Plugins

Provides shared plan, context pickup, and progress update Skills through StateDock Remote MCP without executing tasks or scheduling agents; targets Harness 0.2.0-rc.2.

An audit workspace for DeepSeek Harness: a multi-agent consultation venue where each review seat is filled by an agent, every judgment is routed to a named review face, and the whole run is kept as a traceable record. Works out of the box: the service endpoint is built in, a workspace is provisioned automatically on first launch, and review scenes come with their seats and agents listed.

Role-based expert subagents for DeepSeek Harness with a task sidebar: explorer, librarian, oracle, designer and fixer delegate in parallel, each with its own model and reasoning depth.

An agent preset (Hermit/小寄) that turns DSH into an always-on personal hub: a scoped butler persona, a dispatch tool that delegates multi-step tasks to background sub-agents with per-task model routing, async completion reports woven back into chat, plus a credit budget gate, a P/M confirmation chain and an M1 event log.

Agent mode picker for DSH: pick an external Agent CLI (Claude Code, Codex, Qwen Code, Gemini CLI, Aider, Goose, Hermes…) as the session's default executor from a control next to the input box, instead of editing configuration files. The agent roster is data-driven, and installed CLIs are discovered automatically from PATH, the managed CLI directory and a drop-in convention directory. Agents that are installed but still missing credentials or a required background service are shown as "needs setup" rather than silently hidden.

Pick the model your subagents run on — with a reasoning-effort ceiling and an output-token cap — enforced in code on every child DSH starts, whichever tool starts it.

Replaces the session topbar title with a workspace and session breadcrumb, switching workspaces, sessions and subagents from topbar dropdowns; adding a workspace opens a dialog shaped like the native one, which can hand off to the system folder picker.

JavaScript orchestration over DeepSeek Harness tools using Node.js VM or QuickJS WebAssembly backends.

Blocks AI coding agents from editing files without evidence and from running unapproved high-risk commands, and tells quoted dangerous strings apart from commands actually being executed.

Self-organizing multi-agent clusters with no orchestrator. Real DSH subagents coordinate through a shared append-only log that each agent reads and writes on its own schedule, with no topology and one dispatch per agent; a snapshot mode is also included where the harness freezes each neighbour view into the prompt and drives a ring/mesh/swarm cluster to convergence.

Cross-workspace worker fleets: one orchestrating session spawns named worker sessions in other project workspaces, queues or steers tasks into them, watches them in the background via a real host job, and collects their reports. Worker completions deliver themselves to the orchestrator's session rather than needing to be polled, so an idle orchestrator still reacts. Escalations and failed workers deliver by steer when the orchestrator is mid-turn and by queue when it is idle; a turn that ends without a report counts as a failure and the worker is replaced after a configurable limit. The roster persists to disk and each worker session carries a durable title, so a restart neither loses the fleet nor spawns duplicate sessions. Ships five agent presets at full plugin parity with the standard preset.

Dispatches coding tasks to local Orca-managed agents and reports completion to DSH; documented for DSH 0.1.5-rc.2.

Visual sketchboard for DeepSeek Harness: draw with Excalidraw, let AI agents inspect and annotate sketches, and review proposed edits.

DeepSeek Harness plugin: declare named subagents in TOML files under ~/.dsh/agents and <projectRoot>/.dsh/agents

Document intake for agents: doc_route sniffs a file's real format by magic bytes and measures a PDF's text layer and page column layout before any conversion, and pdf_markdown converts PDFs to Markdown in column reading order with PyMuPDF. The PDF path needs a Python 3 interpreter with PyMuPDF.

Session cost in rubles in the composer dock — the tariff in effect with its countdown, the API cost at that tariff, the CBR rate, the total including subagents, cache savings, and DeepSeek Platform balances.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

DeepSeek Harness plugin for Agent-Playbook: multi-agent claims, isolated git worktrees, and enforced acceptance checks. "Done" is an exit code, not a claim.

Generic Companion-protocol bridge from DeepSeek Harness to phones/IoT/legacy agents (includes Termux companion example).

Meeting rooms for DSH sessions: joining a room grants the right to convene and the duty to attend, and a session belongs to at most one room. Convening forks each participant in with its own completed-turn context and with its tools stripped, a moderator that carries no context chooses the speakers, and every turn is appended to disk as it is spoken. After adjournment each participant receives its own minutes as a user turn and resumes work.

Clusters arXiv, first-party lab, official artifact, hardware-vendor, and opt-in X signals into versioned release evidence bundles, then gates claim-level reproduction on commands, artifacts, metrics, and verifiers.

DSH plugin that registers the ai-eight-honors-eight-shames skill: eight checkable working rules for coding agents (verify before calling, confirm ambiguity, cite evidence, reuse before creating, test before claiming done, follow local conventions, separate fact from inference, keep changes reversible) plus a ninth rule that logs each user request and the change made in two fixed report files at the workspace root.

0.8.6 fixes a startup crash: the host runtime package is an optional peer, never an installed dependency. TypeSafe Jev (System One decision model) wired end to end into DeepSeek Harness (0.8.6). Seven tools: jev_decision (1-25 parallel atomic verdicts in one call; noul/choice/score; typed answers with calibrated confidence; measured median 266-484 ms; verdicts only, never prose), jev_choose (rank 2-10 candidate approaches - fit 0-3 and risk - into an explicit composite with a recommended pick), jev_batch (NEW in 0.8.6: one set of 1-5 judgments over 1-20 texts, one real call per text at bounded concurrency, returning a paste-ready markdown table sortable by a judged dimension; built-in sentiment/priority/intent/pii/spam presets; a failed row is reported as failed with the raw error, never guessed), jev_usage (locally measured usage: calls, tokens, estimated cost, latency median and p95, per-tool mix, rolling windows, projected burn rate, optional local hard budgets, and a declared-balance remainder), jev_overview (session ledger), jev_guard_status (guard counters plus a registrations block that surfaces per-surface registration failures) and jev_verify (frozen 27-question live benchmark at concurrency 6: 96.3%, 26/27). WHAT IS NEW IN 0.8.6 - the ledger survives a restart, the remainder is derived instead of invented, and the plugin can now do batch paperwork. (1) The local ledger persists to $DSH_HOME/jev-usage.json BY DEFAULT, so the cumulative total no longer resets when the host restarts. Two real bugs behind the old silent zero were found and fixed: the ledger path only honoured DSH_HOME (absent inside the host process, so persistence was silently disabled and the file name was null), and save() wrote the still-empty in-memory ring over the history file because it ran before the first load while the debounce window swallowed the follow-up write. (2) Remaining is derived, never invented: TypeSafe exposes no balance endpoint - /v1/usage, /v1/quota, /v1/account, /v1/account/balance, /v1/balance, /v1/credits, /v1/billing, /v1/me, /v1/limits and a dozen more all return 404, and only /v1/models answers, with no balance headers - so the panel shows the remainder as your declared balance (quota.declaredBalanceUsd) minus locally measured spend since quota.balanceSince, and says plainly that it cannot be fetched instead of printing a number. (3) The composer pill re-reads every 20 s instead of every 60 s, so a call you just made shows up while you are still looking at it. (4) The collapsed pill leads with the remainder once you declare a balance, and the cumulative row is renamed when the ledger is on disk. Every tool has an in-conversation structured view; the Settings > Plugins card covers credentials, tool switches, the auto-guard, the dashboard, the prompt section, usage/quota and auto-triage. Honest by design: no API key means an explicit error, never fabricated results; every registration is quarantined so a failure degrades one surface. Tests 38/38 (npm test, ~2.5 s). Client half applies on refresh; server half needs a host restart.

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.