All Plugins

Keep the built-in web_search tool without an official DeepSeek API key: disable web-search-deepseek and use Tavily keyless by default.

Injects allowlisted GitHub Actions and GitLab CI run metadata into agent context without reading logs, credentials, or provider APIs.

Create/modify/inject test assistant messages and import/repair session.jsonl(.zstd) session logs into new sessions.

Cross-session memory for the model: full-text search all past sessions (SQLite FTS5 via ctx.sessionQuery) and bring the strongest matching excerpts back into the current context.

Claude-Code-style lifecycle hooks: configured shell commands run before/after model tool calls with a JSON payload on stdin; a non-zero pre-tool exit blocks the call.

Persistent model tool-call trace recorder: every tool call is durably written to a JSONL file that survives restarts, queryable via a structured call_trace tool and a callTraceHistory service, with size rotation and an optional floating canvas UI add-on.

A hands-off safety net: directories the agent deletes go to a trash folder first and symlinks are never followed, with zero approvals.

A development safety kit: rolling config snapshots, automatic rollback on plugin failures, boot-failure rescue, and an in-settings management panel.

Scouts the deepseek-harness repo and every dsh-plugin-tagged repository to discover harnesses related to your goal, then judges each as worth trying, watching, or skipping.

Desktop and browser automation bridge (36 tools): window/screen/mouse/keyboard control with PaddleOCR element perception, Chrome CDP browsing with accessibility snapshots.

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.

Advanced memoria tools: session context injection (profile + recall), recent decisions, health report, namespace allowlist, memory relation graph, and entity search; companion to dsh-memoria.

Thin on-demand context retrieval: context_query / context_slice / context_grep tools that read already-persisted history back with replay-safe citations.

File-backed working memory: memorize/recall key premises verbatim in a session notes file so they survive context compaction losslessly.

Post-compaction premise-drift guard: injects a one-shot notice when a compaction summary drops a critical literal anchor.

Multi-engine reverse image search aggregator: Google Lens, Baidu, Yandex, TinEye, SauceNAO, IQDB, Ascii2d.

Recurring-habit scheduling from pure date math: next occurrence, range schedules, and overdue advice.

Action-state time memory: record typed states and actions, then analyze trends, anomalies, and causality.

Indexes workspace symbols with Tree-sitter and provides lexical or optional embedding-assisted code search.