Плагины

Short Web Audio cues when a session needs your attention (approval, question, or plan review) and when a task finishes; synthesized inside the page in two selectable styles with a volume setting — no popups, no OS notifications, no audio files, no network — and one bundle that covers DSH 0.1.7+ (desktop & web) and 0.1.0-rc.6.

Desktop notifications and tones when a task finishes, waits for approval, or errors — native on macOS, Windows and Linux with zero runtime dependencies.

Adversarial code review — parallel finders inspect a diff through separate lenses (correctness, lifecycle, contract, security), then each finding goes to independent verifiers tasked with refuting it, and one refutation drops it.

Event-sourced cross-session work ledger: register, track and settle tasks with full audit history, kanban export, and a board digest injected into every model turn.

Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Scans a project's declared build commands — Makefile targets, package.json scripts, just recipes, deno tasks — and exposes them as ready-to-run agent tools.

Project memory for coding agents on DeepSeek Harness: similar past edits surface as precedents, out-of-scope edits are blocked, and cognition persists across sessions (47 upstream-verified fixes, gold-free 20-task run).