Real Skill packageSource verifiedClawHub registry

Multi-Agent Orca

编排两个以上边界独立的本地 worker,使用 Orca Run/Task/Dispatch、独立 worktree/session 或 tmux 回退,由 PM 负责拆解、派发、巡检、429 停滞恢复、独立验收、PR 收口与临时资源清理;也用于用户明确要求“并行推进”“多个 worker”“PM 总控”“Wave Autopilot”或防止 PM 直接实现逃逸。不要用于单个短任务、纯状态同步,或仅需 Git 分支、提交、PR、merge 规则的工作。

Identity and source

Publisher attributionxierluoregistry owner unverified by skillvetai
Functional categoryAgent Engineering, Security & Governanceautomatically inferred · 55% rule confidence
Package forminstruction with code174 recorded files
Canonical sourceClawHub registryclawhub:cat-xierluo:multi-agent-orca
Open canonical source ↗

Platform declarations

These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.

OpenClawnative officialProvenance: registry distribution

Independent structural checks

These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.

Claude Codepasses structure
Checker 0.1.0 · agent-skills-2026-08-13+claude-code-docs-2026-08-13 · 10/15/2026.claude/skills/multi-agent-orca

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenAI Codexpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+codex-docs-2026-08-13 · 10/15/2026.agents/skills/multi-agent-orca

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

OpenClawpasses structure
Checker 0.1.0 · agent-skills-2026-08-13+openclaw-docs-2026-08-13 · 10/15/2026skills/multi-agent-orca

Runtime, accounts, dependencies, permissions, network behavior and task quality remain untested.

Installation and inspection

This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.

clawhub install @cat-xierluo/multi-agent-orca
clawhub inspect @cat-xierluo/multi-agent-orca --version 3.0.1

Security evidence

SkillVetAI static result: high signal

This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.

Status
completed
Coverage
partial text content
Files
40 / 174 inspected as text
Checked
10/15/2026, 5:03:18 PM
Scanner
0.1.3
Policy
1.0.3
1 automated finding
highDynamic code or shell execution is presentscripts/dispatch-profile-adapter.py:41 · confidence 78%exec(
1 High/Critical review queue entry
STATIC_DYNAMIC_CODE_EXECUTIONpending
Open human review queue →
5 inferred permission indicators
  • shell execution — automatically inferred
  • network access — automatically inferred
  • filesystem read — automatically inferred
  • filesystem write — automatically inferred
  • credential access — automatically inferred
1 dependency and API indicators
  • api: github.com
External clawhub result: suspicious

This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.

Evidence checked
10/15/2026, 2:17:25 PM
Release binding
Matches this record
  • skillspector: suspicious
  • llm: suspicious

Recorded files

The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.

Package content hashsha256:4f85d801e178bc96a10bf4ae89d838e1aac438a3818240d8e75b1a8897709061
Show up to 30 recorded paths
  • CHANGELOG.md
  • config/claude-provider-registry.example.json
  • config/claude-provider-settings.example.json
  • config/codebuddy-auth-first-run.sh
  • config/harness-backend-policy.json
  • config/orchestration-personal.example.json
  • DECISIONS.md
  • LICENSE.txt
  • references/00-fast-dispatch-runbook.md
  • references/01-model-selection-matrix.md
  • references/02-runtime-dependencies.md
  • references/03-checkpoint-files.md
  • references/04-sentinel-design.md
  • references/05-legal-domain-patterns.md
  • references/06-agent-cli-reference.md
  • references/07-qoderwork-cli-worker.md
  • references/08-codebuddy-cli-worker.md
  • references/09-zcode-cli-worker.md
  • references/10-parallel-lessons.md
  • references/11-agent-teams-troubleshooting.md
  • references/12-issue-grouping.md
  • references/13-orca-cli-worker.md
  • references/14-pm-orchestrate.md
  • references/15-wave-autopilot.md
  • references/16-autopilot-durability.md
  • references/17-model-capability-profile.md
  • references/18-dispatch-acceptance-contracts.md
  • references/19-maintainer-validation.md
  • references/20-orca-rate-limit-recovery.md
  • references/21-zcode-quota-producer.md

Source changelog

首次以 multi-agent-orca 名义发布(v3.0.0 更名 + v3.0.1 收敛):PM 多 Agent 本地编排,Orca Run/Task/Dispatch + 独立 worktree + tmux 回退;由 2.x multi-agent-orchestration 更名而来,wire schema 与状态路径保持兼容,旧冻结目录已退役删除。