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 juicesharp/rpiv-pi --skill code-reviewgit clone --depth 1 https://github.com/juicesharp/rpiv-piWrote 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/juicesharp/rpiv-pi/code-review)<a href="https://agentmods.dev/skills/juicesharp/rpiv-pi/code-review"><img src="https://agentmods.dev/badge/skills/juicesharp/rpiv-pi/code-review.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00031 | $0.01789 |
| Opus 5 | $0.00015 | $0.00894 |
| Sonnet 5 | $0.00006 | $0.00358 |
| Haiku 4.5 | $0.00003 | $0.00179 |
Grade A, and why
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.
How it starts
The opening of the file, as written. The whole thing — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review System
You are tasked with conducting comprehensive code reviews by invoking parallel skills to analyze changes and synthesize their findings into actionable feedback.
Initial Setup:
When this command is invoked, respond with:
I'm ready to perform a code review. Please specify what you'd like reviewed:
- Latest commit(s)
- Staged changes (git diff --cached)
- Working directory changes (git diff)
- Specific commit hash or range
- Pull request (provide PR number or branch)
You can also specify focus areas or review depth.
Then wait for the user's review request.
Steps to follow after receiving the review request:
-
Read the changes to review:
- Determine what needs reviewing based on user input
- Use appropriate git commands to get the diff:
- Latest commit:
git diff HEAD~1 HEAD - Staged:
git diff --cached - Working:
git diff
- Latest commit:
- IMPORTANT: Read the full diff output FIRST before invoking any skills
- Get list of changed files and understand the scope
- Note commit messages for context
-
Analyze and decompose the review:
- Break down the changes into reviewable areas
- Take time to ultrathink about patterns, security implications, and architectural impacts
- Identify which components are affected
- Create a review plan using the
todotool to track all aspects - Consider which existing patterns and historical decisions are relevant
-
Spawn parallel agents for comprehensive review:
- Plan first then spawn multiple agents to review different aspects concurrently using the Agent tool. Those MUST be run simultaneously to boost efficiency. For codebase research:
- Use the codebase-locator agent to find WHERE files and components live
- Use the codebase-analyzer agent to understand HOW specific code works
- Use the codebase-pattern-finder agent if you need examples of similar implementations
For thoughts directory:
- Use the thoughts-locator agent to discover what documents exist about the topic
- Use the thoughts-analyzer agent to extract key insights from specific documents
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.
- 7d ago First seen · 185 lines · 31 tokens per session scan A 473b2c4fd1bf
code-review is a skill published in the GitHub repository juicesharp/rpiv-pi (11 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 1,789 once invoked, about $0.0002 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
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…