Plugins

Redacts PII in tool-result text before it is logged (error-result metadata is not rewritten), denies read_image and binary/document reads outside allowPaths, provides local privacy_extract, privacy_ocr, privacy_scan and privacy_rehydrate tools (PDF/OCR needs a separately installed local extractor configured through extractCli), and enforces a fail-closed llm/stream egress guard before DSH dispatches any model request.

Domain-routed proxy for DSH fetch traffic: hosts on a force-proxy list always go through the proxy, every other host tries direct first and fails over to the proxy within a second, the first channel to answer is pinned for the session, connections are reused for 120 seconds, and each attempt is logged. Can also route pnpm/git subprocesses used by plugin installs.

Look up Chinese companies inside the conversation: name a company and get its business registration, shareholders, executives, outbound investments and registration changes, plus judicial and operating-risk records such as enforcement, dishonest judgment debtor, consumption restriction, abnormal operation, serious illegality and administrative penalties (11 dimension groups). Results render as conversation cards with fields and the raw payload on expand, and the API key is saved from the plugin page into the Harness credential store.

DIY workflow builder for DSH - compose multi-step prompt workflows with self-check gating, engine-enforced jump rules, agent-driven execution and a live run panel.

Git workflow studio for DeepSeek Harness: pick a branch model, enforce Conventional Commits, review PRs by defect density, rewrite history safely, rescue lost commits with reflog, and version releases by actual behavior change.

One chip in the composer dock: the account balance plus what the current chat has cost, priced per turn at the tariff in force when each turn ran. Clicking it opens a 264px card in the panel style of the host, with refresh and settings buttons.

Mechanism-enforced discipline layer for DeepSeek Harness agent teams: role cards, quorum termination, evidence-gated reports and cost budgets.

Standalone QQ-bot extension pack for DeepSeek Harness — fully independent, no other plugin required. Two-layer SQLite memory with hippocampal recall, a persona that keeps learning from daily chats, group tiers, local-model quick replies with a single-brain arbiter, TTS outbox, sticker library, an approval-gated video studio, and a four-form desktop pet (three custom characters plus the stock fish) playable over a public invite link with access-code login, single seat and brute-force protection. Chat bridging is deny-by-default: c2c/group access defaults to a care mode that only responds to the special-cared people and groups of the owner (shared with the persona system, zero extra config); allowlist, open and disabled modes remain available. Requires QQBOT_APPID and QQBOT_SECRET, and Node.js 22.5 or newer.

An x_archive tool that turns an X (Twitter) post link into a permanent Markdown snapshot via the 2100laike archive service: images are re-hosted so they never break, snapshots survive post deletion, resubmits dedup-hit and return the latest version without spending quota, and refresh forces a refetch with a PAT. Needs the third-party 2100laike service; anonymous use is limited to 8 archives per day per plugin instance and a registered PAT raises that to 100 per day.

Writes short plain-Chinese notes for installed dshmarket plugins that have none and shows them on the market cards; hand-written notes are left alone (only entries marked 🤖 may be regenerated with force=ai), and dshmarket is required.

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.

Tag-based skill filtering: attach tags to DSH skills, then hand each workspace or conversation only the subset its boolean tag expression selects (for example `pdf + docx` or `aegis * plugin`). Excluded skills are deny-shadowed out of the model catalog rather than merely hidden in the settings UI; skills outside the expression can still be added by hand or force-disabled, and the bundled `tagging-skills` teaches the agent to derive a tag set from the machine it is running on.

Decodo Web Data API as the fetch provider behind the built-in web_fetch tool: returns Markdown by default, pins fetchProvider to decodo, and enforces a configurable per-process fetch cap. Requires a Decodo API key; web_search is unchanged.

Per-workspace closet for temporary scripts and their run logs, kept in a .dsh-fix directory inside each project. Registers a script with its language and purpose, scans a project for leftover scratch scripts, backups and log files, runs registered scripts with a timeout and writes each run to a timestamped log, and sweeps chosen files into a reversible trash with per-batch restore. Scanning only lists and never deletes; cleanup moves files instead of deleting them; files already tracked by git are refused unless forced. Ships 7 agent tools and a settings panel.

Force-hides archived sessions from the DSH sidebar whatever the view filter is set to, and adds a panel that restores them or deletes them permanently - session log directory, archive and pin records, and projection cache.

Adds Restart App and Host, Reload Page and Force Quit items to the Windows system tray of the official DSH desktop app by patching app.asar in place, and re-applies that patch after each desktop update.

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.

Deterministic network egress gate: web fetches and searches are checked against a destination allowlist in tools/pre-execute and denied before they run; shell fetch-verbs are observed (enforcement opt-in).

Adversarial review gate for tool calls. It hooks `tools/pre-execute`: a local regex pass over destructive commands (`rm -rf`, `git push --force`, `git reset --hard`, `DROP TABLE`, `format`, disk writes) and sensitive paths (`.env`, `id_rsa`, `.ssh`, `.git/`, `$DSH_HOME`) runs first with no latency, and only a hit is escalated to one review-model call that returns allow or deny. Plain reads and ordinary writes never enter that path, so everyday work pays no added delay. Every verdict is shown live in the Web GUI.

Forces ASD-STE100 Simplified Technical English on every reply and every document. Commands: /asd100 on, /asd100 off, /asd100.

Week-keyed personal memo service: stores entries in ISO-week tables, resolves week/month/quarter/year navigation from one period calendar, archives quarters, runs AI analysis and Markdown report export, summarizes archived DSH sessions into the week as one entry per session in the language and at the length the reader picks, requires an explicit force flag to edit a past week, and turns one suite-wide telemetry failure analysis into a GitHub issue report.

Select a passage in a DSH conversation and read a plain-language explanation in a floating panel, which carries the surrounding message as the context. Three explanation depths (plain / general / pro) that re-explain on the spot when switched; optional web search and local file lookup (the model decides by default, and a button can force one lookup that reports only what is new); follow-up questions; and a button that hands the whole exchange to a new session in standby mode - the background is queued without waking the model or spending tokens. Settings live on the host in settings.json, and nothing is written until you press save. The repository also ships an OpenAI-compatible endpoint and a browser extension (source).

Reload a plugin or skill you just installed without restarting DSH. reload_plugin clears that plugin's own module cache, unloads the old instance and re-imports it, restoring the previous module if the new code throws; reload_skill forces skill directories to be re-discovered. Ships both as tools and as the /reload-plugin and /reload-skill commands.

Harness-neutral Traditional Chinese enforcer + offline converter (skill, DSH bundle, CLI). One script axis either way + Cantonese/Japanese-only filters. Converts both ways; optional wording preference. Also: an LLM output guard, cp950/GBK console scan.