How do I install the Plan Debate skill?

Run npx skillmds add zirui-song/plan-debate in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Plan Debate safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Plan Debate?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Plan Debate free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Plan Debate?

zirui-song (@zirui-song) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Plan Debate by zirui-song — Agent Skill

Name: Plan Debate
Rating: 4.2 (5 reviews)
Author: zirui-song

Plan Debate

Use to run a multi-round cross-model debate on an implementation plan — Claude drafts, Codex (gpt-5.4) critiques against the real codebase, Claude rebuts and synthesizes, optional second Codex pass — converging on a stronger plan. Combines codex-review-plan and review-codex-plan. Trigger phrases include "debate this plan with Codex", "go back and forth with Codex on the plan", "have Claude and Codex argue out the plan".

zirui-song c84a59a 2.4 KB Updated Sep 10, 2026

File contents

plan-debate (Claude ⇄ Codex, round-trip)

Run a short, converging debate between Claude and Codex on a plan. The goal is a single stronger plan plus an honest record of where the two models still disagree.

Mechanics (wrapper, templates, timeout, output rules) live in the codex-bridge skill. This skill orchestrates codex-review-plan (Claude → Codex) and review-codex-plan (Codex → Claude) — read all three first.

Workflow

Ensure a plan exists. If there's an active ~/.claude/plans/ file or a plan the user supplied, use it. If not, draft one first via superpowers:writing-plans.
Round 1 — Codex critiques. Run the codex-review-plan flow: send the plan to Codex (read-only, in the project dir), get its critique. Then synthesize a revised plan as Claude, incorporating accepted points via superpowers:receiving-code-review (verify each point; push back with reasons on wrong ones).
Round 2 (optional) — focused re-review. Send the revised plan back to Codex with a focused prompt: "Were the following issues addressed? What gaps remain?" (list the round-1 issues). Synthesize again.
Stop condition. End when Codex raises no new substantive issue, or after N rounds (default 2) — whichever comes first. Don't loop indefinitely.
Output.
- Write the final converged plan to the plan file.
- Give a short per-round changelog (≤10 lines): what each round changed.
- Surface unresolved disagreements between Claude and Codex explicitly — state each side's position and your recommendation. Do not bury them.
- Note the temp paths holding each round's full Codex output.

Notes

Each Codex call uses a long Bash timeout (~600000 ms); xhigh is slow. For a faster debate, append -c model_reasoning_effort=high to the wrapper calls.
Codex runs read-only throughout — it cannot modify your files.
Keep chat output terse; full reviews stay in their temp files.

---name: plan-debatedescription: Use to run a multi-round cross-model debate on an implementation plan — Claude drafts, Codex (gpt-5.4) critiques against the real codebase, Claude rebuts and synthesizes, optional second Codex pass — converging on a stronger plan. Combines codex-review-plan and review-codex-plan. Trigger phrases include "debate this plan with Codex", "go back and forth with Codex on the plan", "have Claude and Codex argue out the plan".---# plan-debate (Claude ⇄ Codex, round-trip)Run a short, converging debate between Claude and Codex on a plan. The goal is asingle stronger plan plus an honest record of where the two models stilldisagree.Mechanics (wrapper, templates, timeout, output rules) live in the**`codex-bridge`** skill. This skill orchestrates `codex-review-plan` (Claude →Codex) and `review-codex-plan` (Codex → Claude) — read all three first.## Workflow1. **Ensure a plan exists.** If there's an active `~/.claude/plans/` file or a plan the user supplied, use it. If not, draft one first via **`superpowers:writing-plans`**.2. **Round 1 — Codex critiques.** Run the `codex-review-plan` flow: send the plan to Codex (read-only, in the project dir), get its critique. Then **synthesize a revised plan** as Claude, incorporating accepted points via **`superpowers:receiving-code-review`** (verify each point; push back with reasons on wrong ones).3. **Round 2 (optional) — focused re-review.** Send the *revised* plan back to Codex with a focused prompt: "Were the following issues addressed? What gaps remain?" (list the round-1 issues). Synthesize again.4. **Stop condition.** End when Codex raises no new substantive issue, or after **N rounds (default 2)** — whichever comes first. Don't loop indefinitely.5. **Output.** - Write the final converged plan to the plan file. - Give a short **per-round changelog** (≤10 lines): what each round changed. - **Surface unresolved disagreements** between Claude and Codex explicitly — state each side's position and your recommendation. Do not bury them. - Note the temp paths holding each round's full Codex output.## Notes- Each Codex call uses a long Bash timeout (~600000 ms); `xhigh` is slow. For a faster debate, append `-c model_reasoning_effort=high` to the wrapper calls.- Codex runs **read-only** throughout — it cannot modify your files.- Keep chat output terse; full reviews stay in their temp files.

Frequently asked questions