← ClaudeAtlas

rail-reviewerlisted

Run independent code, repository, implementation, performance, safety, or final-quality reviews through the Rail Connector MCP. Use when the user asks Codex to have Claude review work, inspect or find gaps, search prior Claude sessions for review continuity, provide a second opinion, or produce a report, including explicitly requested Ultracode or bypass capability validation.
SNComrade/Rail-Connector-MCP · ★ 0 · AI & Automation · score 68
Install: claude install-skill SNComrade/Rail-Connector-MCP
# Rail Connector Reviewer Use Claude as an independent reviewer, then verify its claims locally. Claude output is evidence, not authority. ## Rules - Use the target project's real same-OS `cwd`, not this skill repo unless this MCP itself is under review. - If MCP tools are unavailable, report that a fresh Codex task or restart is needed. Never imply that Claude reviewed something when it did not. - Ground branch, status, diff, relevant code, docs, and tests before prompting Claude. - Default report-only reviews to `permissionMode: "dontAsk"` when the installed CLI advertises it, plus explicit no-edit constraints. `dontAsk` denies new permission requests while allowing read-only inspection. Use `plan` only as a compatibility fallback; never approve implementation from a report-only review. Report-only is verified by pre/post repository evidence; it is not an operating-system sandbox. Deny `Edit`, `Write`, and `NotebookEdit`, constrain shell use to inspection, and use a read-only copy when hard isolation matters. - Leave `trustWorkspace` false unless the user explicitly authorizes trust after project configuration and hooks are inspected. - Honor an explicit user request for Ultracode with `ultracode: true`, `confirmUltracode: true`, and no ordinary effort. - Honor an explicit user request to test or use bypass only when capability inspection reports policy enabled and the call includes `confirmBypassPermissions: true`. Do not independently elevate