Plugins

Learns a user's coding conventions from instructions and corrections, stores them as confidence-scored rules in editable Markdown, and injects them as reference data into every session. Rules that decay out of range or contradict a newer rule stay visible for review instead of being applied.

Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent tu

Standing instructions edited in the DSH settings UI and injected into the system prompt of every subsequent turn.

Compare DeepSeek Harness, Codex, and Claude Code instruction surfaces for the same workspace.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Session manager and session settings for the DSH sidebar: sessions grouped by workspace with archive filters, title search, batch archive and a read-only transcript preview; global and per-workspace name, occupation and instructions injected into the system prompt; optional recent-only and hide-workspace filters for the sidebar.

Runs local Codex CLI tasks from DSH on Windows with background execution, progress queries, follow-up instructions, completed chat records, and optional supervision; requires Node 22.23.4+, DSH >=0.2.1-rc.3 <0.3.0, and an installed, authenticated Codex CLI.

Bilibili companion for DSH (MIT fork of Alterssss/dsh-bili-whale; do not install alongside the upstream — both register the same `/dsh-bili/` settings routes and share `~/.dsh/bili-whale.config.json`): wakes on a schedule, reads videos through subtitles, danmaku, hot comments and covers, writes two diaries, and shares at most one pick per wake by commenting on the video and @-mentioning the owner (daily quota 3; DM when `share.via=dm`). Inbound DMs, commenter names, summary requests and live danmaku are normalized and scanned for injected instructions before they reach the model; only the owner DM channel can carry an authorization prefix.

Claude-Code-compatible memory for every model in DeepSeek Harness: layered CLAUDE.md/AGENTS.md instructions with @import and rules, a persistent MEMORY.md memory with full writing guidance, refresh on resume and compaction, optional recall, background ext

Serves the OwlCoda RunKit skill in the DSH skill catalog: project-owned objectives, work items, candidate identity, verification receipts, handoffs and recovery stay in project artifacts. Installs instructions only; the project-local owlrunkit CLI is a separate setup step.

Hides opted-in third-party skills and MCP servers from the model-facing catalogs and serves them through one capability tool: search by intent, read the schema or the skill instructions, then call. A local journal records metadata only, never query text or arguments.

Audit what context compaction actually lost. Reads the raw session event log and checks session-constraint survival (the standing instructions the user gave — do-not-X, must-Y, only-in-Z — and whether the summary still carries them; arXiv 2608.11242 measured ~17% survival across compactors), summary hallucination (paths, versions, ports and identifiers the summary invents that were never in the history it replaced), ghost references ("see above" pointing at removed text), token accounting (a summary nearly as large as what it claims to free), and unaccounted prunes. Four agent tools including a cross-session sweep that ranks conversations by how much compaction hurt them. Deterministic — no LLM, so a wrong answer is a rule bug with a name.

One switch that takes an MCP server's tool schemas and its instructions block out of the model context for every agent, live and without a restart, built for the 207 tool schemas REA registers whether or not a task is reverse engineering. A pill in the composer dock, /rea on|off|status|toggle, and GET/POST /rea-toggle/state; the position is remembered across restarts and subagents are covered before their first step.

One standing system prompt for every workspace: a Custom instructions page in DSH's own Settings panel whose text is added to the system prompt of every session, subagents included, and stored in the profile instead of any project.

Adds an Inherit row to the session menu: mechanically extracts concrete anchors (task, recent instructions, files edited, recent failures, commands, todos) from a long session into a handoff and continues in a clean session, with the same preset, no history copied and no model call.

Localizes known DSH system instructions and runtime reminders into Simplified Chinese, trims tool-related guidance to visible tools, and provides editable translations and component toggles while preserving tool names and parameter schemas.

Project-level AGENTS.md loader for DeepSeek Harness: injects .dsh/AGENTS.md (and custom paths) into the agent system prompt, with a settings page.

Configurable Git commit and pull request prompt instructions for DeepSeek Harness

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

Every change to your agent's instructions is recorded with a diff, and any change can be undone.

Edit global AGENTS.md and project AGENTS.md/CLAUDE.md custom instructions in DeepSeek Harness settings, with project-chain discovery, byte-budget display, and save-conflict handling.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

Routes DSH filesystem, shell, subprocess, and PTY operations to local, SSH, and Docker execution nodes, with a node registry, an authentication gate, a mobile-aware management UI, and per-workspace custom project instructions.

SoulFusion-style personalization: 9 response styles, custom instructions, persona cards, per-session switching, long-term memory with audit trails.