feat(reflex): add Reflex Alignment use case

[0xnavarro]

Public change

Adds Reflex Alignment as one flagship Brida Reflex use case: a bounded inference-time semantic supervision gate before consequential agent actions. The public README intentionally combines the problem, execution pattern, configuration, authority boundary, and ReflexBench measurement guidance in one concise example.

Validation

• I used only public/synthetic data.
• I did not copy private Brida material.
• Public-surface checks pass.
• No secrets, internal URLs/IDs or customer data are included.
• This PR does not weaken security/review policy.
• Commits are narrowly scoped and atomic.

Review / QA evidence

Validated locally on Node 24 with pnpm check: registry validation passes, focused Reflex skills are synchronized, 27/27 tests pass, and the full-history public leak scan passes. GitHub CodeQL and Public Registry CI are green. The alignment example includes synthetic aligned, review, and misaligned fixtures.

Compatibility / risk

Additive public example only. No existing recipe, schema, hosted API, authorization model, or execution authority is changed. Reflex output remains recommendation-only and the host retains deterministic authorization and side-effect control.

Release intent

• release-impact: patch
• release-note: Add Reflex Alignment, a public execution-supervision use case and focused skill for evaluating proposed agent actions against explicit execution principles before host-controlled execution.
• qa-scope: Validate registry and generated skills, run the full Node 24 test suite and public-surface leak scan, and verify the Reflex Alignment synthetic aligned/review/misaligned fixtures.

[chatgpt-codex-connector]

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review	Status	Commit	Review trigger
🔒 Security Review	✅ Completed 2026-09-23T19:37:07.234602Z	feeb649	PR opened

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.