Best DSH Code Search & Intel Plugins

Local-first code knowledge graph for coding agents: 10 MCP tools for layered context compression, DAG planning, incremental AST indexing, a cross-session skill flywheel, diagnostics, and graph artifact import/export.

Connect ChatGPT OAuth and OpenAI Codex models to DeepSeek Harness, with opt-in search and image tools.

Use your ChatGPT / Codex subscription with DeepSeek Harness via OAuth, with model access, usage quotas, search, and image generation — no API key or Codex CLI required.

Use ChatGPT (Codex), Claude, and Grok subscriptions as DeepSeek Harness LLM providers, with Settings login, model catalogs, usage, plus image_generate, video_generate, and x_search tools.

Compact Codex coding mode for DSH: light prompt guardrails against GPT over-explaining, with an editable prompt and native Codex-style tools.

LSP action surface for DeepSeek Harness: diagnostics, formatting, completion, code actions, symbols, signature help, inlay hints, and rename tools over language servers

Claude Code /rewind for DeepSeek Harness: git-first workspace snapshots before every mutating tool execution, turn-boundary session forks, and a one-shot /rewind command that restores files and forks the session back to a checkpoint.

AI4Scholar academic search: 38 tools over Semantic Scholar, PubMed, Google Scholar, arXiv, bioRxiv/medRxiv, and DOI resolution (search, citation graph, authors, recommendations, PDF full text in slices, auto-cite, scientific figures), a unified cross-platform search with de-duplication, an API-key card in Settings, and per-call credit accounting with an `/ai4scholar` balance card.

Live skill provider that adds skills from 60+ other agents' directories (Claude Code, Codex, Cursor, Gemini CLI, Copilot), Claude Code plugin marketplaces, and any git repository of skills to the dsh catalog without copying or symlinking; deduplicates, repairs frontmatter, renames name collisions, and ships a CLI (list, add, sync, doctor).

Agent preset for DeepSeek Harness that layers the self-referential Cordis toolset (dynamic plugins, runtime inspection) and preset-authoring skills onto the PTC Code-Mode preset; materialized files carry per-file sha256 markers, so user-edited presets are never overwritten on upgrade or uninstall.

Deep-read books and articles in five modes (quick, deep, knowledge map, Feynman, full book) with claim-evidence-data reports, Mermaid/XMind mindmaps, batch comparison, budget preflight, transparent background-job progress, and MD/HTML exports from URLs, files, or pasted text.

DSH Desktop enhancement plugin: it puts verifiable facts on the table. Constraints are injected only when relevant, so idle chat costs no extra tokens; injection is layered (session-stable text in the system prompt, volatile content as a tail snapshot) and the prompt cache stays valid. Discipline: each turn is classified (question / research / discussion / diagnosis / execution) with boundaries enforced - no file edits on question turns, no unsolicited fixes on diagnosis turns; citing code lines not opened this session, negative claims about unseen symbols, requirements that do not match the deliverable, and dressing up “I did not check” as “waiting for your decision” are all called out; replies are written for humans - a code, field name or id must be explained in plain words the first time it appears. Memory and knowledge: 75%/90% context warnings plus an exported session recap (say "continue" in a new session); project knowledge accumulated across sessions by working directory, auto-captured and deletable by id. Inspectable artifacts: task contract / change record (auto-logged, unverified items flagged at delivery) / hypothesis record (conclusions must pass an evidence gate) / design decisions. Dashboard and personas: routing, trigger hits and block assembly are written to lume-metrics.jsonl and queryable via lume_metrics; personas are distilled from chat logs, novels, scripts or character sheets, with long-term and temporary memory, a memory star map and persona card export/import.

Ten video tools (probe/cut/concat/encode/subtitle/extract/gif/frames/adjust/health) on the official subprocess service: probe summaries, batch frame extraction, speed/volume/mute/rotate adjust, shell-free argv, zero runtime dependencies.

Embedded C/C++ AI engineering plugin — firmware skills (FreeRTOS, Keil, HardFault, state machines) + 1% Rule / Plan Verification Gate discipline | 嵌入式 C/C++ 工程 AI 插件:固件技能与 agent 纪律。 For Claude Code, Codex, Cursor, Kimi, OpenCode, ZCode and DeepSeek Harness (dsh)

OpenCode Go subscription models as a DeepSeek Harness provider: re-resolves the live gateway catalog every few minutes, auto-adapts models the built-in table has not seen, and covers streaming, tool calls, image input and subscription usage. A maintained fork of dsh-opencode-go: a clash with the upstream package over the llm-opencode-go settings namespace makes it withdraw quietly instead of failing the whole plugin tree, and an already-claimed opencode-go route makes it serve on opencode-go-plus.

Structural code index for DSH: Tree-sitter symbol search across 8 languages (including C/C++), a bounded repository map ranked by import-graph PageRank and injected into the system prompt, function-level call graph via code_refs, optional circular-dependency and orphan-module checks via code_health, plus working-tree change context and task-aware code context.

File encoding guard: byte-exact read/write/edit for GBK, Big5, Shift-JIS, EUC-KR, Windows-125x, UTF-16 and UTF-32 files, so editing a legacy file leaves it in its original encoding instead of silently rewriting it as UTF-8; UTF-8 BOM preserved exactly as it was, line endings (CRLF/LF/CR) kept, characters the encoding cannot represent refused rather than written as "?", and non-UTF-8 files listed with candidate encodings so the model can re-read them explicitly.

Provides an OAuth account page for DSH Web, currently supporting OpenAI Codex, GitHub Copilot, Anthropic, Kimi For Coding, OpenRouter, and xAI.

Use your ChatGPT/Codex subscriptions in DSH, with image generation and web search support.

Windows-only computer use for DeepSeek Harness: captures the virtual screen and drives mouse & keyboard through 9 tools built on PowerShell and Win32 SendInput; pairs with picturereader so text-only models can complete the screenshot-analyze-act-verify loop fully locally.

Batch-port official Codex plugins into DSH skills (codex_list/port/status/health; measured: 186 plugins / 583 skills, 577 ported, 0 failures).

A lightweight, general-purpose attachment Dock for DSH: paste, drop, or choose images, PDFs, documents, archives, code, and other files, review and manage them before sending, then pass them to the Agent as local paths. It gives non-image files a consistent attachment entry point.

Manages multiple Jenkins servers and triggers jobs from a Settings page, model tools, or a per-workspace "Run Jenkins Job" entry, with a bilingual host + browser UI.

Wraps colbymchenry/codegraph into agent tools - status, search, callers/callees, impact, explore, and more.

Connect Google Antigravity Code Assist OAuth accounts to DeepSeek Harness for Gemini and Claude streaming LLM routing and Nano Banana 2 image generation.

Two-way Codex↔DSH bridge: skills from ~/.codex/skills, session import with workspace attach, live MCP mirroring of mcp_servers, and a Codex-side reverse MCP installer.

Desktop computer-use for DSH: captures the Windows screen into the agent vision channel and drives mouse/keyboard through a Codex-style overlay with Esc abort; auto-detects Windows native or WSL hosts.

Shows which graft index a dsh session is serving and whether it still matches the code, and gives the model graft_ask, graft_grep, graft_callers, graft_skeleton and graft_map as native tools.

Search AIGC Radar's curated GitHub AI project library (500-star admission, bilingual zh/en tags, star-growth snapshots) over its MCP endpoint with native result cards; an agent/pre-step listener proactively suggests a reuse check before the agent writes code.

Code management panel for the DSH web UI that handles everyday Git in five steps: ① env check auto-detects git/gh/ssh and one-click installs missing tools (gh mirror download sources speed up installs, Windows included) with check-update; ② SSH ed25519 key generation / connection tests plus one-click 443 config to bypass blocked port 22, with the Gitee personal token configured here; ③ repo status, side-by-side diffs, stage/commit, branch switching, history with revert/cherry-pick, one-click repo creation and push, auto-ignoring >100MB files; ④ lists all repos of your account for one-click clone; ⑤ five-step npm publish wizard. GitHub / Gitee dual-platform, with the UI switching between 中文 and English live.

Task-scoped git worktrees for DSH: durable per-repo manifest, worktree mode injects a creation instruction with your first message under an automatic worktree/ branch prefix, header badge instead of workspace clutter, and bring-back or force-remove cleanup.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.

A minimal phone remote control for DeepSeek Harness: the phone page carries only the instruction you send and the AI's final conclusion, while tool calls, file access, sub-agent dispatch, and reasoning traces stay on the computer, reachable over LAN, Tailscale, or a Cloudflare tunnel with a QR code, link, and password for each route.

Patch-style file editing: one apply_patch tool accepting git/unified diff (default) and Codex apply_patch syntax (opt-in), applying every change all-or-nothing after a full read-only verification pass, with sandbox-aware delete and move and a dry-run mode.

Deterministic AST code graph and architecture intelligence tool for call hierarchies, blast radius, circular dependencies, domain slices, and full-stack API contracts.

Harness-kernel mesh for DeepSeek Harness: kimi/grok/codex/minimax model routes (L1), distilled subagent recipes (L2) and kernel_run/kernel_status/kernel_switch tools.

LSP action surface for DeepSeek Harness providing diagnostics, formatting, rename, code actions, and symbols over real language servers.

DSH environment management: auto-installs a Rust/Tauri desktop host (downloaded per-OS from dsh-desktop-host releases, source build as fallback), one-click runtime updates, Windows platform compatibility, official DeepSeek billing, and a built-in code editor for the workspace.

Fetches up-to-date, version-pinned library documentation and code examples from context7.com for DSH agents via context7_search and context7_get_docs tools.

Renders mermaid fences in dsh web chat as SVG diagrams by default, with cursor-anchored smooth zoom and pan, a per-fence diagram/code toggle persisted in localStorage, dark-mode follow, and a bundled offline engine.

Usage statistics dashboard for the DSH Web UI: info cards, a 280-day GitHub-style activity heatmap, daily token trend, and model-usage donut chart.

Codex-backed `web_search`, `image_gen`, and `image_vision` tools for DeepSeek Harness, reusing ChatGPT OAuth login state.

Playwright MCP browser control for AI agents: drive a real, visible Chrome (navigate/click/type/snapshot + ~80 browser_* tools), with a live screenshot panel embedded in the GUI that refreshes after every action.

A CodeGraph tool scoped to the session's own indexed project, resolved from its workspace directory. One MCP server is launched through npx per project root and shared by every session working there; a project indexed mid-session is enabled without a restart, and the managed child process is reaped when the harness exits.

Project/task dual-mode workspaces for DSH: a task skips the workspace picker and gets a fresh scratch directory (D:\dsh_working\<name>-<timestamp>) per conversation, Codex-style; no-workspace sessions are grouped under a persistent Tasks section in the sidebar with empty states, and the new-session workspace picker gains a "no workspace (task)" option.

Official DSH plugin for nuphus-mcp (by the nuphus-mcp maintainers): desktop and browser automation (38 tools) with PaddleOCR element perception and Chrome CDP browsing, via a persistent stdio MCP child process.

External-expert consultation for DeepSeek Harness: headless Claude Code CLI with role personas (advisor/reviewer/designer, extensible), replies as reference answers — thinking effort, model fallback, panels, settings workspace. · DSH 外部专家咨询：headless 调用 Claude Code CLI，角色人设（advisor/reviewer/designer，可扩展）回复即参考答案——推理等级、模型回退、并行会诊、设置工作区。

Use a ChatGPT/Codex subscription in DeepSeek Harness with GPT models, image generation, web search, subscription quota reporting, model and feature controls, and browser or device-code OAuth sign-in.

AI interview practice for DeepSeek Harness Web: generates questions across four modes (concept review, mock interview, scenario, LeetCode Hot 100), scores answers, and provides explanations.

Delegates a self-contained coding task to the local Claude Code subscription through the official Claude Agent SDK, and adds a session tab with live output, cost and remaining quota.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

OpenCode Go balance pill at the right end of the composer tool row: rolling/weekly/monthly quota remaining straight from the Zen usage endpoint, with hover detail and warn/danger coloring.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Hosted tool server over MCP: invoice and bank-statement extraction with in-code arithmetic checks, ledger reconciliation in integer cents, PDF and table conversion, SQL dialect transpiling, and mainland-China reachability probes run from a China Mobile network vantage point.

File workbench library plugin for DSH, provide file processing capability.

Codegraph CLI as eight code-intelligence tools for DSH — symbol search, callers/callees, impact analysis, codebase exploration, symbol/file reading, index status and sync.

DSH bundle that registers 13 native codegraph_* tools wrapping the codegraph CLI, so agents bootstrap, maintain, and query a pre-indexed code knowledge graph (symbol query, explore, node trail, callers/callees, impact, affected tests) instead of grepping files.

Interactive code-reading coach for DeepSeek Harness: a five-phase guided walkthrough of the source behind a paper, starting by identifying its language and framework.

Project .pack.json/.pack.zip into .agent-pack/modpacks/ and expose skills via a workspace allow-list.

Gives an agent its own email inbox through AgentMail — eleven tools for sending, reading and labelling mail, plus inbound mail delivered into one harness session per email thread, with an approval gate and recipient allowlist on everything outbound.

AST-based structural code search and syntax outline tool for DeepSeek Harness powered by ast-grep

Elbow-proof PowerShell for DeepSeek Harness: pwsh_safe tool runs scripts via base64 -EncodedCommand, immune to quoting/escaping pain, sandbox-seam based

GLM Mode agent preset for zhipuai/glm-5.3-flash: PTC/Code Mode tool presentation, a reasoning loop guard and a tool spin guard (live-incident driven), and GLM-specific auto-compaction at 75%/22%.

Scans MCP servers configured in Claude Code, Codex and CodeBuddy and probes real connectivity via stdio and streamable-http initialize handshakes, with enable/disable toggles and a /mcp control panel.

SMS forwarding webhook for DeepSeek Harness. Phone apps (SMS Forwarder, Tasker, or any HTTP POST) push messages to a local HTTP endpoint; the plugin stores them as JSONL and exposes sms_recent / sms_search tools so the agent can read SMS verification codes during tasks. Auto-extracts the first 4-8 digit OTP from each message, supports keyword filtering, and works over LAN or Tailscale.

Static HTML auditor for Chinese line-breaking: checks explicit-`<br>` orphan lines, keep-all CSS coverage, CJK line-start/line-end punctuation rules, and protected-phrase splits, then inserts <wbr> at natural breakpoints; exposes a cn_linebreak_audit tool for agents.

Role-based plugin recommender for DSH: asks the user's role (developer, designer, writer, researcher, ops, student...), recommends suitable plugins, and audits each with a local static security scan (dangerous code patterns + 0-100 risk score) and a reputation check (npm downloads / GitHub stars).

Turn-level workspace undo for Git worktrees: every agent turn gets a private snapshot, /undo previews a red/green diff card that is confirmed in place, files changed after the turn are refused with a conflict diff unless --force or --skip-conflicts is passed, and HEAD, index, stash and commit history of the user repository are never written.

Universal Model Context Protocol (MCP) bridge for DeepSeek Harness: connects agents to stdio/sse/websocket MCP servers with a 10k dormant scale engine, sub-millisecond BM25 tool search, dynamic token budgeting, and a real-time web UI dashboard.

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

Unit conversion toolbox covering 20 categories — length, mass, temperature, area, volume (incl. US cooking units), speed, time, data sizes (decimal MB vs binary MiB), data transfer rates (Mbps vs MB/s), acceleration incl. g-force, illumination (lux / foot-candle), pressure, energy, angle, frequency, power incl. three horsepower definitions, force, torque, typography (px/pt/em/rem), and fuel economy (mpg ↔ L/100km). Two tools — convert_unit and list_units — zero runtime dependencies, pure arithmetic; each result includes the formula applied.

Code knowledge graph bridge for codebase-memory-mcp: semantic symbol search (BM25), source snippets, architecture overview with Leiden communities, call/data-flow/cross-service traces, graph-augmented grep.

Local AI code-review gate: review a workspace/branch/commit diff via the managed ocr.js, returning structured findings with token stats; gate mode fails on findings.

GitHub REST API tools + browser sidebar panel: repos, search, issues, PRs, comments, account binding (credential-store), and one-click clone-as-workspace.

Let DSH subagents call any Claude-compatible CLI, not just the SDK-bundled one. Fork of @deepseek-ai/dsh-subagent-claude-code.

Bridges a local MATLAB MCP server into DSH: evaluate MATLAB code, run .m scripts and tests, and inspect installed toolboxes via mcp__matlab__* tools. Requires MATLAB and the MathWorks MATLAB MCP Server binary, and a path edit after install — the plugin on its own registers no tools.

Manages OpenCode Zen free-tier and Go-tier models in settings.yaml — fetches the live model listings from opencode.ai, reports configured-versus-live drift per route, and adds or removes entries through four agent tools and an OpenCode Models settings section.

Codex-style Git workbench for DSH: workspace-scoped changes, diff, stage, commit, guarded branch operations, graph history, fetch, fast-forward pull, and upstream push through official plugin APIs.

Nine consolidated tools that give agents full access to the stool ops CLI: server management, database query/redis, log search/tail, CI/CD deploy and history, MFA codes, git operations, notes, todos, and misc utilities (accounting, weekly reports, audit, project listing, nginx presets).

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.

Reading archive for dsh: after reading open-source code, capture quick notes or write full deep notes that group into one card per repo / file / symbol, stored as an append-only log of Markdown notes you can open in Obsidian; query your history, browse recent reads, or search your own Obsidian vault and link related notes to a reading record. Nine tools, a /codevault command, and a code-reading skill.

Create and manage sandboxed JavaScript tools for DeepSeek Harness with a Monaco editor and model-driven tool lifecycle.

Fine grained per tool permission rules for DSH at the tools/pre-execute gate, deny and ask lists in Claude Code rule syntax (`Bash(rm -rf:*), Read(_secrets_), mcp__server__tool`), works standalone without migrating.

Bridges the LiuHe MCP code toolkit (44 tools) into dsh web: repo_map, symbol search, edit_batch with tolerant matching, transactional edits with undo journal, and deterministic quality gates — backed by a crash-isolated Rust tree-sitter parse daemon and SQLite index.

Manage frequently used file bookmarks in DeepSeek Harness, supporting bookmark saving, listing and navigation. It also allows creation of frequently used projects, including management projects, code projects and more.

Windows desktop control connector: through 10 agent tools it captures the screen (including occluded and partially off-screen windows), lists and focuses windows, moves, clicks, drags and scrolls the mouse, and sends key chords or arbitrary Unicode text. Built on koffi FFI: no compiler, no per-call subprocess, and its own GDI screenshot plus PNG encoder.

AST-based context compression, test log filtering, and token budget guard for DeepSeek Harness: strips redundant syntax, prunes noisy log lines, and enforces a token ceiling so the context window never overflows.

Tencent CloudBase backend for DeepSeek Harness — scaffold and deploy full-stack apps from chat, render query results as table cards with paging, sorting and CSV export, preview a deployment on its domain, and call the CloudBase MCP toolset (`mcp__cloudbase__*`) with device-code login.

Records every agent write, edit and shell `rm` into a shadow git repository, then reviews them hunk by hunk in VS Code — accept or revert each one. Needs the companion dsh-review-vscode extension; the panel only appears inside VS Code's webview.

Tencent CodeBuddy model provider for DeepSeek Harness that signs in with browser OAuth instead of an API key, lists the CodeBuddy model catalog with the context, output, tool-calling, reasoning and image capabilities of each model, keeps multiple accounts with automatic failover to the next usable one, shows remaining quota in the composer with a token and credit usage panel, and completes automatable CodeBuddy growth tasks per account with an execution log. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-codebuddy`.

Model-agnostic visual-inspection pipeline for text-only agents: page-by-page HTML screenshots plus a ready-made vision-subagent briefing contract (gewu_prep), then source-code truth verification of every finding (gewu_locate); validated on mimo-v2.5 & qwen3.7-plus.

DeepSeek Harness (DSH) plugin: a /! command trigger (run one command, analyze output, inspired by Claude Code's ! gesture) and a /terminal command (interactive PTY popup with on-demand history reference).

Repo reading-map tool for DeepSeek Harness: a structured, priority-ranked map of any codebase before the agent edits it

Real-compute verification gates: math simplification, logic proofs, regex validation, E-prover FOL, state-machine checks, and code repair, backed by Go-compiled binaries with prebuilt Windows executables.

Registers codex-web-search-mcp as native DSH MCP tools (mcp__codex-web-search__codex_web_search / codex_web_research / web_fetch) for model-independent Codex and Grok web search and deep research.

A read_graph tool backed by a codebase knowledge graph (CONTAINS / EXPORTS / IMPORTS / IMPORTS_SYMBOL relations).

Structured git tools for DeepSeek Harness agents: status, diff, log, branch, commit and stash. Output is pinned with ten `git -c` overrides so a user pager, colour or quotepath setting cannot reshape what the agent reads; every invocation is an argv array, so no shell ever parses an argument; and the mutating actions go through the harness approval service, refusing rather than proceeding when no approval service is mounted.

Custom script manager for DSH: turn verified operations into reusable scripts that run directly via /script or register as agent tools, with parameterized scripts, declared expected outcomes, and execution history.

Codex-style attachment formats for the DeepSeek Harness Web GUI: PDF text-layer extraction, Office text extraction, scanned-PDF OCR, long-document spill + index cards, image-to-PNG.

Econometrics research assistant: 6 tools covering method selection, data preparation, model specification, empirical analysis with Python/R/Stata code templates, robustness checks, and result reporting.