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.
npx skills add natsukium/dotfiles --skill pi-reviewgit clone --depth 1 https://github.com/natsukium/dotfilesWrote 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.
[](https://agentmods.dev/skills/natsukium/dotfiles/pi-review)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
- 9d ago First seen · 74 lines · 72 tokens per session scan A 5b597089b08c
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.
Other skills, from other repositories
deep-research-team
This skill should be used when the user asks for "deep research", "research team", "comprehensive analysis", "research report", "investigate thoroughly", "compare X vs Y in depth", or needs synthesis across multiple sources with verification. It spawns a coordinated team of researcher agents across multiple rounds…
audit-permissions
This skill should be used when the user asks to "audit claude permissions", "audit permissions", "review local claude settings", "promote permissions to global", "clean up claude settings", "find permission patterns", or wants to identify project-local Claude Code permissions that should be added to global…
malo-find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
start
Enable auto TTS for this session.
stop
Disable auto TTS for this session.
cancel
Stop any currently playing text-to-speech audio.