Workflow & Automation

Team presets for AgentTeams: ships audit6 / impl5 / lite2 rosters with seed task DAGs and a per-role report contract, plus a captain doctrine section, so a fresh session opens the right team in one approval instead of a pasted prompt. Needs the engine @nanmicoder/dsh-agent-teams added to the same profile first; the team patch targets that engine's entry by id and replaces its whole agent-teams config.

Evidence-based research workspaces with archived sources, knowledge graphs, exact citations and exportable reports. Experimental alpha. Needs Node 24.9 or later, uv and Python 3.13, plus a one-time setup step (setup-engine.mjs) that copies the engine and runs a locked uv sync; pnpm must also be allowed to run the build scripts of onnxruntime-node and protobufjs.

Quest tree for DeepSeek Harness: track a long-running task as a main quest plus a branch tree, with a sidebar panel showing status, progress, markdown notes and a 'you are here' marker to prevent drift.

Multi-workspace agent federation with persistent ticket trees, parallel worker sessions, structured evidence reports, independent acceptance checks, retry/stop and restart recovery. Workers get shell and file tools in the ticket's directory, company_verify re-runs the ticket's acceptance commands in a shell on the host, and scope lists are task authorization rather than a sandbox. State is stored in ~/.dsh/ai-company; the optional company_repo_* tools run separately installed aoci/codegraph commands on any path they are given.

Adds a /grill-me slash command that switches the session to plan mode and prompts the agent to ask 3 to 20 structured questions about your goal, each with a recommended option and alternatives, through ask_user_question before it plans.

Guided first-project harness: asks open questions about your day, shows what it heard versus what it only infers for you to correct, proposes 2-3 projects that reach a runnable prototype in one to two hours, and starts the one you pick — resuming from saved progress if you come back later.

DeepSeek Harness plugin: AI research toolkit — model release radar, model benchmark & community report, and AI news digest (4 tools + 3 skills).

Anthony Fu's agent workflow for DeepSeek Harness: issue triage, digest, task execution, PR creation and simplification

Multi-model council deliberation for DeepSeek Harness

Requirement to a detailed design doc another AI can build from: the model fills a plan, the plugin validates it and emits a SPEC plus task cards, then independent review and implementation evidence check the result. Needs Python 3.11 or newer; the spec-graph engine it calls is bundled in the package.

Event-driven wait for DeepSeek Harness: returns the moment the target completes, fails early, or stalls — instead of burning a full timeout and querying again. Also blocks sleep-polling and over-long waits.

Hand off local development tasks between Codex and DeepSeek Harness with original requirements, project agreements, workspace checks, and a relay board. Needs the Codex desktop app (or a codexBinary path in the settings); verified on macOS only.

340-entry code-animation style library, 8 prompt templates and 5 renderable code templates in a sidebar panel, plus agent tools (awkit_search / awkit_get_style / awkit_render_template) so the model can pick a style and render a template during a turn; content ships inside the package, no extra download.

A goal mode for DeepSeek Harness with no round cap: a goal stays active until it is completed, paused, blocked, or cleared; the minimum interval between automatic rounds is configurable, and quiet windows suppress automatic rounds.

DevLead mode for DeepSeek Harness: a human-only switch turns one ordinary session into a lead with eight devlead_* tools to register workspaces and create, read, continue and watch other ordinary sessions; it dispatches work to those sessions, reviews the delivery and reports, is woken through a durable notification digest when a watched session's turn settles, and can give a dispatched writing session its own Git worktree when the host provides the experimental worktree service.

Installs the whole role-chain toolchain in one step: four agent presets (plan, work, code and review) plus fourteen chain_* tools for evidence-bound rounds, with a settings card. It ships the protocol runtime itself, so no sibling package is needed. It replaces the separate l1-presets and l2-protocol entries, which must be removed before enabling this one.

AI-assisted research workbench with editable step workflows, on-demand skill binding, a live execution graph and in-project document review (needs a local Python with python-docx, python-pptx, openpyxl and PyMuPDF), while keeping existing projects on their original configurations. Requires DSH 0.2.2 or later.

An agent preset that adds a working mode to DeepSeek Harness: the mode text has the model analyze requirements and plan before acting, open a gate document, and reply in a fixed three-block shape. The task tree and session-start profile injection are separate companion packages in the same repository, installed from a clone with scripts/install.mjs; only the term dictionary (dsh-term-dict) comes with this package, and without the task tree the model writes its own alignment bar. Needs DSH 0.2.1-alpha.1 or later.

Source-backed logic reviews with diagrams, code diffs, and resumable human feedback. The first activation downloads the official LogicMargin release (SHA-256 verified); on macOS and Linux this needs curl, unzip and shasum or sha256sum.

Delegates a one-shot task from DeepSeek Harness to a locally installed Reasonix over the Agent Client Protocol, reusing Reasonix's own model, credentials and sandbox settings; exposed as the `subagent_reasonix` tool. Auto-approves every Reasonix permission request.

Runs your kanban backlog during DeepSeek off-peak hours while the machine is idle: per-card git worktrees, evidence-gated completion, merge-back, and budget and idle gates. Linux or WSL only (needs bash, python3, git, jq, flock); initialise a git repo once with `npx dsh-offhours init`.

Agent orchestration for DeepSeek Harness with eleven selectable presets, planning, delegation, review gates and durable project state.

Host-side progress checkpoints for long DSH tasks. After N minutes or M tool calls the model is nudged to post a one-line progress note and keep working, so you can correct it before it runs far off course.

Tongzhou: named local Codex–DSH discussions and read-only conversation views, with a DSH bundle and optional one-click Codex skill setup. Initially supports macOS with DSH Desktop 0.2.2-rc.1.