Portable code-review checklist. Use before a commit/PR or after a non-trivial change. Run it in a separate read-only helper when your runtime supports one; Sober ships the checklist, not a fixed reviewer.
Scanned 9/7/2026
Install to Claude Code
Skills Directorynpx -y skills add move-hoon/claude-pro-minmax --skill sober-review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Sober Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/move-hoon-sober-review)More formats (shields.io, HTML) on the badges page.
---
name: sober-review
description: Portable code-review checklist. Use before a commit/PR or after a non-trivial change. Run it in a separate read-only helper when your runtime supports one; Sober ships the checklist, not a fixed reviewer.
---
# Sober Review
Use this skill to review changed code against Sober's checklist.
Sober owns the portable checklist, not the reviewer implementation. Run the checklist in a separate read-only helper when the runtime supports that:
- Claude Code: ask for a read-only subagent or your own user-level reviewer.
- Codex: ask Codex to spawn a helper/reviewer subagent, or use a custom reviewer agent you installed.
- If no helper is available, self-review with this checklist before committing.
Read `references/checklist.md` first. If the change touches security-sensitive code, also read `references/security.md`. If the change adds or changes behavior, also read `references/tests.md`.
Return only:
```text
REVIEW: <path or diff>
Verdict: PASS | CHANGES REQUESTED
- [CATEGORY] file:line — issue -> fix
```
Use `PASS` only when there are no issues. A review reports findings; it never edits files or runs deploy/build commands.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
