What it doesAI
Governance plugin for orchestrated multi-agent development with task routing, human approval, and audit events.
- Deterministic task routing with explicit human approval
- Coordinates Codex, Claude Code, and DeepSeek Harness agents
- Governance session events for replayable audit facts
AI-generated from the repo README — for reference only.
Installation
dsh plugin --profile web add github:EnglandTong/governance-multi-agent-harnessInstall method: GitHub · not yet tested in container (L3+)
Compatibility
| DSH Version | Status |
|---|---|
| not stated | Declared — not tested |
Requirements
- • Node.js: not stated
- • DSH: declared "not stated"
- • External credentials: none detected
Security Report
Automated static scan, not manual review.
No critical or warning findings in the automated scan. The result is valid only for the commit hash shown.
—9763e69b327a2026-08-209763e69b327aThe scan result is valid for the scanned commit. New commits within 7 days are tolerated (the rating still counts); after 7 days without a rescan the badge shows outdated.
Disclaimer: automated static analysis, not a security guarantee. Always review what you install.
vet verdict: vet: clean · score 87
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.pid
- R9 · medium [likely] — 循环内集合写入 map.set（无界增长信号）
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.argv
- R3 · info [certain] (downgraded) — 只读 process 成员（能力触达面）：process.exitCode
- R3 · info [certain] — 只读 process 成员（能力触达面）：process.argv
vet is advisory and does not change dsh’s four-tier level.
• Static heuristic scan: done (10 files)
• Dependency vulnerabilities: requires deep audit (L3+)
• Permission sandboxing: requires runtime testing (L4+)
Activity
Last commit 2026-08-20 · activity: Active
• Repo created: 2026-08-20
• Stars: ★ 0 · Forks: 0
• Health: Active — committed within last 30 days
Source
GitHub: github.com/EnglandTong/governance-multi-agent-harness