Add multi-agent collaboration system with 16-person team and two-tier governance

- agents/README.md documents company principles (first principles + practical
  delivery), 6-stage collaboration flow, and two-tier governance: CEO has
  highest priority and final say; work groups self-govern internally for
  staffing, scheduling, technical choices within CEO-defined boundaries.
- 16 employees recruited to match CPU physical core count, enabling up to
  16 subagents to run in parallel. Each profile.md has independent name,
  background, strengths, weaknesses, and performance log.
- Roles: 1 CEO, 3 architects (lin/yang/huang), 5 engineers (zhao/chen/li/
  zhou/sun), 3 QA (wang/liu/xu), 2 DevOps (ma/hu), 1 designer (zhu),
  1 writer (deng), 1 security (cao).
- Five working groups defined under agents/groups/: grp-quality-core,
  grp-ai-plugins, grp-cli-ux (B3), grp-build-matrix, grp-security-audit.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

agents/groups/grp-security-audit.md

@@ -0,0 +1,18 @@
+---
+group_id: grp-security-audit
+name: 安全审计小组
+members:
+  - security-cao
+  - qa-xu
+  - qa-liu
+mission: 全面审计 dstalk 的内存安全、API 密钥处理、反序列化路径
+lead: security-cao
+created: 2026-05-27
+active_tasks: []
+standby: true
+---
+
+## 协作模式
+- 曹武：威胁建模，列出可疑路径清单
+- 徐磊：用 ASan/UBSan 跑测试，触发实际漏洞
+- 刘静：用 fuzzing 覆盖输入边界