Run a Codex review from Claude Code against the current uncommitted work, a base branch diff, or a specific commit. Use when the user explicitly asks for a Codex review or second reviewer.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add IgorGanapolsky/ThumbGate --skill review --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Review?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/igorganapolsky-review)More formats (shields.io, HTML) on the badges page.
---
name: review
description: Run a Codex review from Claude Code against the current uncommitted work, a base branch diff, or a specific commit. Use when the user explicitly asks for a Codex review or second reviewer.
---
# Review
When this skill is invoked, translate the request into one of these bridge calls:
- default: current uncommitted work
- `base=<branch>`: compare against a branch such as `main`
- `commit=<sha>`: review one commit
Prefer these forms:
```bash
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" review --uncommitted
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" review --base main
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" review --commit <sha>
```
If the user gave a focus area, pass it as `--prompt "..."`.
After the bridge returns:
1. summarize the highest-signal findings
2. mention the saved artifact path if the user may want to inspect the raw result
3. do not pretend Codex found issues if the result says no issues
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!
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', ...
