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/slbug/claude-ruby-grape-rails/auditnpx skills add slbug/claude-ruby-grape-rails --skill auditgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-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/slbug/claude-ruby-grape-rails/audit)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/audit"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/audit.svg" alt="Measured on agentmods" 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 | $0.00040 | $0.00663 |
| Opus 5 | $0.00020 | $0.00331 |
| Sonnet 5 | $0.00008 | $0.00133 |
| Haiku 4.5 | $0.00004 | $0.00066 |
Grade A, and why
rb:audit 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 4d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit
Review five categories:
- Architecture — boundaries, fan-in/out, module coupling
- Performance — N+1, indexes, preloads, Sidekiq bottlenecks
- Security — Brakeman findings, authorization, secrets handling
- Test Quality — coverage, flake risk, factory discipline
- Dependencies — bundle-audit, CVEs, version freshness
Preconditions
- Before emitting any A-F grade or weighted composite, Read
references/scoring-methodology.mdfor canonical category weights and deduction rules. - Before architecture / boundary findings, Read
references/architecture-checks.mdfor the service-object health matrix and fan-in/out thresholds.
Gotchas
- Scope creep. Audit reports stay project-wide; do NOT propose fixes
mid-audit.
/rb:auditis read-only — fixes route through/rb:plan. - False-precision metrics. "23.5% of skills underperform" without sample size or corroboration is meaningless. Source every metric or downgrade language to advisory.
- Unverified third-party claims. "Library X handles Y safely" — verify against current docs (Context7 MCP) or Brakeman scan, never against training-data assumption.
- Gem version / release-status claims (current stable, pre-release,
deprecated, EOL) require
gem info <name>, rubygems.org, or Context7 lookup — never extrapolate from training data. - Schema drift. Iron Laws / preferences references must match current
generator output. Regen via
bash scripts/generate-iron-law-outputs.sh allif mismatched.
References
| Need | Reference |
|---|---|
| service-object health matrix, fan-in/out scoring, boundary violation checks | ${CLAUDE_SKILL_DIR}/references/architecture-checks.md |
| A-F grade scoring per category + weighted overall score | ${CLAUDE_SKILL_DIR}/references/scoring-methodology.md |
Related — invoke manually if needed
- Slow / latency / memory regression →
/rb:perf(performance analysis) - Compression telemetry summary →
/rb:compression-report(internal QA (telemetry report)) - Research trust / source-quality audit →
/rb:provenance-scan(research-trust audit) - Service-boundary or split-monolith decision →
/rb:boundaries(service-boundary analysis) - Request-state / session-leak hygiene check →
/rb:state-audit(request-state hygiene) - Adjacent debt noticed but out of scope →
/rb:techdebt(tech-debt logging) - Skill-router telemetry summary →
/rb:discovery-report(internal eval-tuning tool — drafts a redacted report from skill-discovery telemetry)
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.
- 4d ago First seen · 61 lines · 40 tokens per session scan A db2083ec5a71
rb:audit is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 4d ago), licensed MIT. It adds 40 tokens to every session and 663 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 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
overleaf-sync
Two-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to…
omh-code-review
This is a Hermes-native code-review workflow skill.
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.