prompt-alignment-audit

对提示词按模型厂商规范进行合规性审计与重写。

對 LLM 的 system/模板或抽取 prompt 做合規與效能稽核，會依模型廠商（如 Anthropic、OpenAI、Gemini）和特定版本的建議出具有依據的報告與重寫建議。當 prompt 表現不佳、換模型或要上線前都該做一次審核。不會直接改生產 prompt 檔案，而是提供可驗證的改寫與最佳實務建議。

# Prompt Alignment Audit

Audit a prompt against the **current, model-version-specific** recommendations of its
provider, then produce a citation-backed report and a fully justified rewrite. A rewrite is
a hypothesis: prove it with the project's eval harness when one exists; otherwise state
plainly that confidence is compliance-based.

**Never edit a production prompt file without explicit user approval.**

## Cost policy (non-negotiable)

All heavy reading — doc research, prompt-file reading, per-dimension audits — is done by
**Sonnet subagents** (`model: "sonnet"`) returning compact structured findings. The
orchestrator never reads raw provider docs and never pastes full documents into con