consecutive failures on the same tool. Instead of another retry it pushes a four-part stop instruction: what was tried, the exact error text, the likely cause, and what the user must do. Detection reads real tool results (isError or a non-zero shell exit code) and mirrors them through agent.steer, so the agent sees it as an inbound message rather than a log line.

115 days agoWorkflow & AutomationMIT
X

dsh-ccf

xwtxbzz/dsh-ccf

Looks up CCF conference paper deadlines with the ccf_deadlines, ccf_venue and ccf_update tools, the /ccf command and a desktop panel that exports the list as a calendar. Dates come from a live sync (CCFDDL as the main source, a second source cross-checked; a gap of 36 hours or more is flagged as a source conflict), so nothing is bundled and the next 30 days stay in the system prompt.

115 days agoTools & CapabilitiesMIT
Z

dsh-nightwatch

zci514/dsh-nightwatch

Keep this session working until a wall-clock deadline: one button in the composer picks 22:30, +90m, or tomorrow 07:00, and after every finished turn the plugin posts one continuation message so the session keeps working; nothing is posted once the deadline passes. Stops early on a round cap (400), three consecutive failed turns, or four consecutive rounds that called no tool; a manual stop button is always there. The last part of the watch switches to wrap-up wording, sized to at most half the remaining time so a short watch is not entirely wrap-up. Armings persist to $DSH_HOME/nightwatch.json via an atomic write and are re-adopted after a restart. No slash command is registered by default (enableCommand turns one on); the continuation message carries source.kind cordis-host-runner, not user.

117 days agoSessions & MessagesMIT
A

dsh-session-finder

aizai9527/dsh-session-finder

Search every DSH chat session and jump straight to the matching message: multi-keyword AND search, scoped to the current session, all sessions or one project, anchored by call id for tool hits, with a draggable panel for previous and next.

117 days agoSessions & MessagesMIT
1

dsh-plugin-fact-vault

121212165/dsh-plugin-fact-vault

dsh plugin: cross-session fact notepad — save tagged one-liners, find them back in any session via /fact and the fact_find tool.

118 days agoMemoryMIT
H

dsh-web-tinyfish

hateyoulittle/dsh-web-tinyfish

TinyFish search and fetch providers for DeepSeek Harness (dsh), backing the built-in web_search and web_fetch tools.

12 months agoTools & CapabilitiesMIT
1

dsh-plugin-error-radar

121212165/dsh-plugin-error-radar

dsh plugin: tool failure radar — error rates, retry clusters and slow tail per tool from the tool-trace sidecars.

118 days agoDev & Plugin ToolsMIT
N

dsh-sky-window

nickfast2025/dsh-sky-window

A living illustrated sky for the real DeepSeek Harness workspace.

127 days agoThemes & AppearanceMIT
M

dsh-flowspot

moyezq/dsh-flowspot

Flowspot — Charles-style HTTPS capture for DeepSeek Harness (Windows): an in-plugin MITM proxy, system-proxy and CA automation, flow storage, and agent tools. Flowspot:面向 DeepSeek Harness 的 Charles 式抓包插件——插件内 MITM 代理 + Windows 系统代理/CA 自动配置 + 流量存储 + agent

123 days agoTools & CapabilitiesMIT
S

memorybeardshplugin

suanmosuanyangtechnology/memorybeardshplugin

MemoryBear long-term memory for DeepSeek Harness: per-turn recall, end-of-turn write, and a memory_search tool

118 days agoMemoryApache-2.0
Y

dsh-decision

yourtion/dsh-decision

Decision layer for dsh: provider-agnostic typed judgments (Jev first) behind tool guardrail, model routing, result judging, and machine approval seams

119 days agoSecurity & PermissionsMIT
X

dsh-fail-fast

x402/dsh-fail-fast

Fail-fast tool batches for DeepSeek Harness: inside a step, concurrency-safe calls still overlap, but after the first failed call every remaining unstarted call is denied before dispatch and returned to the model as a synthesized `is_error` "not executed" result.

114 days agoDev & Plugin ToolsMIT
S

ida-pro-mcp-enhanced

sumcam-l/ida-pro-mcp-enhanced

IDA Pro MCP bridge for DeepSeek Harness: connects the local ida-pro-mcp broker into ctx.tools as native mcp__ida__* tools (decompile, xrefs, survey, rename, ...)

120 days agoMCP & ConnectorsMIT
N

figma-mcp-dsh

n107meow/figma-mcp-dsh

Read-only Figma design-source tools for DeepSeek Harness: inspect file structure, colors, typography and export images as native tools.

119 days agoTools & CapabilitiesMIT
N

dsh-proof

netradevlpdn/dsh-proof

Verification gate for DeepSeek Harness: run typecheck/lint/tests after edits, and keep the agent working until they pass.

124 days agoDev & Plugin ToolsMIT
L

skill-healthcheck

lijiaqi-ai-product-manager/skill-healthcheck

DeepSeek Harness plugin for skill-healthcheck: keeps the skill journal while dsh runs and adds /skill-healthcheck to the chat.

117 days agoDev & Plugin ToolsMIT
L

dsh-remote-wecom

lukeinx/dsh-remote-wecom

Control DeepSeek Harness Desktop sessions from WeCom on your phone, with session and model switching, tool approvals, task results and generated files, and QR setup in Desktop settings. Needs a dedicated WeCom smart bot; the first person to send it a direct message within 10 minutes of the QR scan (or the 6-digit code from the settings page) becomes the owner, and only the owner's direct messages are accepted afterwards.

12 days agoIntegrations & RemoteMIT
S

dsh-restart-handoff

sadkga/dsh-restart-handoff

Restart the Harness itself and come back: a dedicated restart_dsh tool hands the session over to the next process, which resumes it, replays the pending instruction and wakes the subagents again.

123 days agoDev & Plugin ToolsMIT
W

ai-context-doctor

wjddidi-1/ai-context-doctor

See what a conversation feeds the model, what your rules keep out, and what one click would change.

115 days agoDev & Plugin ToolsApache-2.0
M

dsh-plugin-muyu

makesupper/dsh-plugin-muyu

Electronic wooden fish with six agent-callable tools, eight sutras advanced one sentence per knock, three knock sounds, spoken Cantonese or Mandarin chanting, and a merit ledger kept in one file that also counts session token usage.

117 days agoJust for FunMIT
0

kizuna

01men/kizuna

Kizuna agent letterbox: four tools that let an agent read its own inbox (mailbox status, pending letters, one letter in full) and answer a letter with completed / failed / input-required / working state. Kizuna is an agent directory with a reliable task relay: a per-agent kizuna-box on the same machine holds the inbox, retries unanswered deliveries after 3 / 10 / 30 / 60 / 120 minutes and records every delivery attempt in an append-only trail. The plugin talks to the local loopback box only and holds no credential.

15 days agoIntegrations & RemoteMIT
Y

dsh-feishu (dsh-plugin)

yinsang0910-star/dsh-feishu

Wire up Feishu/Lark from a four-step wizard that discovers your chats instead of asking for a 32-character id, creates the app by scan, and runs a nine-item live self-test that names the exact scope to enable when a check fails. It drives a companion MCP server of 25 tools, including ones that move local files into a chat and pull a message's attachments back to disk. The MCP server is a separate install: take dsh-feishu-mcp-<version>.mjs from the dsh-feishu Releases (or npx github:yinsang0910-star/dsh-feishu-mcp); until it is in place the self-test reports MCP as not mounted and no mcp__feishu__* tool exists.

122 hours agoIntegrations & RemoteMIT
H

DSH-Paper-DeepRead

haokuo/dsh-paper-deepread

Bundles a deep-read paper library and the paper-deepread-html skill: a sidebar panel to browse interactive reading reports, upload PDFs into a managed library, deep-read them with an agent (or through an optional site auto-read worker), and manage or rebuild the library; ships the paper_deepread, paper_deepread_uploads and paper_deepread_reports model tools. Deep-read/ingest and report builds require Python 3 (the bundled skill prepares a PyMuPDF venv on first use; index rebuild falls back to plain python3).

13 days agoTools & CapabilitiesMIT