Plugin
Sfoglia, filtra e installa i plugin di DeepSeek-Harness.
440 plugin trovati
dsh-sound-cue
nixz0824/dsh-sound-cue
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.
notifier
johnxu22786/notifier
Desktop notifications and tones when a task finishes, waits for approval, or errors — native on macOS, Windows and Linux with zero runtime dependencies.
dsh-review
viger1/dsh-review
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.
task-board
johnxu22786/task-board
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.
deepseek-harness-orchestrate
apheli0os/deepseek-harness-orchestrate
Declarative task-DAG orchestration for DSH: validates dependency graphs, runs topological task layers in parallel through workflow-backed subagents, and propagates failures deterministically.
dsh-human-task
ywgatustcbbs/dsh-human-task
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.
command-scout
johnxu22786/command-scout
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.
dsh-cognition
scd13150/dsh-cognition
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).