add AGENTS.md to github-action-datadog-reporting

[jsr6720]

Summary

Adds AGENTS.md to give AI agents working in this repo instant orientation:

• What this service does and where it fits in Clearcover's platform
• Domain position (layer, domain, what it owns, who calls it, what it calls)
• Quick start commands (install, test, lint, build) — verified against actual repo files
• Tech stack, project structure, code style, and git workflow
• Hard boundaries (what the agent must never do)

Process

Generated and verified in two autonomous passes:

1. Generation — agent scanned the repo and wrote AGENTS.md
2. Verification — second agent audited every command, path, and name against actual files;
   removed anything it could not confirm ("be right or be silent")

---

🤖 Generated with Claude Code

Co-Authored-By: Claude Sonnet 4.6 noreply@anthropic.com

[devloai]

PR Summary:

Adds AGENTS.md to orient AI agents working in this repo, covering: purpose, domain position, quick-start commands, tech stack, project structure, and hard boundaries. Also adds CLAUDE.md as a pointer alias (@AGENTS.md). The content was generated and reportedly verified by two autonomous AI passes.

Review Summary:

The structure and most factual content of AGENTS.md checks out against the actual repo files — script arguments, ACTION enum values, file paths, and gem dependencies are all accurate. Two internal contradictions were flagged:

1. The Boundaries section tells agents to "run tests before pushing" while the Tech stack section explicitly documents no tests exist.
2. The footer disclaimer claims the content is unverified (blind scan), directly contradicting the PR description's claim of a full verification pass.

Follow-up suggestions:

• @devloai fix the two identified contradictions in AGENTS.md
• @devloai add a basic test scaffold (e.g., RSpec or minitest) so the "run tests before pushing" boundary instruction actually has something to run against

[devloai]

The "Always" boundary says "run tests before pushing", but the Tech Stack section on line 37 explicitly states "Test: none". Telling agents to run non-existent tests before pushing is contradictory and will confuse them.

Suggested change

	**Always:** run tests before pushing · respect domain boundaries above · no secrets in commits
	**Always:** respect domain boundaries above · no secrets in commits

Or, if test infrastructure is planned, add a placeholder note; otherwise just remove the instruction.

⚡ Apply quick fix

actions

Quick Fix: Apply a small focused fix for this specific issue (takes < 1min).

Feedback: Rate this comment to help me improve future code reviews:

• 👍 Good - Helpful and accurate
• 👎 Poor - Wrong, unclear, or unhelpful
• Skip if you don't have any strong opinions either way.

[devloai]

The footer disclaimer says contents were not manually verified and are based on a "blind repo scan", but the PR description explicitly claims a second autonomous pass verified every command, path, and name. These two statements directly contradict each other.

If the verification pass actually happened, remove the disclaimer — having it here undermines agent confidence in the whole file. If the content is still unverified, the PR description is misleading.

⚡ Apply quick fix

actions

Quick Fix: Apply a small focused fix for this specific issue (takes < 1min).

Feedback: Rate this comment to help me improve future code reviews:

• 👍 Good - Helpful and accurate
• 👎 Poor - Wrong, unclear, or unhelpful
• Skip if you don't have any strong opinions either way.

[jsr6720]

🤖 AI review complete — seeking human approval

This AGENTS.md was generated in two autonomous passes (generation + accuracy verification), then devloai inline comments were addressed.

Please verify:

• Domain position — layer, domain, what it owns, who calls it, what it calls
• Quick start commands — do these work in your local dev setup?
• Project structure — does the tree reflect reality?
• Any items flagged "for human review" inside the AGENTS.md itself

If anything is wrong, just edit AGENTS.md directly on this branch and push — no need to close and reopen.

---

🤖 Generated with Claude Code · Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>