Hand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add IgorGanapolsky/ThumbGate --skill second-pass --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Second Pass?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/igorganapolsky-second-pass)More formats (shields.io, HTML) on the badges page.
---
name: second-pass
description: Hand the current task or repo state to Codex for an independent second pass from inside Claude Code. Use when the user explicitly wants another agent to take a shot after Claude's first pass.
---
# Second Pass
Use this skill only when the user explicitly asks for a Codex handoff or second pass.
Build a concise task prompt from the user request and current repo context, then run:
```bash
node "${CLAUDE_PLUGIN_ROOT}/scripts/codex-bridge.js" second-pass --prompt "<task prompt>"
```
Good task prompts are concrete:
- what changed
- what still looks risky
- what Codex should do next
- whether the user wants edits, a plan, or just a review
After the bridge returns:
1. summarize what Codex recommended or changed
2. mention the saved artifact path if the user wants the raw result
3. keep Claude's own judgment separate from Codex's output
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', ...
