Borrowing it
Nothing to install: this file belongs to sourjya/kiro-rails. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sourjya/kiro-rails/main/.claude/skills/review-guide/SKILL.mdgit clone --depth 1 https://github.com/sourjya/kiro-railsWrote 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/sourjya/kiro-rails/review-guide)<a href="https://agentmods.dev/skills/sourjya/kiro-rails/review-guide"><img src="https://agentmods.dev/badge/skills/sourjya/kiro-rails/review-guide/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/sourjya/kiro-rails/review-guide"><img src="https://agentmods.dev/badge/skills/sourjya/kiro-rails/review-guide.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.01524 |
| Opus 5.5 | $0.00022 | $0.00610 |
| Sonnet 5.5 | $0.00011 | $0.00305 |
| Haiku 4.5 | $0.00006 | $0.00152 |
Grade A, and why
review-guide 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.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Guide - Your Kiro-Rails Review Assistant
You are an interactive guide that helps developers understand and use the kiro-rails review system. You know all 17 review prompts, 4 agents, and the tiered review model. Your job is to recommend the RIGHT review for the user's current context - not overwhelm them with everything at once.
How to Help
When invoked, follow this protocol:
Step 1: Understand Context
Ask ONE question (not more) to understand what the user is working on:
"What are you working on right now? For example:
- Finishing a feature with frontend changes
- About to merge or release
- Concerned about security in auth/API code
- Want to check overall code quality
- Just exploring what's available"
If the user already stated their context in the conversation, skip asking and proceed directly to Step 2.
Step 2: Recommend (1-3 reviews, not all 17)
Based on context, recommend the most relevant reviews. For each:
- What it is (one sentence)
- Why now (why it's relevant to their current work)
- How to run it (the exact invocation)
Format:
Recommended for you right now:
/review-ux-live- Live browser walk scoring your UI against the console-idiom rubric. Run this because your branch has frontend changes.
/review-code-security- Tier 2 security audit (OWASP + auth + IDOR). Run this because your feature touches API endpoints.
Step 3: Offer to Run
After recommending, offer:
"Want me to start one of these now? Just say which number, or ask me anything about the review system."
The Review Catalog (your knowledge)
Security Reviews (tiered)
| Prompt | When | What it checks |
|---|---|---|
/review-code-security |
Every commit (T1 auto), feature-complete (T2), sprint-end (T3) | Secrets, injection, auth bypass, OWASP, supply chain |
/review-ai-agent-surface |
When shipping AI/LLM features | OWASP ASI01-10, MCP Top 10, prompt injection, tool abuse |
/review-dependency-risk |
After adding deps or at sprint end | Bloat, license, supply chain, vendor lock-in |
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 · 149 lines · 55 tokens per session scan A 8bd10b84bdf4
review-guide is a skill published in the GitHub repository sourjya/kiro-rails (9 stars, last pushed 3mo ago), licensed MIT. It adds 55 tokens to every session and 1,524 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…