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 igmarin/rails-agent-skills --skill review-enginegit clone --depth 1 https://github.com/igmarin/rails-agent-skillsWrote 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/igmarin/rails-agent-skills/review-engine)<a href="https://agentmods.dev/skills/igmarin/rails-agent-skills/review-engine"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/review-engine/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/igmarin/rails-agent-skills/review-engine"><img src="https://agentmods.dev/badge/skills/igmarin/rails-agent-skills/review-engine.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 | $0.00031 | $0.01277 |
| Opus 5 | $0.00015 | $0.00639 |
| Sonnet 5 | $0.00006 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
review-engine 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 10d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Engine
Use this skill when the task is to review an existing Rails engine or propose improvements.
Quick Reference
| Review Area | Key Checks |
|---|---|
| Namespace | isolate_namespace used; clear boundaries; no host constant leakage |
| Host integration | Configuration seams, adapters; no direct host model access |
| Init | No side effects at load time; reload-safe hooks in config.to_prepare |
| Migrations | Documented, copied via generator; no implicit or destructive steps |
| Dummy app | Present in spec/; used for integration tests; exercises real mount and config |
HARD-GATE
Before writing findings, confirm every row in the Quick Reference table has been addressed:
- [ ] Namespace isolation verified
- [ ] Host integration points checked
- [ ] `engine.rb` initializer blocks inspected
- [ ] Migration/generator flow confirmed
- [ ] Dummy app presence and usage confirmed
- [ ] Integration tests exercise real mount
If any box cannot be checked (e.g., file not provided), record it as an open assumption.
Core Process
- Identify the engine type and purpose. Read
lib/<engine_name>/engine.rbandlib/<engine_name>/railtie.rb. Confirm isolated vs plain. - Inspect the namespace and public API surface. Check for
isolate_namespaceand unqualified top-level constant references. - Check host-app integration points. Flag direct host constant references. Verify host dependencies flow through config seams.
- Check initialization and reload behavior. Inspect
initializer,config.to_prepare, andActiveSupport.on_load. Flag anything that mutates global state atrequiretime outside an initializer block. - Check migrations, generators, and install flow. Confirm migrations are copied via a generator. Check for destructive or irreversible migrations.
- Check dummy-app and integration tests. Confirm
spec/dummy/exists and exercises the mount point. - Summarize findings by severity. Flag High findings first. Do not surface Low findings before architecture issues.
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.
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.
- 10d ago First seen · 131 lines · 31 tokens per session scan A d54bb651161e
review-engine is a skill published in the GitHub repository igmarin/rails-agent-skills (25 stars, last pushed 19d ago), licensed MIT. It adds 31 tokens to every session and 1,277 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.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.