Plugins

Wiederverwendbare Subagenten-Definitionen, verwaltet über eine Einstellungsseite und dispatcht über ein einziges delegate_agent-Tool; mit integriertem schreibgeschütztem Explorer-Preset und einem Umschalter für verschachtelte Delegationsrichtlinien.

Sicherer, auditierter SQLite/PostgreSQL/MySQL-Zugriff für dsh-Agenten: Schema-Introspektion, erzwungene Nur-Lese-Abfragen, ein Schreibgenehmigungs-Gate und ein dauerhafter JSONL-SQL-Audit-Trail.

Führen Sie isolierte, schreibgeschützte parallele Gespräche neben einem aktiven DeepSeek-Harness-Agenten.

OpenAI Codex CLI-Wrapper: Einmal-Ausführung (one-shot exec), Repo-Überprüfung und Sitzungswiederaufnahme mit einer standardmäßig schreibgeschützten Sandbox.

Generator für wöchentliche Zusammenfassungen: aggregiert Git-Commits, DSH-Sitzungsaktivität und tägliche Speichereinträge zu einem wöchentlichen Markdown-Bericht, schreibgeschützt.

Skill-Manager-Seite im DSH-Einstellungsbereich: System-, Benutzer-, Workspace- und Preset-Skills durchsuchen, einen Skill zu seinem Dateibaum aufklappen, Dateien anzeigen und bearbeiten, Skills aus einer ZIP importieren sowie exportieren oder löschen (System-Skills sind schreibgeschützt).

Git-Hygiene-Prüfer: schreibgeschützter Scan nach zusammengeführten und veralteten Branches, übergroßen versionierten Dateien, nicht versionierten Dateien und nicht committeter Arbeit, mit Bereinigungsvorschlägen (löscht niemals etwas).

Schreibgeschützter Repo-Initialisierungsscanner (repo_setup_scan-Tool): erkennt Stack/Tests/Doku/git/db und empfiehlt Plugins, MCP-Server und Hygiene-Dateien.

Teile die aktuelle Sitzung im LAN als schreibgeschützten, durch ein Token geschützten HTML-Schnappschuss mit Sitzungsstatistiken und Markdown-Rendering.

Evidenzbasiertes Betriebskit: sechs rein lesende Tools (Fähigkeitskatalog, stufenweise Workflow-Pläne, Reader für gepackte Skills, begrenzte lokale Gedächtnissuche, Release-Audit für Repositories, Release-Checkliste) sowie fünf gepackte Skills — plant und prüft, schreibt nie remote.

Task ledger board for dsh (DeepSeek Harness): read-only board over task-ledger skill workspaces. The task-ledger skill is bundled — install the plugin, get the skill globally.

Fortune-telling toolkit: bazi, ziwei doushu, meihua yijing, liuyao (six-line coin oracle with najia), almanac, chenggu bone-weight, zodiac, date selection, qimen dunjia, fengshui, name scoring, compatibility, numerology, a life K-line chart, tarot and xiaoliuren — 16 tools whose ganzhi, stars, hexagrams and bone weights are all computed by deterministic local engines, with the model only interpreting results. Supports solar and lunar dates with leap months, China DST and true solar time correction, plus a ten-page read-only side panel.

Counts persistent operations within a turn and escalates on the total: a reminder first, then an explicit stop instruction, then an approval prompt. Reads the session sandbox mode on every call, and stays silent under read-only and workspace-write.

Run a read-only security assessment of a Dameng DM8 database with 60 checks and produce an HTML report with GB/T 22239-2019 control mapping. Needs Java 8+ and a DmJdbcDriver jar you provide yourself.

Automatic second-opinion review: a restricted child session re-reads the agent's recent work with read-only tools and delivers at most one evidence-backed note, or stays silent. Requires a model route in the config; the plugin stays disabled until one is set.

Settings page for agent modes (presets): switch up to 15 capabilities per mode (commands, files or read-only files, web, subagents, and more) or individual plugin rows; edit each mode's system prompt with variable checks, a full preview, version history, optional live updates for running sessions, and an approval-gated mode_prompt chat tool; create modes from four starter templates or copies; merge built-in updates after a dsh upgrade while keeping your changes, and turn off rows that fail to load.

Requires the Codex CLI installed and `codex login` completed. Consult the OpenAI Codex CLI from DeepSeek Harness with three tools: codex_consult runs Codex in a read-only sandbox, inlines evidence files, verifies the served model and reasoning effort from the Codex rollout file, retries disconnected streams, and records quota before and after the call; codex_quota reports the current 5-hour and weekly quota; codex_calls lists recent calls.

Read-only assessment of whether a Dameng DM8 database can be recovered and to which point (LSN or time), across 16 recovery scenarios, with an HTML report. Needs Java 8+ and a Dameng JDBC driver jar (DmJdbcDriver8.jar) that you provide yourself.

Read-only CSV/XLSX comparison by business keys, with offline HTML review and exportable comments.

Workspace memory for DeepSeek Harness ported from ZCode: one Markdown memory directory per workspace (a MEMORY.md index plus one file per fact), injected into each main session and refreshed by a background extraction request after completed turns; a sidebar page browses the stored files read-only.

Read-only session-log projector (drsc) for DSH: scans ~/.dsh/sessions/**, decodes zstd/tiled-frame logs with a vendored leaf decoder and rewrites per-session projections into its own SQLite (node:sqlite, segments / replaces + FTS5), exposed through a single fenced HTTP route — surface ledger, recall/compression pair accounting and Chinese-capable full-text search. Token counts share the exact DeepSeek-V4 tokenizer and formula as CCI verify, falling back to a labelled chars/4 basis when assets are absent. Never writes session files; all output lands in its own data directory. Serves three consumer plugins: context-compression-improved (surface marking + recall reconciliation), session-steward (search-corpus switch), prime-memory (historical anchor backfill). Hosts 0.1.0-rc.2 .. 0.2.1-rc.2 (17-tag exact engines.dsh enum). npm: dsh-reference-session-collector.

Replaces the harness identity block with its own prompt pack: three system-prompt sections (identity, rules, footer) in full, concise and dev presets, a per-turn rule card appended as a real user message, a remote announcement feed that falls back to a bundled copy offline, a GitHub Releases update check with an apply command, five `sunder_*` tools, and a read-only status section in Settings.

Reports Codex reset probabilities, completed resets and upcoming schedules in the DSH composer, with a read-only tool for status and paginated records.

Local-only, read-only DSH token dashboard: provider-reported usage across all backends, all-time totals, a 365-day heatmap, input+output and cache read/write details, turn/step counts, average tok/s, and durable history after sessions are archived.