sandbaseai/sandbase-harness

TaskSwarm (蜂群) — DeepSeek Harness 上的多智能体任务编排插件：waves/lanes 并行执行、git worktree 隔离、任务包与跨模型评审、崩溃可恢复 | Multi-agent task orchestration for DeepSeek Harness: waves/lanes parallel execution, git worktree isolation, task packets, cross-model review, crash recovery

Multi-agent math problem-solving & verification framework: brainstorm → solver iteration → multi-verifier debate → Verified knowledge base, with checkpoint resume and manual/auto intervention (also ships as an agent preset).

Developed and reviewed in the iterate-skill monorepo: the plugin code is maintained in the main repository and synced here via git subtree; releases and npm publishing happen in this (plugin) repository, which is the canonical publish point for the dsh ecosystem. Please star / fork the main repository and file issues at the main repository Issues.

Your own dsh session becomes the product manager (PM). The PM is the only one who talks to you. It writes down what "done" means, asks you to confirm it, then starts an architect to design the work, engineers to write the code, and reviewers to judge both. The roles never talk to each other — they share work through files on disk, and the PM passes messages.

Before installing any plugin, run it through dsh-plugin-vet: static rules produce a verdict (deterministic, unforgeable), the agent investigates sensitive points and quality issues following the vet-audit-protocol skill (no one can substitute for that), and a final scorecard is handed to a human/model to decide. Positioning: a monitoring alarm, not an enforcer. vet only does "check → alarm → advise": checks at write time (static scan), watches at run time (runtime guard), and surfaces alarms (sc

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.