pi-review

pi-review is a skill for Claude Code, Codex from natsukium/dotfiles. It costs 72 tokens per session (735 once invoked), scanned A, original, CC0-1.0.

A process for getting an independent review of a code or design change from a separate pi review session. The review uses either the sol or luna model and checks the repository or supplied document.

In plain words
What is it for?
It helps perform early checks, adversarial design reviews, and final reviews of code changes or design documents.
Why use it?
A fresh session does not inherit the original conversation's assumptions, so it can expose missed problems or blockers. The main agent then verifies the findings and makes any needed revisions.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Good fit It helps perform early checks, adversarial design reviews, and final reviews of code changes or design documents.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/natsukium/dotfiles/pi-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.

Any agent
npx skills add natsukium/dotfiles --skill pi-review
Clone the repo
git clone --depth 1 https://github.com/natsukium/dotfiles

Made for: Claude Code, Codex.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/natsukium/dotfiles/pi-review/github.svg)](https://agentmods.dev/skills/natsukium/dotfiles/pi-review)
Your own site
<a href="https://agentmods.dev/skills/natsukium/dotfiles/pi-review"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/pi-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-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/natsukium/dotfiles/pi-review"><img src="https://agentmods.dev/badge/skills/natsukium/dotfiles/pi-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 735 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00072 $0.00735
Opus 5 $0.00036 $0.00367
Sonnet 5 $0.00014 $0.00147
Haiku 4.5 $0.00007 $0.00073

Measured 9d ago against content hash 5b597089b08c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

pi-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 9d 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.

modules/features/coding-agents/common/skills/pi-review/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reviews Through pi

Run a fresh pi process so the review does not inherit the calling conversation. The reviewer inspects the repository; the calling agent verifies findings and owns any revisions.

Models

Model Use for
openai-codex/gpt-5.6-sol Adversarial design or diff review; final gate
openai-codex/gpt-5.6-luna Early drafts, quick checks, and triage between sol rounds

Use an explicitly requested model. Otherwise use luna for an early pass and sol for high-risk reasoning or the final pass.

Prepare the review

Run pi from the target repository root. Write the change-specific information to a scratch file outside the repository:

# Review context

Target: <document or change>
Review range: <git diff, git diff --cached, or base...HEAD; omit for a document>
Revision context: <what changed and why>
Focus: <risks to examine>
Previous findings: <findings and claimed resolutions, or none>

For a design, attach the document as another @file. For code, let pi inspect the named Git range and surrounding source instead of copying the diff into the prompt.

The fixed review criteria and output format live in ./references/reviewer.md. Resolve that file to an absolute path before invoking pi.

Run the review

Use a foreground command with a timeout of at least 30 minutes:

PI_REVIEW_WORKER=1 pi \
  --model openai-codex/gpt-5.6-sol --thinking high \
  --tools read,grep,find,ls,bash --print --no-session \
  "@<skill-directory>/references/reviewer.md" \
  "@/absolute/path/to/review-context.md" \
  "@/absolute/path/to/design.md" \
  "Follow reviewer.md and review-context.md. Inspect the repository in the current working directory." \
  > /absolute/path/to/review-1.md 2>&1

Omit the design attachment for a code review. Change the model ID for a luna pass. Keep PI_REVIEW_WORKER=1: pi then omits this delegation skill from the child while loading other global and project skills normally. Print mode may stay silent until completion, so an empty output file does not indicate a hang. Treat the process as hung when it exceeds the harness's 30-minute wall-clock timeout, then terminate it and retry once. A nonzero exit is not a review result.

Read the full file on GitHub · 74 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 74 lines · 72 tokens per session scan A 5b597089b08c

Subscribe to this mod's changes

pi-review is a skill published in the GitHub repository natsukium/dotfiles (103 stars, last pushed today), licensed CC0-1.0. It adds 72 tokens to every session and 735 once invoked, about $0.0004 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 2026-08-30.