docs: add CLAUDE.md shim importing AGENTS.md (BE-3537)

[mattmillerai]

ELI-5

Claude Code only looks for a file called CLAUDE.md for its instructions — it never reads AGENTS.md and doesn't fall back to it. This repo keeps its agent instructions in AGENTS.md (the cross-agent standard), so Claude Code sessions were getting zero instructions. This PR adds a tiny CLAUDE.md that just @-imports AGENTS.md, so Claude Code now picks up the same instructions every other agent already reads.

What changed

• Added root CLAUDE.md containing exactly the org-standard shim (an HTML comment explaining it's a shim + @AGENTS.md), per the 2026-07-15 "Pillar 1: Agentic Engineering" guide and the org-wide audit (BE-3241).

What did NOT change

• AGENTS.md is untouched (the single source of truth stays canonical).
• No .cursorrules added/removed (none exists; modern tools read AGENTS.md).
• No nested AGENTS.md files exist, so no nested shims were needed.

Verification

• CLAUDE.md content is byte-for-byte the canonical shim (em-dash preserved as UTF-8).
• Relevant pre-commit hooks pass on the new file: end-of-file-fixer ✅, trailing-whitespace ✅ (ruff/toml/uv hooks skip — no matching files).
• Doc-only change; no Python/CLI behavior touched, so pytest/ruff/mac/windows suites are unaffected.

Closes BE-3537.

[coderabbitai]

Warning

Review limit reached

You’ve reached a temporary PR review limit under our Fair Usage Limits Policy.

Your recent review volume is higher than typical usage, so adaptive limits are currently applied.

Next review available in: 14 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro Plus

Run ID: 689e87a9-7f33-4feb-9efa-8282b1973538

📥 Commits

Reviewing files that changed from the base of the PR and between a732f5c and d8fa528.

📒 Files selected for processing (1)

• CLAUDE.md

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch matt/be-3537-claude-md-shim

✨ Simplify code

• Create PR with simplified code
• Commit simplified code in branch matt/be-3537-claude-md-shim

---

_{Comment @coderabbitai help to get the list of available commands.}

[github-actions]

🔍 Cursor Review — Consolidated panel

Triggered by @mattmillerai.

✅ No high-signal findings.

Panel: 6/8 reviewers contributed findings.

Reviewers that did not contribute: kimi-k2.5:adversarial (empty), kimi-k2.5:edge-case (empty)