Plugins
Browse, filter, and install DeepSeek-Harness plugins.
248 plugins found
dsh-task-notifier
lizhijie429/dsh-task-notifier
Sends desktop notifications when a DSH turn finishes or fails, and sends 继续 automatically after the model-retry budget is exhausted.
dsh-workflow (l2-protocol)
weihao654/dsh-workflow
Plan-native multi-agent workflow for DeepSeek Harness: plan directs, work coordinates, code writes, and review audits read-only. Ordinary tasks need no authorization card or budget form. Includes 14 chain_* tools for explicitly authorized controlled rounds, with a frozen T0 baseline, layered evidence, and blocking close gates. Provides per-role model settings. Requires the sibling l1-presets bundle. For new installs, Weihao654/dsh-workflow#role-chain provides this runtime and the four presets in a single bundle. Do not enable role-chain alongside either legacy l1-presets or l2-protocol.
baton
lumos-789/baton
Runs an approved OpenSpec change to completion while the model stays a mechanical forwarder: a bundled Python CLI computes the ticket DAG frontier, claims tasks atomically, prepares one git worktree per assignment, and returns exact actions. The session delegates each action with the DSH subagent tool and reconciles the completion notice against a hash-bound receipt produced by re-running verification commands on a clean, advanced HEAD, so free-text "done" never counts. Runtime scope changes are plain tasks.md edits. Liveness is observable, not guessed: status returns a relay block (elapsed and lease budget, receipt presence, heartbeat and activity age, a suggested action); abandoning a plausibly-still-working attempt is refused with the judgment data unless --force; a late sealed receipt is revived by adopt after full re-verification instead of rebuilding the ticket; dispatched subagents refresh a progress heartbeat outside the worktree. Requires Python 3.10+ on PATH and a git project that uses OpenSpec.
dsh-obsidian-memory
aoyamabf-max/dsh-obsidian-memory
Stores the agent's long-term memory as plain Markdown in an Obsidian vault — every memory is a .md file with YAML frontmatter that Obsidian indexes natively, so you can read, edit, link and back up it with tools you already use. Nothing is locked in a database. Ships a sidebar panel (tag filter, sort by recency or importance, edit in place), 7 agent tools, three-tier token-budgeted recall, BM25 ranking (no embeddings, no API key, works offline, CJK bigram tokenization), importance decay with archiving (moved to .archive/, never deleted), and optional GitHub Contents API sync. A note containing a secret is refused rather than redacted, because a redacted memory reads as complete while the important part is gone. Zero runtime dependencies; everything comes from the DSH host.
token-usage-statistic
zhiwuli0228/token-usage-statistic
Tracks token usage and estimated costs for every model call, with daily charts, session and workspace names, provider balances, budgets, and secret-free CSV/JSON exports.
dsh-mega-plugins (ui-memo-settings)
zhangj1164/dsh-mega-plugins
A Settings page for the memo plugin suite in DSH Web: edits the memo Host's AI route, archived-session summary language, length, transcript budget, template and prompt, and repository URL, adds a GitHub intake section for the claim label, per-run issue cap, autopilot switch and its working directory, preset, time zone and dispatch prompt, with per-field reset and saves that reach the running services without a restart, and carries an update entry that checks the npm registry and can install a newer release through the deployment's plugin manager.
dsh-science-legion
lengrufeng2008/dsh-science-legion
Skill bundle for tiered multi-agent science campaigns in math, physics, astronomy, engineering, and biomedical evidence: a shared blackboard, independent verifier and red team, wolf-pack and flanking tactics, token and time budgets, known-answer evals, a four-agent pendulum pilot, and a six-agent fourth-order pilot that caught and corrected a benchmark answer-key error. Does not claim open-problem solutions.
dsh-sap-ai-core
solstice621/dsh-sap-ai-core
SAP AI Core provider with shared OAuth, five Qwen model choices, thinking budgets, streaming, and tool calls; validated on cn40.
dsh-budget-view
sushuheng/dsh-budget-view
DSH 插件:在输入栏和新会话页展示 Codex / OpenCode Go 额度、DeepSeek 余额、波峰/波谷状态,并按 DeepSeek 官方人民币峰谷价估算会话费用。
sleep-not-permitted
jjjacksong/sleep-not-permitted
Rejects foreground waiting in DSH agents: waiting commands (sleep, wait, tail -f, watch, ping without -c, infinite loops), blocking wait tools (wait_agent, job_output with wait: true), progress polling (the same check command repeated within a window) and commands that need human input/confirmation (sudo without -n, ssh without BatchMode, login flows, interactive editors, docker -it) are refused with an actionable retry to run in the background or end the turn. Configurable budget and polling window, message language follows the system (zh/en), zero runtime dependencies.
dsh-context-budget
dsh-raising-plan/dsh-context-budget
Trim tools for long chats: trim_context / estimate_context_tokens keep the system persona and the last message, drop the oldest user/assistant pairs to fit a turn or token budget, and report before/after estimates; the conversation is not trimmed unless something calls the tools.
dsh-compact-control
zdjmrq/dsh-compact-control
Adjusts the context-window percentage at which DSH triggers its native automatic compaction: a slider on the plugin page in the plugins manager sets it from 1% to 100% (default 80%, arrow keys adjust by 1%), and the retained-history budget shrinks with lower thresholds so early compaction is not defeated; the compaction run itself stays with the native engine.
dsh-context-keeper
orliba/dsh-context-keeper
Watches the context budget of a DeepSeek Harness session: a colour dot in every turn footer (green <50%, yellow 50-65%, orange 65-80%, red >=80%) read from the official contextPressure projection, a reminder panel with a one-click new-session handoff at orange/red, the /context-watch and /handoff commands, and a static reasoning-rule prompt section. Budget and handoff read local session files only; the badge and reminder spend no tokens until the button is clicked.
dsh-plugin-task-budget
i1537725423-dotcom/dsh-plugin-task-budget
Sets a CNY spending cap for each DeepSeek Harness turn (¥5 by default) and stops the run before the next model request once the cap is reached; the switch and amount sit at the right end of the composer dock.
dsh-prompt-enhance-keyless
ozjxnxh/dsh-prompt-enhance-keyless
Adds a sparkle button left of the model selector in the composer toolbar: one click rewrites the draft in place through the host and briefly offers an undo that restores the original text. A Prompt Enhancement settings section picks the lane — the conversation model (the provider/model the next message would use, falling back to the configured default) or a keyless Pollinations channel that needs no login and no token budget but allows one reply per 30 seconds. During that cooldown a click completes through the conversation model instead of being refused, and the first click after the window reopens returns to the keyless channel on its own. The rewrite keeps the draft's language, and a result in a different language is rejected rather than pasted over the draft.
dsh-web-firecrawl
xyonium/dsh-web-firecrawl
Firecrawl as the DeepSeek Harness web backend: query routing, on-demand enrichment, credit budgets and failure memory for web_search/web_fetch.
dsh-plugin-cohere
cn47mp/dsh-plugin-cohere
DSH model provider for Cohere — OpenAI-compatible wire by default, Cohere's native v2 lane for citations/RAG/thinking-budget. Direct wire adapter, no proxy.
dsh-quorum
141w/dsh-quorum
Mechanism-enforced discipline layer for DeepSeek Harness agent teams: role cards, quorum termination, evidence-gated reports and cost budgets.
dsh-context-budget
bushizhanghan/dsh-context-budget
Audit how each turn's context budget is spent. Breaks down what a turn pays for AGENTS.md, the skill catalog, tool schemas and runtime context; flags repeated injection of unchanged content as pure waste; ranks skill-catalog bloat (with 60+ skills installed, how many tokens of descriptions does the model read every turn) and tool-schema inflation per plugin. Deterministic — no LLM, so a wrong answer is a rule bug with a name. Four tools including a cross-session sweep.
dsh-bailian-catalog
kennethfan/dsh-bailian-catalog
Bailian (DashScope / Model Studio) model catalog in the DSH settings page: lists every model the configured API key can reach, groups them by model family, probes whether a model is actually callable (an unopened model answers 403, which DSH reports as an invalid key), refuses to add models that fail the probe, and shows the active session's context window and remaining budget. An sk- key has no balance endpoint, so quota here means context quota.
dsh-lossless-anchors
evannzhongg/dsh-lossless-anchors
Budgeted verbatim user anchors that survive DeepSeek Harness compaction
dsh-pocket-glide
gaudi-xix/dsh-pocket-glide
Turn DSH's phone side into one thumb-reachable column: the host renders pages for narrow screens, zero build, no front-end framework, no desktop pixels streamed. The order is responsiveness > honest state > familiarity > brand > looks. A WeChat push opens the workspace with the conversation on top; sends appear optimistically, streaming never steals your scroll, approvals and queued prompts happen on the phone, plus new sessions, model switching, image and file uploads, and sub-agent rows. The DS Bot team is a tap away with member DMs, group chat and tool-approval cards. Pair over LAN by QR, or go out through a Cloudflare quick tunnel; after a restart the next push carries the new address. A shell byte budget is asserted in tests.
dsh-rf-toolkit
bestgi/dsh-rf-toolkit
Six RF calculators as agent tools: level conversion, link budget and maximum range, cascade noise figure, Shannon capacity, and impedance match.
dsh-context (agent-embodiment)
qiangweiliu/dsh-context
Context observability and control for DeepSeek Harness: cross-session token analytics, session-level budget/prompt/tool controls, and optional agent scaffolds. It reuses the official tokenMeter, compaction, systemPrompt, and tools.restrict seams; monitoring is read-only.