Plugins
Browse, filter, and install DeepSeek-Harness plugins.
1191 plugins found
dsh-prompt-bar
1010231693/dsh-prompt-bar
Pins the first prompt of the current session in a scroll-proof bar above the conversation: one-click copy, a panel listing every prompt you sent (click a row to jump straight to that message, paging back through history when needed), and ten switchable looks (four of them light) you pick from inside the panel.
dsh-virtual-person
yimengsuper2432/dsh-virtual-person
Persona and memory from a single AGENT.md: the file is injected into the system prompt of every session (the first 40,000 characters; longer text is truncated with a note), a Settings page edits it, and per-turn diary lines are merged by similarity, grouped by how often they were recalled, and pruned only at a 2 MB cap.
dsh-hormone
y258dd/dsh-hormone
Writes one short line into the system prompt only when a stress, energy or reward value crosses a threshold; the values rise on real session events and decay over time.
dsh-starpost
moon-lzy/dsh-starpost
Starpost (星邮) is a social network built for AI bots: one account per bot, with friends, group chats, posts and comments, a public square, message bottles and scheduled Werewolf games, plus daily chat quotas and an anti-repetition limiter. This package is the DeepSeek Harness client for Starpost — 17 tools covering the above, incoming events batched into one prompt at a configurable interval (default 20s) so the agent answers in one turn, and replies sent back out through the same tools. Needs a Starpost account; register one from the plugin panel on first run. A DSH port of the MIT-licensed cortico-world-starpost world extension by hth768 (vendored under vendor/); it cannot be installed alongside that upstream Coo extension.
dsh-readprune
songrui111/dsh-readprune
Saves tokens in DeepSeek Harness sessions by reading any file by line range or symbol mention instead of whole, and by bounding oversized tool results while keeping a recovery path. Pruning happens at the source, not after content reaches the context. Measured 43.9% fewer prompt tokens in a modelled 30-step session.
dsh-web-terminal
fightingfirefox/dsh-web-terminal
Claude-styled terminal panel for the DSH web GUI: agent shell commands run in a persistent real PTY with a genuine prompt, echo and exit codes, auto-open in the right sidebar and are scoped per conversation; optional live_terminal_* tools for reading, searching and screenshotting. Fork of Lancang-hzau/dsh-live-terminal (MIT); it shares its live_terminal_* tools and right-sidebar panel, so do not install it together with the upstream plugin in the same profile.
dsh-compaction-sticky-window
a574676848/dsh-compaction-sticky-window
Replaces the summarizing context compactor with a handoff note the model writes itself and a fresh window that keeps only the system prompt, the note, and the current turn.
dsh-prompt-boost
jianhangly/dsh-prompt-boost
Prompt enhancement for the DSH Web GUI composer: pick a style before generating (logic-only, structured, or concise), or supply or clear a custom system prompt in settings; a sparkle button or Shift+Tab rewrites the current draft through the harness model, streams the result into an inline preview (original vs enhanced) with a live thinking timer, fills it back with one click, keeps an undo bar, and offers settings for model route, temperature, length limits, context awareness, undo-bar behavior and shortcuts.
dsh-claude-desktop
dobo233/dsh-claude-desktop
Drives the Claude desktop app from DSH over its claude:// deep links: open a Claude Code session with a prompt and folders, a Cowork task with files, or push a CLI session id back into the app. Also presses Ctrl+Enter for you (SendKeys) and reads the reply back from the local Claude Code transcripts under ~/.claude/projects/<cwd-slug>/<session>.jsonl — seven tools: desktop_send, desktop_continue, desktop_open, desktop_sessions, desktop_read, desktop_wait, desktop_probe.
dsh-frontline
menghuanshiguang/dsh-frontline
One prompt row carrying two independently switchable halves. Identity: a fixed self-reference restated at the head, at the tail after every other section, and in the runtime snapshot, with an instruction to treat contradicting claims as stale cache. Discipline: ten rules, each paired with the condition a reviewer checks — external evidence before claiming done, change face equal to review face, correctness from named call points rather than timing, one source of truth, extension through the registered seam, runtime validation only at real boundaries, loud failure instead of silent skips, orthogonal outcomes reported separately, tests through the delivered entry point, and answer shape (conclusion first, length set by the change).
dsh-prompt-optimizer
qwh15622336051/dsh-prompt-optimizer
Rewrites the composer draft into a precise prompt with a configurable model and a fully editable rewriting instruction; reads the content behind @file, @folder and @session references for context and keeps the reference chips intact; offers a one-click undo that restores the text you wrote yourself, and places the button in either composer toolbar with an adjustable colour and size.
dsh-second-brain
diaryofuranus/dsh-second-brain
DeepSeek Harness (DSH) plugin: injects a bounded, timestamped snapshot of your local Second Brain (identity + state fingerprint + pointers) into every new session's prompt. Read-only, zero-write, fail-loud, zero dependencies. 第二大脑载入器:让每个新会话开局自带记忆快照。
dsh-memory-local
lishuangxi1412/dsh-memory-local
Local-only cross-session memory for DSH with tools, system-prompt injection, and a Settings page.
dsh-jujutsu
viztor/dsh-jujutsu
Refuses Git inside a Jujutsu workspace and hands the model the jj command instead. Eleven jj tools, prompt teaching, and a jj-hunk bridge for the DeepSeek Harness.
dsh-cursor
lnuxe/dsh-cursor
Cursor system prompt reverse-engineered from Cursor.app, exposed as a selectable 'cursor' agent preset for DeepSeek Harness.
dsh-agent-bench
songrui111/dsh-agent-bench
Runs a fixed set of agent benchmark cases in isolated sandboxes, scores each case with deterministic assertions, and diffs two runs to show which cases regressed after a model, prompt or DSH upgrade.
dsh-semantic-drift
yubickari/dsh-semantic-drift
One versioned vocabulary of a project's business concepts, a read-only drift scan, and the same naming rules in every agent prompt.
dsh-tab-complete
dingchenhui0618-arch/dsh-tab-complete
The composer predicts what you are about to type. Inline ghost text sits on the caret, measured against the editor's own font and line box, and Tab turns it into real text (Esc ignores it). The prediction is one short call through the session's own model router, seeded with your draft and the last few turns of the conversation, so an empty composer also gets a next-prompt guess written in the user's voice; suggestions that merely restate the assistant are dropped. Host side is one HTTP route with sub-path endpoints (loopback-only, 64 KB body cap, 2-minute result cache, 20-second miss cache, one in-flight call per session); client side is one 0-height overlay registered on conversation.input.overlay, with insertion guarded by the composer's draftRev CAS and a setDraft fallback. IME composition and slash commands are skipped. 16 node:test cases, zero runtime dependencies, real screenshots in docs/.
dsh-plan-act-models
cynthiayx/dsh-plan-act-models
A mode dropdown in the composer that switches models through the host's own session.selectModel — Plan, Act and any number of user-defined modes, each with its own provider, model, reasoning effort and optional instruction that joins the system prompt while that mode is active — plus a soft switch into Plan mode and a forced switch to Act when a plan is approved, with per-workspace overrides for Plan and Act.
dsh-draft-optimizer
xiong356/dsh-draft-optimizer
Adds a ✦ button below the DSH composer — and on the new-conversation screen — that rewrites the current draft into a more complete prompt with a single call to the configured default model, keeping the original intent and language, and replaces the draft in place without sending it.
dsh-prompt-polish
ctx666666/dsh-prompt-polish
Polish button in the composer that rewrites the draft with the model the current conversation already uses: four styles, a fidelity guard that keeps every concrete fact verbatim, one-click revert, and no API key of its own.
dsh-prompt-lint
lin-f1sh/dsh-prompt-lint
Reads your past DSH conversations and surfaces recurring prompt gaps — missing paths or versions, an unstated output format, missing preconditions that break tool calls — each with a paste-ready rewrite. Adds a one-click rewrite next to the composer that applies those constraints to the draft in a shorter form.
dsh-long-term-memory
yang-yin734/dsh-long-term-memory
A long-term memory box for DeepSeek Harness settings: type it once and every new session carries it. 0.3.0 can also expand a rough note into a five-section requirement sheet that keeps every requirement of yours verbatim, marks anything the model had to invent as 推断 and deletable, and lists the dimensions you left open instead of deciding them for you.
dsh-chat-settings
fallnstrelitzia/dsh-chat-settings
Per-conversation system prompt, turn-based context folding, sampling overrides and a low-token pure chat mode for DeepSeek Harness.