review-pr-lite

review-pr-lite is a skill for Claude Code, Codex from dyoshikawa/rulesync. It costs 34 tokens per session (683 once invoked), scanned A, original, MIT.

A lightweight pull-request review workflow for checking code quality and security without starting extra agents. A pull request is a proposed set of changes submitted for review before it is merged.

In plain words
What is it for?
Use it to inspect a pull request's description, changed files, and diff, then identify code-quality problems, security risks, weak checks, or missing context.
Why use it?
It provides a focused review while keeping the current local branch unchanged.

Skill for Claude CodeCodex

About the project

Rulesync is a command-line tool that generates configuration for different AI development tools from a shared set of rules. Developers use it to keep instructions, commands, MCP settings, ignore files, subagents, and skills consistent across coding agents. Catalogue skills support workflows built around Rulesync.

dyoshikawa/rulesync · 1,385 stars · on GitHub

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.

agentmods
npx agentmods add skills/dyoshikawa/rulesync/review-pr-lite
Any agent
npx skills add dyoshikawa/rulesync --skill review-pr-lite
Clone the repo
git clone --depth 1 https://github.com/dyoshikawa/rulesync

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 review-pr-lite

README.md
[![agentmods](https://agentmods.dev/badge/skills/dyoshikawa/rulesync/review-pr-lite.svg)](https://agentmods.dev/skills/dyoshikawa/rulesync/review-pr-lite)
Your own site
<a href="https://agentmods.dev/skills/dyoshikawa/rulesync/review-pr-lite"><img src="https://agentmods.dev/badge/skills/dyoshikawa/rulesync/review-pr-lite.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 683 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00034 $0.00683
Opus 5 $0.00017 $0.00342
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured 5d ago against content hash 4aa2e3fdee19, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-pr-lite 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 5d 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.

.rulesync/skills/review-pr-lite/SKILL.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

target_pr = the user's request

If target_pr is not provided, use the PR of the current branch.

Important: Do Not Switch the Local Branch

  • Do NOT check out, switch, or otherwise move the local branch (e.g., git checkout, git switch, gh pr checkout).
  • To inspect the PR's changes, use git and gh commands that read remote state without moving the working tree. For example:
    • gh pr view $target_pr to read PR metadata and description.
    • gh pr diff $target_pr to read the diff.
    • gh pr view $target_pr --json files or gh api to list changed files.
    • git fetch origin pull/<PR_NUMBER>/head:refs/remotes/origin/pr-<PR_NUMBER> and git diff origin/main...origin/pr-<PR_NUMBER> if a local read-only ref is needed.

Step 1: Gather PR Context

Run the following in parallel:

  • Get the PR description and metadata via gh pr view $target_pr (do not check out the PR locally).
  • Get the PR diff via gh pr diff $target_pr.
  • If needed, inspect changed files individually for deeper context using gh / git commands (e.g., gh api, git show) — without switching the local branch.

Step 2: Review the Changes

Review the PR directly in this skill without calling any subagents.

Focus on both of the following:

  1. Code Review

    • Bugs or behavioral regressions
    • Incorrect assumptions or edge cases
    • Missing or weak tests
    • Maintainability issues that could cause near-term problems
  2. Security Review

    • Injection risks
    • Auth/authz mistakes
    • Secrets exposure
    • Unsafe file, network, shell, or deserialization behavior
    • Dependency or configuration changes that could weaken security

Step 3: Report Findings

Integrate all findings into one review result. Please output the PR number in the result so that the user can easily find the PR.

Reporting Rules

  • Assign a severity level to each finding: low, mid, high, or critical.
  • Assign a sequential number to each finding (e.g., #1, #2, #3, ...).
  • Present findings first, ordered by severity.
  • If no findings are discovered, explicitly state that no findings were found.
  • Keep the summary brief and focused on risk and testing gaps.

Read the full file on GitHub · 71 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. 5d ago First seen · 71 lines · 34 tokens per session scan A 4aa2e3fdee19

Subscribe to this mod's changes

review-pr-lite is a skill published in the GitHub repository dyoshikawa/rulesync (1,385 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 683 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.

Related

Other skills, from other repositories

snip

You are an expert at writing declarative YAML filters for snip, a CLI proxy that reduces LLM token consumption by filtering shell output.

edouard-claude/snip · 0 tokens

opensrc

Fetch dependency source code to give AI agents deeper implementation context. Use when the agent needs to understand how a library works internally, read source code for a package, fetch implementation details for a dependency, or explore how an npm/PyPI/crates.io package is built. Triggers include "fetch source for"…

vercel-labs/opensrc · 103 tokens

building-agents

Use when building or restructuring an LLM agent — provider adapter, tool calling, structured output, RAG, agent loop, eval gate, cost routing, tracing, MCP server — model-agnostic across OpenAI/Anthropic/Gemini/OSS so a model swap is a config change. NOT vector-store SQL alone (that is postgresdb) or service…

ericrisco/rsc-harness · 85 tokens

agent-eval

Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…

ericrisco/rsc-harness · 79 tokens

prompt-engineering

Use when one prompt must give the same right answer across reruns, models, and pasted-in hostile input: forcing a fixed schema, picking the few-shot set, ordering the prompt blocks, or the inline cases you run while tuning. NOT the agent loop, tools, or retrieval (that is building-agents), NOT a standing CI eval…

ericrisco/rsc-harness · 83 tokens

linked-intent-dev

Guide for linked-intent development (LID). Consult for ALL code changes. Walks changes through a mode-aware six-phase workflow (HLD → LLD → EARS → intent-narrowing edge audit → tests-first → code) with mandatory stops between each phase. Bugs walk the arrow like any other change — no short-circuit. Enforces cascade…

jszmajda/lid · 87 tokens