Pi Multi Review — Development skill for Claude Code
Triple-provider adversarial review — Codex + Gemini + Claude synthesis.
How to install Pi Multi Review
Installs to ~/.claude/skills/tznthou-claude-prism-pi-multi-review/SKILL.md
mkdir -p ~/.claude/skills/tznthou-claude-prism-pi-multi-review && curl -fsSL https://raw.githubusercontent.com/tznthou/claude-prism/HEAD/commands/pi-multi-review.md -o ~/.claude/skills/tznthou-claude-prism-pi-multi-review/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Pi Multi Review does
command: pi-multi-review description: Triple-provider adversarial review — Codex + Gemini + Claude synthesis
Multi-Provider Adversarial Review (Codex + Gemini + Claude)
Send the same code to both Codex and Gemini for **adversarial review with divided attack surfaces**, then Claude synthesizes. Codex attacks security & data integrity; Gemini attacks design, UX & maintainability. **Three adversarial perspectives, maximum blind spot elimination.**
Execution
**Dispatch rules (v0.1
Alternatives in Development
- Om Weekly — Weekly synthesis — cross-session review of vault activity, North Star alignment, patterns, uncaptured wins, an 4.6k ★
- Providers — Multi-Provider Support 1.1k ★
- Claude Code Skill — Persistent multi-engine coding session manager 326 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Otherside CLI
Totally Free Claude Code inspired terminal coding agent. Multi-provider: Anthropic, Codex, Gemini, Kimi, DeepS
DevOrch
A terminal-native, multi-provider intelligent assistant that plans, executes, and tracks developer tasks, not
Agy Review
Adversarial critique via agy using Gemini Pro — independent second opinion on code, plans, or arguments
Pi Askall
Ask both Codex and Gemini the same question — get three perspectives with Claude synthesis
Review Sequence
/review-sequence — Multi-role adversarial review protocol
Review Fanout
Adversarial multi-dimension review of the current diff, with refutation
Related Agents
LLM Orchestrator
Use this agent for LLM integration work — prompt engineering, multi-provider abstraction (OpenRouter, Gemini,
Consult Agent
Execute cross-tool AI consultations via Task spawning. Use when agents or workflows need a second opinion from
Codex Deep Reasoner
CLI-backed read-only deep-reasoning worker — the codex variant of deep-reasoner. Use for root-cause analysis,