Plugins

Local-folder knowledge base for DSH: builds a SQLite FTS5 index over Office, text, PDF and scanned files, ships five tools (kb_search / kb_read / kb_list / kb_status / kb_session) plus a Web panel, and retrieves or syncs only when the user explicitly asks.

Cross-session lesson book (the agent wrong-answer notebook) for DeepSeek Harness: injects a memory index capped at 2 KB verbatim into every turn, adds mem_recall and mem_save model tools whose write gate demands four sections, a locatable reference and explicit human approval before anything reaches disk, registers the /memory command, and keeps every lesson as a zero-dependency Markdown entry in the .memory/ directory.

Permanently delete a DeepSeek Harness conversation and every local copy of its data: session log, derived caches, workspace index entries, spill files, and unreferenced attachments.

Resident search index living in the host process: hot_find (fuzzy filename and path match, with frecency and git status), hot_fuzzy (content search that tolerates typos, including in Chinese), hot_grep (literal and regex content search), hot_plan (groups hits per file so a batch of files can be read in order) and hot_stats. One in-memory line index is built once and rebuilt on demand, so a query does not spawn a process.

Cross-session full-text search over persisted DSH session logs: builds an incremental message-level index and returns sessionId, seq, and a short excerpt; exposes an agent tool and a standalone panel. Requires Node.js 23.5+.

Model-facing codebase-memory CLI tools (codebase_list_projects/index_repository/index_status/search_graph/query_graph/trace_path/get_code_snippet/get_graph_schema/get_architecture/search_code/detect_changes/manage_adr/ingest_traces/delete_project) that ru

Claude-compatible memory for DeepSeek Harness: a user-chosen memory directory with MEMORY.md index and topic files, the memory tool, and a settings page

Federated plugin registry aggregator for DeepSeek Harness — combine npm, GitHub, and JSON catalogs into one searchable index.

Progressive long-term memory for DSH: sharded markdown bodies under ~/.dsh/memory/topics/, with only a live-generated index (shard · count · path · per-entry line numbers) injected into the system prompt — so the prompt cost stays flat however large the m

Tiered compaction hub: replaces the single 80% compaction cliff with a configurable ladder (default 30/50/70/90) whose tiers escalate from gentle to maximum consolidation laws, folds a deterministic keyword index into every checkpoint so facts accumulate across cycles, and summarizes through a model chain — primary plus up to 3 fallbacks, each with its own reasoning effort. Adds a Compaction module sub-tab and a Settings card; toggling off always restores stock compaction.

Context compaction that keeps its receipts: a five-section handoff summary, a durable segment index, review tools that read compacted text back, optional working notes, and a read-only extraction exit. Mounts as the compaction-basic row's replacement; cha

Long-term memory for DeepSeek Harness, read-only as of 0.1.0: a scribe_recall tool that reads a plain-markdown memory room, path rules that refuse directory traversal, Unicode smuggling and NTFS alternate data streams, and a bounded index whose truncation is always reported rather than silent.

Indexes the current workspace into a relation graph and exposes one agent tool, codegraph_explore, for reachability, callers, and impact, plus a Web sidebar graph pane.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Local file recall: indexes the folders you choose into one local SQLite database, so 'where did I put that file?' is one query instead of a disk walk. Caches, VCS and program folders are pruned per directory; each folder keeps its own incremental anchor, so a folder added later is backfilled in full. Read-only: it never modifies, moves or deletes your files. Works on DeepSeek Harness 0.1.7 through 0.2.x, tested on 0.2.0-rc.1.

Project PDF library with background indexing and cited page highlights for DeepSeek Harness Web

In-place redaction and row-level rollback for session logs, preserving the seq-equals-row-index invariant that makes deleting a middle row corrupt the entire log. Originals are copied to a quarantine sibling before any write, and the reader's own semantics are replayed as a pre-write gate.

Ships the Zhouli-mode agent preset, which runs a session in three phases (declaring roles on opening, citing authorities while working, a six-item self-audit at the close), plus one tool with seven actions over a bundled 49,384-character 《周礼》 corpus that returns every passage with a stable 篇序.职官序 coordinate, a per-office establishment index and collation between two Kanripo witnesses.

The missing backend for the dsh-artifacts sidebar tab — serves the /report artifact index and the artifact bytes it renders.

dsh (DeepSeek Harness) plugins for project-level persistent context: session archive with a mechanical index, memory consolidation (CONTEXT.md + MEMORY.md), low-frequency skill autolearn, and automatic handoff.

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.

Skill recommender for DeepSeek Harness: browse local Codex/Claude/DSH session records, derive a user profile, and recommend suitable open-source skills with a tunable weighted match index (higher index = higher-relevance only). Tools + Web settings panel.

Disk-indexed session title lookups for the DeepSeek Harness web GUI — @-mention candidates ~30× faster.

Read-only repository fact scanner kernel for DSH analysis plugins: deterministic probe / file index / modules / dependencies / entry points / symbols / graphs and git facts over a stable JSON schema (CLI + library + skill runbook).