add AGENTS.md to commit-analyzer

[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: purpose, domain position, quick-start commands, tech stack, project structure, and hard boundaries.
• Adds CLAUDE.md as a thin pointer (@AGENTS.md) so Claude Code picks up the same file.
• Content was generated + audited by two autonomous AI passes against the actual repo files.

Review Summary:

The structure and commands in AGENTS.md are accurate against the repo — scripts, file paths, and Node engine version all check out. Two issues were found: the runtime dependency list omits debug and import-from (both present in package.json), and the auto-generated disclaimer contradicts the PR's own claim of a thorough verification pass, which could mislead future agents consuming this document.

Follow-up suggestions:

• @devloai fix the two identified issues in AGENTS.md (missing deps + contradictory disclaimer)

[devloai]

Two runtime dependencies are missing from this list: debug and import-from. Both are present in package.json under dependencies. Since this document is intended to give agents an accurate picture of the dependency graph, omitting them defeats that purpose.

Suggested change

	**Observed dependencies:** `conventional-commits-parser`, `conventional-commits-filter`, `conventional-changelog-angular`, `lodash`
	**Observed dependencies:** `conventional-commits-parser`, `conventional-commits-filter`, `conventional-changelog-angular`, `debug`, `import-from`, `lodash`

⚡ 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 contradicts the PR description. The PR says a second agent "audited every command, path, and name against actual files" and applied a "be right or be silent" standard — implying the content was verified. Yet this footer tells agents (and humans) "not manually verified."

This creates a trust problem: agents that read this caveat may discount the document's accuracy, or worse, re-verify everything from scratch on every task. If verification was actually done, remove or reword this disclaimer accordingly.

Suggested change

	> ⚠️ Auto-generated by AI agent via blind repo scan. Contents reflect observed code at time
	> of generation — not manually verified. Review and update when this repo next changes.
	> ⚠️ Auto-generated by AI agent and audited against actual repo files at generation time. Review and update when this repo next changes.

⚡ 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>