pi-multi-review

pi-multi-review is a command for Claude Code from tznthou/claude-prism. It costs 13 tokens per session (6,031 once invoked), scanned A, original, MIT.

A command that sends the same code change to Codex and Gemini, two separate AI assistants, for hostile review, then asks Claude to combine their findings.

In plain words
What is it for?
Review a change from security and data-integrity angles with Codex, from design, user experience, and maintainability angles with Gemini, and receive a combined review from Claude.
Why use it?
Different reviewers can notice different classes of problems, reducing the chance that one assistant's blind spots go undetected.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions subagents.

Good fit Review a change from security and data-integrity angles with Codex, from design, user experience, and maintainability angles with Gemini, and receive a combined review from Claude.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/tznthou/claude-prism/pi-multi-review
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/tznthou/claude-prism

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pi-multi-review

README.md
[![agentmods](https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-multi-review/github.svg)](https://agentmods.dev/commands/tznthou/claude-prism/pi-multi-review)
Your own site
<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-multi-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-multi-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pi-multi-review

Your own site · 80×15
<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-multi-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-multi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,031 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00013 $0.06031
Opus 5 $0.00006 $0.03016
Sonnet 5 $0.00003 $0.01206
Haiku 4.5 $0.00001 $0.00603

Measured 12d ago against content hash 347fe20f7a68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

pi-multi-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/pi-multi-review.md · 478 lines

How it starts

The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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 (v0.13.0+): For parallel provider consultation, use the Agent tool with subagent_type: "general-purpose" to spawn two parallel sub-agents — NOT two Bash tool calls in a single main-conversation response. Main-conversation Bash is a structural FIFO queue: the second Bash waits for the first to finish (delta ≈ first_exec precisely, measured N=7 across two capacity slots), which defeats the parallel intent. Sub-agent fan-out dispatches Bash calls truly in parallel (median delta 2.8s, N=13), saving roughly 28% wall-clock on a two-provider call.

Inside each sub-agent, run call-codex.sh / call-gemini.sh in foreground synchronous mode with timeout: 600000 (Bash tool's 10-minute ceiling). Do not use &, nohup, or run_in_background: true — Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the child (output file stays 0 bytes). If a sub-agent's Bash returns empty stdout, the Bash template below falls back to reading the caller-owned $OUT_PATH file (v0.14.3+, wrapper tees here via CLAUDE_PRISM_OUT_TMP).

1. Determine review scope

Same as /pi-code-review, based on $ARGUMENTS:

  • No args → staged changes
  • File path → specified file
  • --diff → unstaged changes
  • --pr → PR diff
  • --verbose → also show issues that were filtered out (< 80 confidence) with their scores

2. Get the code

Use Bash / Read tool. The same code goes to both providers.

2.3 Gather project guidelines

Search for project guideline files to use as compliance context:

# Check common locations for guideline files
for f in CLAUDE.md .claude/CLAUDE.md Agents.md .claude/Agents.md; do
  [ -f "$f" ] && echo "=== $f ===" && cat "$f"
done

Read the full file on GitHub · 478 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 478 lines · 13 tokens per session scan A 347fe20f7a68

Subscribe to this mod's changes

pi-multi-review is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 6,031 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.