Plugins

A mid-run steer input for DeepSeek Harness Web: while the agent works, an input bar appears above the composer to inject modification requests into the next decision via agent.steer(), without stopping the conversation. Drafts persist per session, unread injected messages can be recalled from the bubble, and an optional guiding prefix is supported.

Edit a sent message to rewind and branch the conversation from that turn, switch versions with a counter under the bubble, and browse every branch in a turn-level version tree.

VSCode-style editing experience for DeepSeek Harness: a Monaco-based central file editor (tabs, Ctrl+P quick open, status bar) and interactive diff review of agent edit/write results with per-change Keep/Undo, rollback and archiving, persisted across restarts.

Bridge Claude Code's .claude/ directories into DSH with zero migration: project and user-level skills, commands, rules (one system-reminder envelope), agent files, hooks (PreToolUse/PostToolUse/UserPromptSubmit/ SessionStart/SessionEnd) and .mcp.json servers, plus Claude Code plugin marketplaces. Ships /cc-plugin for full plugin/marketplace management (claude CLI first, self-implemented fallback), /cc-resume to list and import Claude Code sessions into DSH as native event-sourced logs, and /cc-export to write DSH skills back as Claude Code skills. Two-way Claude Code <-> DSH bridge, versioned and released as dsh-claude-compat.

Self-built DSH memory plugin: SQLite persistent storage + database-level audit guard (enforceAudit) + audit log. Auto-captures knowledge after conversations, agents recall via memory_recall, supports Claude Code/Codex/Cursor multi-agent sharing. Zero external dependencies.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Adds a configurable vision model to text-only main models: a vision_read_image tool, a composer-bar vision-model selector, and automatic image-to-text conversion for text-only routes.

Runtime-switchable model output styles with Claude Code outputStyles parity, plus the output.render.* presentation protocol: a /style command, per-session persistence, systemPrompt injection, six built-in styles, a web picker, and a renderer registry with per-session/per-tool rules and /export.

Font switcher for the DSH Web GUI: 99 UI fonts and 31 code fonts with CJK-Latin pairing stacks, instant apply and localStorage persistence.

Font switcher for the DSH Web GUI: 99 UI fonts and 31 code fonts with CJK-Latin pairing stacks, instant apply and localStorage persistence.

DeepSeek Harness plugin that turns Jev judgments into three automatic actions — pruning oversized tool output to the segments relevant to the request, screening fetched pages for instructions aimed at the model, and picking which skill fits the next step — plus the jev_ask and jev_gate tools, a judgment ledger that survives restarts, and a /jev-status report. Needs a TypeSafe API key; without one it is inert and sends nothing.

Auto-expands newly arrived tool-call cards in the DSH Web UI, with a sidebar toggle cycling no-op/expand/collapse and the state persisted to localStorage.

A better fold bar: automatically folds tool calls and Think segments into step fold bars, and collapses each finished turn into a single turn header with live metrics (duration, TTFT, token, tok/s, cache hit) — only the final summary stays visible; customizable leading icons with animated poker cards built in (suit-cycling card animation while running, a deck when collapsed, a fan when expanded), a settings row for the official fold mode, compatible with both new and old DSH versions. Zero intrusion into DSH source.

Local-first four-bucket Token observability: persistent session/provider/model/day dashboards, trends, budget and anomaly signals, public-rate estimates, safe aggregate exports, and explicit opt-in usage or session-trajectory analysis.

Session-bound persistent TypeScript REPL for DSH PTC mode: bindings and imports stay live across run_code calls, edit_run_code replaces one line without resending the block, module import/export syntax is adapted via AST rewriting, and durable bindings are restored from the session journal after a cold restart.

Provider-independent DSH document parsing powered by MinerU, with native background jobs, immutable results, and safe request coalescing.

Content-aware tool-result reducer: 13 reducers cut oversized output by meaning at tools/post-execute (failing tests kept, diff context dropped, JSON and CSV sampled, lint problems grouped by rule, dependency stack frames collapsed, crowded directories counted), with full originals spilled to disk behind a locator.

Self-evolution: the agent hot-mounts/removes persistent plugins on itself mid-session.

Role-based multi-agent team for DeepSeek Harness. The /team command assembles up to 12 specialist subagents (product, architect, researcher, UI, backend, frontend, database, security, reviewer, QA, DevOps, docs) and runs a nine-phase gated pipeline (clarify, research, design, spec review, plan approval, implement, review, test, deliver) over a shared workspace of artifacts (SPEC, PLAN, TASKS, STATE, REVIEW, TEST). Quality gates are enforced by plugin code rather than requested in prompts: an unfinished task cannot be marked completed, quality findings must be adjudicated by the reviewer or QA role, and coverage gaps or rework over budget appear live in the overlay and in /team status. Ships a live team overlay (phases, roster with per-role models, task DAG, artifact preview, decision buttons), a persistent-team mode that resumes across sessions, and per-run token and time accounting. Zero runtime dependencies, no build step.

Per-conversation persona / master prompt plugin: create, edit, switch and delete persona templates from the composer toolbar, with highest-priority system-prompt injection, fixed interaction guardrails, subagent inheritance, new-conversation default, and local JSON persistence.

One-level session folders for the web sidebar - group sessions per workspace, move them by drag-and-drop or context menu, archive and restore, server-side persistence.

Local PDF, Office, image, and OCR document intelligence for DeepSeek Harness.

Two-way WeChat (iLink) bridge: turn-end and approval-request push, in-chat approve/reject and message injection, persistent dedup and convergent long-reply chunking; channel layer extensible to other IMs.

Skills for building websites on the Creght platform: CLI pull/push sync, page and component conventions, CMS, forms, auth, SEO, publishing and version rollback.