pi-code-review

pi-code-review is a command for Claude Code from tznthou/claude-prism. It costs 17 tokens per session (3,629 once invoked), scanned A, original, MIT.

A command that asks Codex, a separate AI coding assistant, to attack a code change and look for reasons it could fail.

In plain words
What is it for?
Review staged or unstaged changes, a specific file, or a pull request (a proposed code change), with an optional verbose list of lower-confidence findings.
Why use it?
It reduces blind spots when the same assistant that wrote the code would otherwise review it. The review focuses on finding problems rather than confirming that the change looks correct.

Command for Claude Code

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

Good fit Review staged or unstaged changes, a specific file, or a pull request (a proposed code change), with an optional verbose list of lower-confidence findings.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-code-review.svg)](https://agentmods.dev/commands/tznthou/claude-prism/pi-code-review)
Your own site
<a href="https://agentmods.dev/commands/tznthou/claude-prism/pi-code-review"><img src="https://agentmods.dev/badge/commands/tznthou/claude-prism/pi-code-review.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,629 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 $0.00017 $0.03629
Opus 5 $0.00009 $0.01814
Sonnet 5 $0.00003 $0.00726
Haiku 4.5 $0.00002 $0.00363

Measured 7d ago against content hash 3816fe135dc5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

pi-code-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 7d 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-code-review.md · 308 lines

How it starts

The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Adversarial Code Review via Codex

Use Codex CLI to adversarially review code. Core value: the AI that wrote the code (Claude) is NOT the one reviewing it (Codex) — eliminates same-source blind spots. The reviewer's job is to break confidence in the change, not validate it.

Execution

Bash invocation rules (v0.12.3+): Call call-codex.sh / call-gemini.sh in foreground synchronous mode with timeout: 600000 (Bash tool's 10-minute ceiling). Do not use &, do not set run_in_background: true, do not use nohup — Claude Code 2026-04+ has an auto-background child-lifecycle regression that silently kills the process (output file stays 0 bytes). Use run_in_background: true + BashOutput polling only as an exception when the call is genuinely expected to exceed 10 minutes.

1. Determine review scope

Based on $ARGUMENTS:

  • No args: review git diff --cached (staged changes)
  • File path: review the specified file
  • --diff: review git diff (unstaged changes)
  • --pr: review full PR diff (git diff main...HEAD)
  • --verbose: also show issues that were filtered out (< 80 confidence) with their scores

1.5 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
  • If any guideline files are found, their content becomes part of the review context (passed to the provider and used in confidence scoring).
  • If none are found, skip this dimension — do not fabricate guidelines.
  • Keep the raw guideline text available for Step 5 (confidence scoring).

1.7 Gather historical PR comments (--pr mode only)

When using --pr mode, search for recurring review patterns on the same files:

  1. Get files in this PR: git diff main...HEAD --name-only
  2. Find recent merged PRs: gh pr list --state merged --limit 10 --json number,title
  3. For each (up to 5), fetch review comments on the same files:
    gh api "repos/{owner}/{repo}/pulls/NUMBER/comments" \
      --jq '.[] | select(.path == "TOUCHED_FILE") | {path, body}'
    
  4. Include found comments as additional context in the Codex prompt (Step 3), prefixed with: "Historical Review Context (previous review comments on the same files — recurring issues are high-confidence signals):"

Read the full file on GitHub · 308 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. 7d ago First seen · 308 lines · 17 tokens per session scan A 3816fe135dc5

Subscribe to this mod's changes

pi-code-review is a command published in the GitHub repository tznthou/claude-prism (10 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 3,629 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.