Plugins

Pack de compétences de l'agent de notes virales Xiaohongshu/RED : recherche de notes tendance, génération/réécriture de notes, vérification, analyse des comptes autorisés, connexion par QR et publication contrôlée.

Examine le code local et GitHub/npm avant le développement pour trouver des implémentations réutilisables, évalue réutilisation contre réécriture et vérifie le couplage de l’architecture.

Mémoire native par espace de travail, directement intégrée aux propres coutures du harness : des faits et un profil toujours actif mais borné sur l’unité JSON du domaine de stockage, des écritures soumises à approbation avec citations `(sessionId, seq)`, un rappel déterministe et une FTS session-query sur les sessions passées — sans serveur externe ni SQLite personnalisé.

Passe en revue tous les fichiers écrits par l'agent dans une session depuis l'en-tête de session, avec hunks par fichier et écritures refusées comptées à part des modifications.

Kit opérationnel axé sur les preuves : six outils en lecture seule (catalogue de capacités, plans de workflow par étapes, lecteur de skills empaquetés, recherche bornée dans la mémoire locale, audit des releases du dépôt, checklist de release) et cinq skills empaquetés — planifie et audite, sans jamais écrire à distance.

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

Prompt-polish template injector for DSH: click ✨ in the composer to inject a "polish my prompt" template (current draft auto-embedded), no send, no network, no model — the main agent rewrites with full context. Replaces narrative-prompt-polish (2026-09-14 migration).

Pool AI provider accounts per platform and route them through a local loopback proxy that bridges the OpenAI, OpenAI-Responses, Anthropic and Gemini protocols, then write the proxy into Codex, Claude Code, Gemini CLI, Grok, OpenCode, OpenClaw and Hermes config files with snapshot-and-rollback safe writes; registers no agent tools.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

One-click draft polish for the DSH composer: rewrites your spoken draft into professional wording, sends only the draft snapshot (never conversation context), and never blocks sending if the LLM is unavailable.

Per-project memory for DeepSeek Harness. Three Markdown files per workspace — PROJECT.md, DECISIONS.md and SESSIONS.md — are auto-created on the first step of any session in that workspace, re-read from disk and re-injected only when they change (and re-injected if compaction dropped them), and written back by classification through a memory_checkpoint tool, with a bounded end-of-turn nudge when a turn did work but recorded nothing. memory_read and memory_search read the live log and the archive, the latter over a zero-dependency BM25 index. The session log is capped at 200 entries with the overflow moved to SESSIONS-archive.md — never injected, but visible, readable and searchable, and restorable one entry at a time. Settings page: a workspace list with a path filter, read-only tabs for the three memory files plus the archive, reload, export/import of one workspace's memory as a JSON bundle, a two-step clear, a panel that rewrites or removes the AGENTS.md instruction block, and a PROJECT.md staleness reminder. A composer status chip shows that workspace's sync state and creates the files on click. Zero dependencies — no vector store, no embeddings, and no model calls.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

DSH 插件：读写钉钉 AI 表格（多维表 / aitable），并提供「钉钉文档」设置面板与定时导出。包装钉钉官方 dws CLI。 Read and write DingTalk AI Tables from DeepSeek Harness, with a settings panel and scheduled CSV export.

Six independently togglable modules in one DSH plugin: per-turn CNY cost, DeepSeek account balance, PDF/Word/Excel/CSV read-write tools with right-sidebar preview, a compiler/runtime environment registry, and run/build tools that execute a program or an MSBuild project by environment id. Toolchain paths are resolved at run time (Visual Studio install-root scan, %ProgramFiles%, PATH) and can be overridden per environment through plugin config, so nothing is pinned to the author's machine.

Education mode for DeepSeek Harness: research a course, teach it, write the class notes, and quiz the learner.

Connects DeepSeek Harness to FitMeet through per-user OAuth with 17 tools for people search, gatherings, notifications, personal items, connection feedback, Hall publishing, and direct messages, with preview-and-confirm guards for write actions.

Language-pack framework that rewrites model replies: A is an independent LLM rewrite, B injects FTS5 terminology retrieval into that rewrite, C applies local dictionary and regex rules, and composite runs a pipeline such as B then A then C. Ships a GitHub pack marketplace, a ZIP installer with path, size and file-type checks, and a mandatory risk disclaimer gate.

Portable agent knowledge base in plain OKF v0.2 Markdown: 13 wiki_* read/write tools, progressive disclosure, backlinks, gated writes via AGENTS.md rules, auto index/log maintenance, linting, and named multi-bundle switching (session-level or global).

Strips the harness-injected prefix and suffix system prompts so the agent runs on the preset's native prompt alone, for soft-jailbreak catgirl persona simulation: ships a bundled plugin that idempotently deploys the 猫娘 Yuike preset to ~/.dsh/.agent-presets/yuike/ and never overwrites an edited preset.

macOS menu bar app for the DSH web server, plus the host plugin it reads: the plugin writes the running server's port, PID and tokenized URL to ~/.config/dsh-launcher/runtime.json and removes it on shutdown, so start, open, restart and stop work from the status bar even for a server started from a terminal.

Self-tending living memory in one local SQLite file — a nightly patrol dedupes, merges, decays and cross-links entries on its own, with seven-signal RRF hybrid recall (FTS5 + jieba Chinese-first tokenization, optional vector KNN, graph PPR), a typed knowledge graph, conflict detection instead of silent overwrites, and web telemetry panels.

Search, read and write an Outline knowledge base from conversations, with whitelist-guarded approval for every document write.

Open folders on remote hosts over SSH as Harness workspaces: file tools (read/write/edit/grep/glob) and shell commands run directly on the remote host over SFTP, ripgrep, and ssh2 exec, with no local mirroring, an encrypted multi-host registry, and the local sandbox policy still enforced.

DSH GitHub connector: review PRs, triage issues, debug CI, prepare changes (18 tools, gh-first + REST fallback, approval-gated writes).