Lawful AI Daily Brief — 2026-04-23

🛠️ Tool Updates

• Claude Code kept shipping at “espresso x2” speed: MCP tools can now be called directly from hooks (type: "mcp_tool"), /usage now combines cost+stats, and /resume got smarter.
• Codex CLI v0.123.0 added Amazon Bedrock provider support, better /mcp verbose diagnostics, cleaner realtime handoffs, and fixed sticky “Working” states.
• Community pulse: awesome-claude-code was mostly automation churn (repo ticker refreshes), not a big new-skills day.

💡 Tip of the Day

If you’re wiring legal/compliance automation, make every subagent decision auditable by default:

{
  "mcpServers": {
    "legal-audit": { "command": "node", "args": ["audit-mcp.js"] }
  },
  "hooks": [
    {
      "event": "SubagentStop",
      "tool": { "type": "mcp_tool", "name": "legal-audit.record" }
    }
  ]
}

⚖️ Legal x AI Watch

• Fresh regulation-adjacent repos updated in the last 24h:
  • Hasanjaafar/ai-academic-regulations-chatbot — RAG assistant over university regulations.
  • dislovelhl/acgs-lite — governance/safety layer with EU AI Act framing.
  • Jozithe3019/ai-act-guardian — EU AI Act-oriented compliance auditing for Python projects.
• Compliance nudge: keep prompt/response hashes + tool-call logs, so audits are boring (in the best possible way).

📚 Fresh Papers

• Exploiting LLM-as-a-Judge Disposition on Free Text Legal QA via Prompt Optimization
  http://arxiv.org/abs/2604.20726v1
• CHASM: Unveiling Covert Advertisements on Chinese Social Media
  http://arxiv.org/abs/2604.20511v1
• Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation
  (new RAG eval framing from latest digest)

📈 Trending Repos

Top new repos (latest snapshot):

• Russell-cell/PPT-Design-Prompt ⭐58
• SparkEngineAI/QuantClaw-plugin ⭐49
• Yu9191/sub-store-workers ⭐33

AI/LLM giants still sprinting:

• Significant-Gravitas/AutoGPT ⭐183k+
• langgenius/dify ⭐138k+
• firecrawl/firecrawl ⭐111k+

🎤 Standup One-Liner

“Yesterday we upgraded our agent stack for faster execution and stronger auditability—so we can ship quickly and sleep well during compliance reviews.”

---

Repo: https://github.com/laugustyniak/lawful-ai-staging