← ClaudeAtlas

rami-rebut-findinglisted

Use when the user wants to challenge, rebut, or dispute a Rami code review finding — phrases like "rebut this", "this is a false positive", "Rami is wrong about X", "tell Rami this is intentional". Walks through the right MCP tool to use, the four valid rebut reasons, and what to do when Rami rejects the rebuttal.
rami-code-review/claude-code-marketplace · ★ 0 · AI & Automation · score 62
Install: claude install-skill rami-code-review/claude-code-marketplace
# Rami Rebut Finding Use the Rami MCP `rebut` tool to challenge a finding. This is the only sanctioned channel for disagreement. Nothing posted to the GitHub review thread itself — whether via the web UI, the REST/GraphQL API, the `gh` CLI, or any GitHub MCP server — flows into Rami's state machine. ## Decide first: rebut, fix, defer, or dismiss | Situation | Tool | |-----------|------| | The finding is wrong (false positive, framework guarantee, intentional design, duplicate) | `rebut` | | The finding is correct but you want to fix it | normal Edit + commit + push, then re-run `get_review_results` | | The finding is correct and valid but out of scope for this PR | `defer` (acknowledges and stops re-raising) | | The user has explicitly told you to discard the finding without evaluation | `dismiss` (user-asked-only escape hatch) | | You don't have evidence for any of the four rebut reasons | Fix it. Do not rebut to avoid work. | ## Valid rebut reasons A rebuttal must rest on one of these four: 1. **False positive** — the code does not exhibit the behavior Rami claims. Cite the specific line that disproves the claim. 2. **Framework guarantee** — the surrounding framework, runtime, or library handles the case Rami is worried about. Name the framework and the guarantee. 3. **Intentional design** — the code is deliberate, and the trade-off is documented or otherwise defensible. Cite the rationale. 4. **Duplicate** — the same finding has already been raised and addressed else