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 VSN2015/concerns_on_rails --skill gem-docs-reviewgit clone --depth 1 https://github.com/VSN2015/concerns_on_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/vsn2015/concerns_on_rails/gem-docs-review)<a href="https://agentmods.dev/skills/vsn2015/concerns_on_rails/gem-docs-review"><img src="https://agentmods.dev/badge/skills/vsn2015/concerns_on_rails/gem-docs-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.
<a href="https://agentmods.dev/skills/vsn2015/concerns_on_rails/gem-docs-review"><img src="https://agentmods.dev/badge/skills/vsn2015/concerns_on_rails/gem-docs-review.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 | $0.00152 | $0.01657 |
| Opus 5 | $0.00076 | $0.00829 |
| Sonnet 5 | $0.00030 | $0.00331 |
| Haiku 4.5 | $0.00015 | $0.00166 |
Grade A, and why
gem-docs-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gem-docs-review
A self-contained, dependency-free skill (Ruby stdlib + Bundler only) for gem-aware code review. It keeps a local cache of each gem's own docs and source-derived API, refreshes it incrementally as versions change, and uses it to review diffs/PRs.
The engine
All deterministic work lives in one script. Define a shorthand and run it with the project's bundler so the locked gems resolve:
SCRIPT="${CLAUDE_SKILL_DIR}/scripts/gem_docs.rb"
bundle exec ruby "$SCRIPT" <command> [options]
This repo (concerns_on_rails): prefix every invocation with
ASDF_RUBY_VERSION=3.2.2, e.g.ASDF_RUBY_VERSION=3.2.2 bundle exec ruby "$SCRIPT" check. Other projects just usebundle exec ruby. If a project has no Gemfile.lock at the repo root, pass--lockfile PATH.
| Command | What it does | Output |
|---|---|---|
check |
Diff current Gemfile.lock vs the stored manifest. Read-only. |
JSON: up_to_date, added/removed/changed (with upgrade/downgrade direction), stale_cache |
sync |
Harvest docs for gems that are added/changed/uncached, then rewrite the manifest. | JSON: harvested, errors |
sync --all |
Re-harvest every gem (use after changing the harvester or to rebuild). | JSON |
sync --prune |
Also delete cached dirs for gem-versions no longer in the lockfile. | JSON |
status |
Human-readable cache summary + pending changes. | text (add --json for JSON) |
surface NAME |
Print the absolute cache paths (readme/changelog/api/meta) for one gem. | JSON |
changelog NAME |
Print the cached CHANGELOG for one gem (for upgrade-impact). | text |
Cache layout
Default location: <project>/.gem-docs-cache/ (override with --cache PATH or $GEM_DOCS_CACHE).
Add it to .gitignore — it is a rebuildable, machine-local cache.
.gem-docs-cache/
manifest.json # schema, ISO8601 generated_at, lockfile sha256, bundler/ruby
# versions, and per-gem {version, platform, harvested, paths}
gems/<name>-<version>/
README.md # the gem's own README (capped at 300 KB)
CHANGELOG.md # the gem's own CHANGELOG/History/NEWS (capped)
api.txt # qualified public API index: "Klass#method", "Module.method"
meta.json # summary, homepage, licenses, runtime deps, changelog_uri
What ships with it
2 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 · 113 lines · 152 tokens per session scan A 3e98f5489d0e
gem-docs-review is a skill published in the GitHub repository VSN2015/concerns_on_rails (25 stars, last pushed 3d ago), licensed MIT. It adds 152 tokens to every session and 1,657 once invoked, about $0.0008 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
ruby-refactor
Ruby refactoring guidelines from community best practices. This skill should be used when refactoring, reviewing, or restructuring Ruby code to improve design, readability, and maintainability. Triggers on tasks involving code smells, method extraction, conditional simplification, coupling reduction, design patterns…
sgcop-setup
A setup guide for adding the sgcop Ruby and Rails code-checking rules to a project. RuboCop is a tool that finds style and quality problems in Ruby code.
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…
code-review
Use when reviewing a Rails PR, diff, or merge request. Ground findings in a real file:line. Trigger words: review PR, code review, review my diff, CR.
gemtracker
Analyze Ruby gem dependencies, vulnerabilities, outdated packages, maintenance health, and insecure gem sources with the gemtracker CLI. Use when asked to audit Ruby gems, check Gemfile.lock security, review dependency health, or run gemtracker.
apply-code-conventions
Use when applying daily Rails conventions by path (DRY, YAGNI, PORO, CoC, KISS). Style defers to the project linter. Trigger words: conventions, clean code, RuboCop, DRY, YAGNI.