Plugins

White noise player: lays a layer of background sound (rain, streams, campfire, café) while AI codes, for flow and focus. Supports multiple playback modes (sequential / shuffle / single-loop / intermittent) and AI automatic background music download from Wikimedia Commons (CC0/PD/CC-BY).

Adds combo scoring, activity breakdowns, turn ratings, and optional Jev-based encouragement to DSH Web sessions.

Ports the obra/superpowers methodology as 14 native DSH skills — brainstorming, writing-plans, executing-plans, subagent-driven development, test-driven development, systematic debugging, parallel agent dispatch, git worktrees, code review, verification before completion and skill authoring — served through the DSH skills registry with their scripts, references and cross-links intact (frontmatter folded into a manifest, prefixes realigned to DSH skill names). Requires DSH session format v4 (official DeepSeek Harness 0.1.7+): the /superpowers slash command declares the producer-owned source kind plugin:dsh-plugin-superpowers.

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.

Matrix digital rain: drapes the chat window in the classic green character rain — cascading columns with incandescent white heads and green tails, streaming the tokens the agent is generating into the rain in real time; opacity, speed, density, font size and colors are all adjustable, and rain intensity follows agent activity.

loci second-brain sidebar tab: hybrid search, cited Q&A, day-grouped memory browsing and quick capture over a local loci knowledge base; proxies `loci serve-http` same-origin from dsh-better-sidebar, no core fork.

AlphaRSI — three-role self-improvement loop that evolves the training recipe of alpha sequence models. Operator runs walk-forward, Evaluator grades with OOS RankIC, Refiner proposes hyperparameters via TPE Bayesian search; only strictly-better recipes are kept. Offline one-command run, data bundle shipped with sha1 reconciliation, GPU auto-detect. Ships one skill.

Keeps a redundant sandbox-escalation argument from failing a tool call. Escalating tools (pwsh, bash, write, edit) advertise the full sandbox_permissions enum, but DSH only accepts a level strictly wider than the one already in effect — a check its own source calls 'deliberately not a schema constraint'. A model that reflexively passes the argument therefore picks the level it is already at and the call dies before running with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "workspace-write" mode', costing some models a whole turn of retries. This plugin registers one tools/execute waterfall listener and, only on that documented rejection and only when the arguments really carried an escalation field, re-issues the identical call once without it. Safe by DSH's own documentation: the rejection precedes any execution ('nothing has run'), and the corrected call cannot match again, so the retry is loop-free. Reproduced and verified end to end — before: isError true, the command never ran; after: the command's real output, isError false, one tool/call and one tool/result. Zero dependencies.

Training attestation — reproducible, attributable, auditable off-site standardized training for asset pricing. Hard-gates four failure modes (half-refresh, hash mismatch, unknown-read-as-pass, master pollution). Ships one skill.

Coordinates bounded project recall from compatible memory and learning providers, with shared settings and provider lifecycle management.

DSH web 插件：侧栏字标、空白会话大标题与「预览版」标签的用户可编辑品牌配置，保存在 DSH 设置文档，改完即时生效

Model training stage — end-to-end analysis, model training, and estimation for asset pricing and machine learning research. Ships one skill.

Brick — a restrained, token-only theme layer for DeepSeek Harness Web. Warm plaster neutrals, mortar hairlines, one fired-clay accent, and a Settings on/off switch. 一切皆插件，每一块砖都可承重。

An ink-wash theme for DeepSeek Harness inspired by Luzhou Moon, a guofeng song by the Chinese singer Vae. Built on dsh-theme-customizer, it repaints the app background, sidebar, composer, new-session button, settings panel, Cordis panel and floating panel with generated ink-landscape artwork, adds gold filigree frames and a full-screen rain effect, and rotates vertical lyrics drawn from 24 of his Chinese-style songs.

Records scoped workflow rules and correction reminders with bounded evidence, local settings, and optional Brain Hub integration.

Project-scoped local memory with review-before-recall, source references, reversible consolidation, and a portable Cordis service; the Harness adapter provides search and settings, with optional Brain integration.

Self-organizing AI second brain for Obsidian, as a single DeepSeek Harness plugin. Merged fork of dsh-plugin-wiki-skills + dsh-plugin-wiki-tools, targeting parity with claude-obsidian.

Tiered task queue as the single source of truth for DSH↔Hermes work (reset > approve > review): enqueue tools for all submission paths, lease/claim model with concurrency 1, priority aging against starvation, atomic busy mutex, and a Hermes-side consumer (cron */1 + monitor gating) that drains tasks, writes review-handoff requests with single-slot checks, and invokes the reset agent.

Algorithm learning toolkit syncing Codeforces and AtCoder submissions, profiling weaknesses, generating AI training plans, and tracking spaced-repetition reviews across a 114-lesson algorithm curriculum.

Deterministic Reasoning Engine (DRE) for dsh: dre__* tools for knowledge verification (three-stage discrimination), deterministic cognition loops, constraint solving, mental models and synapse memory - strengthens information certainty.

LLM-as-a-Verifier for dsh with the Best-of-N conversation mode built in: rank N candidates with a fine-grained verifier (expected grade over the logprob distribution), on demand via the verify tool or automatically on every turn of a Best-of-N session. In

Community DSH plugin for constrained, auditable diePi research backtests

A typed, inference-capable ontology (TBox + ABox) plugin for DeepSeek Harness — durable domain knowledge the agent can define, assert against, and query under schema constraints.

Deployment-level static web plugin for DSH: cerrda dark re-theme of the DeepSeek Harness Web GUI (rose/purple oklch, Liquid Glass composer, Silk WebGL2 background, Sora/Fraunces/JetBrains Mono). Install with: dsh plugin --profile web add dsh-cerrda-theme