Description
Dispatch Pilot:一个在 Claude 之外的决策模型(默认 Perplexity 的 pplx,没有 Perplexity key 时退回 TypeSafe 的 Jev,也可以固定用 Jev)在你每次发消息时决定主 agent 这一轮的 effort,每一步都按这一档发出,一轮进行中每隔几步再判断一次;也为主 agent 派出的每个 agent 和 Workflow 脚本里的每个 agent 按 Artificial Analysis 的基准选模型和 effort(sonnet 和 opus 至少 medium)。主 agent 的模型从不改变,prompt cache 不受影响(只在 Claude Code 订阅下成立;Bedrock、Vertex 和网关上切换 effort 会让缓存失效)。它还不让主 agent 读完整的 skill 列表,改为在你发消息时推荐合适的几个,一轮中途主 agent 可以用 find_skill 工具查 skill。agent 的工具调用接连失败时强制升高它的 effort(失败的 haiku agent 改用 sonnet),除非这些失败本来就在意料之中。所有判断和理由都放在看板上:prompt 上方的 band 列出本轮每个 agent 的模型和 effort,脚部一个短摘要,/dp 打开的依据面板写明每个决定的依据和决策日志。
What it can do
Reach level 3 — network What does this mean? →
Can see: subagent spawns · every prompt · /"(?:)"/ calls · Agent calls · Workflow calls · compaction · every tool call
Raw API calls (30)
- $.agent.list
- $.clock.after
- $.clock.now
- $.clock.sleep
- $.command.list
- $.command.register
- $.env.get
- $.fs.exists
- $.fs.list
- $.fs.read
- $.http.fetch
- $.model.complete
- $.session.cwd
- $.session.messages
- $.session.usage
- $.settings.read
- $.state.get
- $.state.set
- $.store.delete
- $.store.get
- $.store.keys
- $.store.set
- $.tool.register
- $.ui.close
- $.ui.invalidate
- $.ui.log
- $.ui.open
- $.ui.panes
- $.ui.resolve
- $.ui.toast
Static check passed on Claude Code 2.1.295.
Install
$/plugin marketplace add alexcz-a11y/claude-mods $/plugin install dispatch-pilot Check the repo for the exact name.
Details
- Repository
- alexcz-a11y/claude-mods
- Path in repo
- dispatch-pilot
- License
- Unknown
- Last updated
- Oct 9, 2026
- First seen
- Oct 10, 2026
- Last scanned
- Oct 10, 2026
Related mods — reach level 3
- ruflo-console ★ 76,337
- ruflo-goals ★ 76,337
- ruflo-agentdb ★ 76,337
- ruflo-graph-intelligence ★ 76,337
Capability data is machine-generated by static analysis and may be incomplete. A SAFE badge is not a guarantee — read the code before installing anything with broad access. Not affiliated with Anthropic.
Found a mistake in this listing or verdict? Report an issue →