agent: @U0AJM7X8FBR @U0AJM7X8FBR become an expert at this repo https://github.c#3
Conversation
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. ℹ️ Review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (7)
✨ Finishing Touches🧪 Generate unit tests (beta)
📝 Coding Plan
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment Tip CodeRabbit can generate a title for your PR based on the changes.Add |
Removes the send_email MCP tool from the chaining section. No REST equivalent ships yet (only /api/emails/inbound + admin-only GET), and the rest of the skill is intentionally portable over plain REST — assuming MCP would make this section the odd one out. Reframes the skill as producing drafts that the user sends themselves rather than executing external-facing actions. Changes: - Chain-pattern table: "Data → Action" renamed "Data → Draft" - "Tools this skill chains into" renamed "What this skill produces" - Rule #3 rewritten: "Draft, don't execute" — no approval gate needed because no execution happens - Example A renamed "Peer collab outreach draft"; Steps 5-6 (approval gate + send_email call) removed; Step 4 extended to say drafts are presented for the user to send manually - "When NOT to chain" bullet retargeted from external-facing actions to workspace writes Examples B and C were unaffected (neither used send_email). Made-with: Cursor
- scripts/run_resolver_eval.py: LLM-tier router system prompt referenced the old "recoup-records plugin" → "Recoup Skills plugin" (cubic #1). - resolver-eval.jsonl: add adversarial gating negatives so the eval defends the invariant that internal skills must NOT fire without the recoup-internal keyword (de-gated valuation/caption/overview requests route to the customer skill, not the internal one). The dev/eval internal skills have no customer-request surface, noted inline (cubic #2). - README.md: reword the Manual install so it matches the flat-plugin architecture (the repo root is the plugin) instead of "point your agent at skills/" (cubic #3). - hooks/check-env.sh: same stale-"recoup-records" class as cubic #1 — updated the SessionStart directive to "Recoup Skills". All five validators still exit 0 (eval: 40 positives + 10 adversarial negatives). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
1 participant
Automated PR from coding agent.