Menu
Ask Claude to audit Codex's work. Use when the user wants a second opinion, Claude audit, independent review, or a check of Codex changes.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Basé sur la classification professionnelle SOC
This skill should be used when the user asks about libraries, frameworks, API references, or needs code examples. Activates for setup questions, code generation involving libraries, or mentions of specific frameworks like React, Vue, Next.js, Prisma, Supabase, etc.
Respond to code review comments point by point, quoting each reviewer point verbatim and answering directly beneath it.
Use when moving local sessions between Claude Code and Codex, converting Claude Code JSONL into Codex rollout format, converting Codex rollout JSONL into Claude scrollback, or debugging cross-agent resume state.
Use when moving local sessions between Codex and Claude Code, converting Codex rollout JSONL into Claude scrollback, converting Claude Code JSONL into Codex rollout format, or debugging cross-agent resume state.
Operate remote hosts over SSH through the ssh-mcp server, driving a box like a person at a terminal instead of firing blind one-off commands.
Use when a task involves SSH or a remote host, including remote commands, interactive shells, sudo over SSH, tailing logs, deployments, scp or rsync file transfer, and port forwards or tunnels.
| name | claude-second-opinion |
| description | Ask Claude to audit Codex's work. Use when the user wants a second opinion, Claude audit, independent review, or a check of Codex changes. |
| metadata | {"short-description":"Ask Claude to audit Codex work"} |
Invokes Claude in a constrained, read-only audit mode to look for bugs, dead code, tech debt, and architectural errors.
Resolve the claude-audit helper next to this SKILL.md.
Run it with the user's focus text, file path, or no argument. Prefer a path or concrete focus when the user gives one:
./claude-audit <focus-or-path>
Print the full output directly for the user. Do not soften, summarize away, or reinterpret the findings.
If the helper exits with a timeout, print the timeout output, then rerun once with a narrower path or focus string from the user's request. Say clearly that the broad audit timed out.
CLAUDE_AUDIT_TIMEOUT_SECONDS (default 180) and CLAUDE_AUDIT_MAX_BUDGET_USD (default 1) to avoid silent hangs.