docs: bootstrap AGENTS.md + CLAUDE.md shim (BE-3582)

[mattmillerai]

ELI-5

Agents (Claude Code, Cursor, etc.) look for a file that tells them how to work in
a repo. The cross-tool standard is AGENTS.md; Claude Code specifically reads
only CLAUDE.md and won't fall back. This repo had neither, so agents touching
these shared CI workflows got zero guidance. This PR adds a tight AGENTS.md
(the real source of truth) and a one-line CLAUDE.md shim that imports it — so
every agent, including Claude, gets the same instructions.

What this does

• AGENTS.md (108 lines) — authored from the repo's actual contents:
  one-paragraph purpose, the exact build/test commands, the .github/ directory
  map, the reusable-workflow catalog, and the repo's real conventions/gotchas
  (public-repo caller-name masking, full-SHA pin policy, scripts-as-single-
  source-of-truth tamper-proofing, the one-bumper rule, Conventional Commits +
  (BE-####) suffix, semver major tags).
• CLAUDE.md — exactly the canonical @AGENTS.md shim, nothing else.

Implements the 2026-07-15 "Pillar 1: Agentic Engineering" standard — the same
one this repo's own agents-md-integrity.yml workflow enforces on consumers.

Verification

• python3 .github/agents-md-integrity/check_agents_md.py --root . → passes
  (108 < 200-line ceiling, valid @AGENTS.md shim, no .cursorrules). Only the
  warn-level "no CODEOWNERS DRI" note remains — see judgment calls below.
• Every command listed in AGENTS.md was copied verbatim from the CI
  test-*.yml run: steps and executed locally green:
  • cursor-review tests — 19 passed
  • agents-md-integrity tests — 18 passed
  • bump-callers tests — 25 passed
• Change is additive root-markdown only; no path-filtered test-* workflow
  fires on these paths, so nothing existing is affected.

Judgment calls

• CODEOWNERS left out of scope. The integrity checker emits a warn-level
  "no DRI" note; it is not a failure, and picking a DRI is a decision the ticket
  doesn't specify. Scoped this PR to AGENTS.md + CLAUDE.md per the ticket.
  Adding a CODEOWNERS rule for AGENTS.md is a clean follow-up.

[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: 54 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: 83e90382-9740-4ee9-aa1f-a3b6dd61e948

📥 Commits

Reviewing files that changed from the base of the PR and between cb4e09a and f51471f.

📒 Files selected for processing (2)

• AGENTS.md
• CLAUDE.md

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch matt/be-3582-agents-md

✨ Simplify code

• Create PR with simplified code
• Commit simplified code in branch matt/be-3582-agents-md

---

_{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)