Plugins
Browse, filter, and install DeepSeek-Harness plugins.
320 plugins found
dsh-adaptive
dingchenhui0618-arch/dsh-adaptive
Version-adaptive tooling for DeepSeek Harness: it reads the running DSH version from the plugin manager, mirrors app-boot plugin-compatibility rules (engines.dsh first, then @deepseek-ai/dsh* peers, prerelease-inclusive comparison, exact-version exemptions) to score every installed plugin, and statically flags source still using APIs renamed or deprecated between v0.1.6 and v0.2.1. Ships a conversation-view panel, an agent tool and HTTP state/scan/report routes. Read-only, offline.
dsh-memory-library
wafernm-crypto/dsh-memory-library
Per-workspace memory library with manual per-chat opt-in, editable rules, three sharing modes, and continuous forgetting; cards stay readable Markdown.
dsh-dialog-fence
ilovehaku/dsh-dialog-fence
Per-conversation behavioral rule fence for DeepSeek Harness: rules live in one JSON file, are edited from a Settings page or the conversation panel, and every rule carries its own on/off switch so a single rule can be muted without deleting it (muted rules are skipped at injection and the remaining numbering stays contiguous); any number of conversations can also be excluded as a whole so they receive no fence at all, and picking conversations never touches the rules themselves; the enabled rules are injected as one runtime-context section at a fixed order so the system prompt prefix stays stable.
dsh-project-supervisor
midnight-1991/dsh-project-supervisor
Beta: a project supervisor for DeepSeek Harness — standing rules plus a Web panel (three switches, dispatch modes) that splits a goal into parallel teammate dialogs, checks engineering baselines, interviews new-project requirements and protects beginners. The standing rules come from the repo kit installer, an optional separate step.
paper-format-check
stephen-pc/paper-format-check
Format checker for theses and lab reports: verifies body font size, first-line indent, line spacing, Chinese font, header student ID and name, page margins, and figure/table caption numbering against a JSON rules preset, then reports each problem with its paragraph location and the concrete fix. Read-only, zero dependencies (Python standard library only), and it refuses to report a pass when no check actually ran. Requires Python 3.8 or newer on PATH.
dsh-annals
duhuashan/dsh-annals
Memory that outlives the session, kept as plain daily log files: one markdown file per day plus a generated index the agent greps instead of re-reading. Registers the annals skill, injects the write-it-down rules into the system prompt, and exposes three tools — annals_init builds the log directory, the index generator and a separate Git repository in one call; annals_query full-text searches past entries and returns them with file and line anchors; annals_links resolves which entry cites which. Reminds the agent once per turn when it changed files but wrote no log that day, and once more when the log was updated but the index was not. Adds a settings page for the six switches.
dsh-reflect
caimc21069065-prog/dsh-reflect
Turns corrections into permanent rules: explicit remember: triggers and auto-detected corrections pass a confirm bar (save globally / per project / edit / skip) and are written into a marked AGENTS.md section. New rules take effect in the current session and load natively in future ones; writes are deduplicated and version-guarded, and secret-looking content is refused.
dsh-qq-voice
hzh5021/dsh-qq-voice
Mounts a per-channel speaking-rules file into the QQ preset's system prompt only, so that channel answers in one or two lines while every other channel stays untouched. Does nothing until home points at a folder with the rules file (default QQ线口径.md); meant for the QQ preset, not the global plugin list.
dsh-daoyi-yijing
wangxuewangxue98/dsh-daoyi-yijing
Yijing-based decision review plugin for DSH: six-layer weighted aggregation engine (384 yao to taiji) with strong-association veto rules, pure JS with zero solver dependencies. Free tier is capped at 9 runs per day and activation codes raise it; the stock-trend scenario pulls live quotes from Tencent for the stock codes in the request.
mydsh-auto-model-router
apinggithub/mydsh-auto-model-router
Hybrid model router for DeepSeek Harness: declarative rules, user-configurable cost control (cost-first / quality-first / balanced), optional LLM task classifier, and failure fallback chains.
dsh-line-pool (dsh-line-pool)
why-147369/dsh-line-pool
Outbound route pool for DeepSeek Harness. Ships 15 seed routes plus a 20-entry candidate pool covering 7 target kinds (GitHub raw/codeload/main, npm registry, PyPI index, HuggingFace, general). Routes are verified before use: upstream IP lists go through a TLS handshake with full certificate-chain validation (a bare TCP check can be answered locally and report dead IPs as healthy), and failures advance a cooldown ladder of 2/5/15 minutes with the fastest healthy route picked per target kind. Routes are applied by rewriting the URL with one of four rules (prefix, registry, index, host-replace), reaching git, pip, npm, pnpm, gh, curl and wget through three paths: the shell seam (download commands the model runs through the bash tool are intercepted and rewritten automatically; commands wrapped by the pwsh tool, and fetches made by the host itself or the renderer, are not covered), two registered tools the model can call directly (line_pool_status, line_pool_run), and child-process spawn. Multi-line commands keep their line breaks and only the download segment is touched. URLs carrying credentials (user:token@host) are never rewritten, so tokens are not forwarded to third-party mirrors. No global config is modified. A sidebar panel lists every route with latency, failure reason and cooldown countdown, supports per-route retest and enable/disable, and shows live TUN/proxy status from network-adapter and loopback port checks. The candidate pool is re-verified every 24 hours so newly usable routes are added and dead ones dropped. 570 tests, 87% line coverage.
dsh-milestone-guard
xt765/dsh-milestone-guard
Milestone progress soft-enforcement guard: injects persistent system-prompt rules and post-execute notices when tool calls omit visible progress text, with a Web settings form.
harness-review (dsh-harness-review)
rpegorov/harness-review
Skill that reviews your coding-agent session transcripts (Claude Code and Codex only; DSH's own transcripts are not supported) over the last two weeks and reports which skills, hooks and rules work, need attention or go unused. Requires Python 3.
dsh-humanize
lry722/dsh-humanize
Prose review for human-facing writes. The write and edit tools require a human_facing flag; the plugin reviews the text against layered PROSE.md rules in the background, stages annotations, reconciles them against the full file, and merges them through /humanize, /humanize-loop or post-compaction while the main session keeps working. /humanize-review runs a batch over git-tracked files on demand.
dsh-dotclaude
rui-debug769/dsh-dotclaude
Runs a Claude Code project's .claude/ slash commands and permissions.deny rules inside DeepSeek Harness. Command bodies expand $ARGUMENTS, positional arguments and @file references into the agent's next turn; matching tool calls are denied before they run. Every host service is probed, so a host without a command registry, working-directory service or TUI status line degrades one feature instead of failing the boot.
dsh-open-with
hildebrandyu/dsh-open-with
Gives DSH its own per-extension "open with" map: delivery cards, the sidebar preview and change review launch the app you pick, while macOS keeps its own default for Finder double-click. Rules are edited in a Settings tab and stored in ~/.dsh/open-with.json; "show file location" still reveals in Finder.
dsh-lesson-loop
jayyuen666/dsh-lesson-loop
Turns guard denials, gate failures, abnormal resumptions and human negative feedback into per-project lessons, merges reports into candidate rule cards, and injects only the rules a human has armed into each new root session of that project; it registers no model tools, and a machine never promotes a rule.
dsh-zh-ui
1186258278/dsh-zh-ui
Chinese frontend UI design spec for dsh: injects the zh-ui-design skill and prompt rules (section-name headings, no filler copy, one signature element), plus a 10-rule UI copy/style linter.
dsh-chess-game (chess-float)
x-cores/dsh-chess-game
Two-player chess in a draggable floating window with full rules, undo and PGN export.
dsh-ai-arcade
439436269-ctrl/dsh-ai-arcade
Two games inside DeepSeek Harness where the model supplies intent and a local engine owns the rules: a twin-brain snake that periodically draws a strategy card, and Chinese chess where the model only comments on a move picked from locally generated legal candidates. Both keep running when the model is slow, offline or out of quota.
dsh-pr-gate
zhengqiuyang/dsh-pr-gate
Deterministic write gate: scope policy denies out-of-scope write/edit calls before they touch the disk, residue rules scan the written text, and every decision lands in a content-hashed JSONL ledger; can reuse the repo's agent-pr-gate.yaml so CI and session enforce one policy.
cloakpack (dsh-cloak)
zhangmiao03/cloakpack
Context firewall for DeepSeek Harness: credentials in successful plain-text tool results become opaque ⟦cloak:category:n⟧ placeholders before they reach the model, with originals kept only in a process-memory, agent-scoped vault. 36 built-in signature families (shared with the cloakpack git pre-push guard), key-name rules for unknown formats, custom regex rules, dry-run mode, an audit log, and the /cloak command.
dsh-deepseek-billing-period
zi7tian/dsh-deepseek-billing-period
DeepSeek API billing-period chip in the composer dock: shows whether the current time is peak or off-peak with a countdown to the next rate switch, opens the peak/off-peak window rules on click, and during peak hours intercepts sending to ask for confirmation first.
dsh-Alist-
r-roker315/dsh-alist-
AList v3 file management: browse, search, upload (streamed and multipart), offline downloads, archive listing, task polling and control, plus admin tools for storages, users, roles, meta rules, settings, search index, shares and labels - 75 tools in total; every write goes through the approval flow and passwords are never read back.