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 agentmods add skills/rootstrap/rails_api_base/rspec-conventionsnpx skills add rootstrap/rails_api_base --skill rspec-conventionsgit clone --depth 1 https://github.com/rootstrap/rails_api_baseWhat 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 | $0.00082 | $0.01124 |
| Opus 5 | $0.00041 | $0.00562 |
| Sonnet 5 | $0.00016 | $0.00225 |
| Haiku 4.5 | $0.00008 | $0.00112 |
Grade A, and why
rspec-conventions 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 2d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RSpec Conventions (Rootstrap)
Apply these whenever producing or modifying RSpec test code. Full guide: https://github.com/rootstrap/tech-guides/blob/master/ruby/rspec/style_guide.md
Complements ruby-conventions — language-level Ruby style still applies.
Structure & Formatting
- No blank line directly after
describe/context/featureopening. - Leave one blank line after
let/subjectgroups and afterbefore/afterblocks. - Group
letandsubjecttogether; separate them frombefore/afterwith a blank line. - One blank line around each
itblock. - Use
before(notbefore(:each));before(:all)should be rare and explicit.
describe & context
describe '#method'for instance methods,describe '.method'for class methods.contextdescriptions must start withwhenorwith, forming a grammatical sentence.context 'when the display name is not present'- Every
contextshould have a matching opposite/negative case — a lone context is a smell. - Don't end
itdescriptions with a conditional ("...if X") — wrap in acontextinstead.
it / Examples
- Never start
itwith "should" / "should not". State behavior directly.it 'returns the summary' # not: 'should return the summary' - One expectation per
itblock (split multi-assertion examples). - Avoid generating examples via iterators; use shared examples instead.
shared_examples 'responds successfully' do it 'returns 200' do ... end end it_behaves_like 'responds successfully'
let & subject
- Prefer
letoverbefore { @x = ... }for test data (lazy, no instance vars). letis lazy (evaluated on first reference) and cached within a single example, not across examples. Uselet!when you need eager evaluation before each example.- Use
letfor values shared across several (not necessarily all)its in a context; avoid overuse — it hurts readability. - Use
subjectwhen describing a single primary object.subject { create(:article) }
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.
- 2d ago First seen · 88 lines · 82 tokens per session scan A a8f2321362f4
rspec-conventions is a skill published in the GitHub repository rootstrap/rails_api_base (631 stars, last pushed 4d ago), licensed MIT. It adds 82 tokens to every session and 1,124 once invoked, about $0.0004 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
tests
Write clear, maintainable Vitest and Playwright tests with precise assertions, consistent structure, and strong behavioral coverage.
completion-rule
大模型代码生成任务的自动自检与纠错规则。 在代码输出后强制执行功能自测、单元测试设计和 Linter 检查。 未通过则自动修正并循环,直到全部通过或达到最大迭代次数。 适用于大模型生成或修改代码且要求正确、可测试、规范的场景。 支持 Python、TypeScript、Go、Java,语言规则通过 references 加载。.
rails-upgrade
Analyzes Rails applications and generates comprehensive upgrade reports with breaking changes, deprecations, and step-by-step migration guides for Rails 2.3 through 8.1. Use when upgrading Rails applications, planning multi-hop upgrades, or querying version-specific changes. Based on FastRuby.io methodology and "The…
test-runner
Run and triage Go tests with correct environment handling; produce compact, actionable failure summaries.
upgrade-cleanup
Clean up after (or abandon) a Rails upgrade. Drop NextRails.next? and NextRails.current? branches and retire dual-boot scaffolding (Gemfile.next, Gemfile.next.lock, conditional Gemfile groups), keeping either the next or the current version. Trigger when the user says they are done with the upgrade, want to clean up…
testing-patterns
Writes Minitest tests with fixtures following 37signals conventions. Uses Minitest (not RSpec) and fixtures (not factories). Use when writing tests, adding test coverage, or creating fixtures. WHEN NOT: For RSpec or FactoryBot patterns (this project uses Minitest + fixtures exclusively). For test configuration/CI…