A read-only code-review guide for Ruby, Rails, and Grape changes. It uses separate reviewers for areas such as correctness, security, tests, database queries, background jobs, performance, and style.

Use it to review a pull request or local changes for bugs, security issues, missing tests, performance problems, maintainability, and framework-specific mistakes.

It helps identify problems in changed code before those changes reach production while keeping the review focused on the actual diff.

rb:review — Skill for Claude Code by slbug/claude-ruby-grape-rails

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add slbug/claude-ruby-grape-rails

Claude Code

/plugin install ruby-grape-rails

Made for: Claude Code.

Or install ruby-grape-rails, the plugin that ships this one along with the rest of its 52 skills, 19 agents, 17 hooks.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/review/github.svg)](https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/review)

Your own site

<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/review"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/review"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,253 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.

Model	Per session	Once invoked
Fable 5.1	$0.00048	$0.04253
Opus 5.5	$0.00019	$0.01701
Sonnet 5.5	$0.00010	$0.00851
Haiku 4.5	$0.00005	$0.00425

Measured 1mo ago against content hash 02a3ebf702d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rb: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 1mo 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.

plugins/ruby-grape-rails/skills/review/SKILL.md · 376 lines

How it starts

The opening of the file, as written. The whole thing — 376 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Ruby/Rails/Grape Code

Review changed code by spawning specialist agents. Review is read-only - never fix during review.

Review Philosophy

Reviews catch issues before they reach production. Each specialist focuses on their domain:

Correctness: Does it work? Handle edge cases?
Security: Are there vulnerabilities? Input validation?
Maintainability: Can others understand and modify this?
Performance: Will it scale? Any N+1s?
Style: Does it follow conventions?

Collecting Changed Files

Run ${CLAUDE_PLUGIN_ROOT}/bin/resolve-base-ref → 3 KEY=value lines on stdout (BASE_REF, REMOTE, DEFAULT_BRANCH). Substitute the values into subsequent Bash commands. Then capture:

MERGE_BASE via git merge-base HEAD BASE_REF_VALUE
CHANGED_FILES via git diff --name-only --diff-filter=ACMR MERGE_BASE_VALUE...HEAD
DIFF_STAT via git diff --stat MERGE_BASE_VALUE...HEAD

Pass the captured CHANGED_FILES, BASE_REF, MERGE_BASE, and DIFF_STAT values to every spawned reviewer. Reviewers scope analysis to the file list and NEVER scan unchanged files.

Reviewers own diff strategy. For reviewer diff discipline, see ${CLAUDE_SKILL_DIR}/references/review-playbook.md § "Diff Collection".

Main-Session Fanout

/rb:review spawns specialist agents directly from the main session in parallel. Subagents are leaf workers — they return findings; they do not spawn further agents.

MUST spawn in foreground. Never pass run_in_background: true on any Agent call. Use parallel via multiple Agent tool calls in a single message.

Fanout Pattern

Classify complexity (tier + critical-path escalation).
Select core + conditional reviewers per matrix below. Derive review-slug. Use the BASE_REF value captured in § "Collecting Changed Files" — substitute literally into shell commands below (e.g. --base-ref=BASE_REF_VALUE).
Run ${CLAUDE_PLUGIN_ROOT}/bin/manifest-update prepare-run --skill=rb:review --slug=REVIEW_SLUG_VALUE --base-ref=BASE_REF_VALUE --agents=AGENTS_CSV_VALUE. Captures stdout as $MANIFEST (absolute manifest path). Helper archives any prior manifest, computes datesuffix, agent paths, consolidated path, git pins; writes fresh manifest atomically.
Run ${CLAUDE_PLUGIN_ROOT}/bin/manifest-update prepare-respawn "$MANIFEST". Rotates existing files at manifest-tracked agent paths to <agent-slug>.stale-<rename-ts>.md.
For each agent, patch status: in-flight via printf '{"agents":{"%s":{"status":"in-flight"}}}\n' "$AGENT_SLUG" | ${CLAUDE_PLUGIN_ROOT}/bin/manifest-update patch "$MANIFEST".
Spawn all reviewers in ONE parallel block. Read agent paths via ${CLAUDE_PLUGIN_ROOT}/bin/manifest-update spawn-paths "$MANIFEST" (tab-separated agent_slug<TAB>absolute_path). Pass each absolute path verbatim in the spawn prompt.
Wait for all reviewers to complete.
Apply Artifact Recovery per ${CLAUDE_PLUGIN_ROOT}/references/artifact-recovery.md (coverage-noun Reviewer). Patch each agent's status field with its recovery-state value (artifact | stub-replaced | recovered-from-return | stub-no-output).
Read each verified artifact via the absolute path from manifest-update spawn-paths "$MANIFEST". Read consolidated path via ${CLAUDE_PLUGIN_ROOT}/bin/manifest-update field "$MANIFEST" consolidated_path. Write the consolidated review to that path.
Patch manifest status: complete.
Present verdict to the user.

Read the full file on GitHub · 376 lines

Files

What ships with it

3 files 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.

1mo ago First seen · 376 lines · 48 tokens per session scan A 02a3ebf702d3

Subscribe to this mod's changes

rb:review is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 16d ago), licensed MIT. It adds 48 tokens to every session and 4,253 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.

Claude Code Code review Languages Ruby ai ai-agent ai-agents ai-tools claude

simplify

Simplifies and refines Ruby on Rails code following 37signals patterns and the One Person Framework philosophy, while preserving exact functionality. Focuses on recently modified code unless instructed otherwise. Use this skill when simplifying or refactoring Rails code, reviewing recently written Rails code for…

maquina-app/rails-claude-code · 123 tokens

coding-best-practices

Reviews Swift/iOS code for adherence to modern Swift idioms, Apple platform best practices, architecture patterns, and code quality standards. Use when user mentions best practices, code review, clean code, refactoring, or wants to improve code quality.

rshankras/claude-code-apple-skills · 55 tokens

python-services

Python patterns for CLI tools, async parallelism, and backend services. Use when building CLI apps, async/parallel Python, FastAPI services, background jobs, or configuring Python project tooling (uv, ruff, ty).

iliaal/whetstone · 48 tokens

react-frontend

React, TypeScript, and Next.js patterns for frontend development. Use when building React components, managing state, fetching data, optimizing performance, or working with Next.js App Router. Covers React 18-19, hooks, Server Components, and type-safe patterns.

iliaal/whetstone · 57 tokens

pinescript

Pine Script v6 patterns: syntax rules, performance, debugging, backtesting, visualization. Use when asked to "write a Pine Script", "create an indicator", "build a strategy", "fix Pine code", or mentions PineScript, TradingView, indicator, strategy, or backtest.

iliaal/whetstone · 64 tokens

shared-tooling-eslint-prettier

ESLint 9/10 flat config with defineConfig(), Prettier v3.0+ shared config, eslint-config-prettier integration, typescript-eslint v8+ projectService.

agents-inc/skills · 46 tokens