Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add slbug/claude-ruby-grape-rails/plugin install 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/permissions)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/permissions"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/permissions/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/slbug/claude-ruby-grape-rails/permissions"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/permissions.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 | $0.00042 | $0.01262 |
| Opus 5.5 | $0.00017 | $0.00505 |
| Sonnet 5.5 | $0.00008 | $0.00252 |
| Haiku 4.5 | $0.00004 | $0.00126 |
Grade D, and why
rb:permissions scanned grade D with 2 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`~/.claude/settings.json` policy folded into the recommendations. Cloud metadata endpointhighServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
"deniedDomains": ["metadata.google.internal", "169.254.169.254"] How it starts
The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Permission Analyzer
Scan recent Claude session transcripts, find Ruby-project Bash commands that keep
requiring approval, compare them against current Claude settings.json
permissions, and recommend the safest missing entries.
Primary goal: Discover missing permissions from actual usage. Secondary goal: Clean up deprecated, duplicate, or garbage permission rules.
Usage
/rb:permissions [--days=14] [--dry-run] — Scans recent session JSONL files
for the current project, finds uncovered Bash commands, classifies risk, and
recommends settings.json changes. Use --dry-run to preview without
writing.
Arguments
$ARGUMENTS — --days=N (default: 14), --limit=N, --include-global,
--dry-run. Repo-local settings are the default scope.
Iron Laws
- Never auto-allow RED commands.
- Evidence-based only — recommend commands observed in recent Bash tool-use events for this project.
- Show before writing — present the diff, get explicit confirmation.
- Preserve existing settings — merge, never overwrite.
- Prefer the narrowest safe scope — project settings for Ruby app commands, user settings only for universal tools.
Workflow
Step 1: Extract Uncovered Bash Commands
Run the canonical extractor first:
Run ${CLAUDE_PLUGIN_ROOT}/bin/extract-permissions --days "${DAYS:-14}" with optional flags --include-global, --limit "${LIMIT}", and --dry-run as needed.
See ${CLAUDE_SKILL_DIR}/references/extraction-script.md for the output format.
Keep repo-local settings as the default audit scope; only add
--include-global when the contributor explicitly wants personal
~/.claude/settings.json policy folded into the recommendations.
Do not skip straight to writing settings. The extraction step is the evidence.
Step 2: Classify and Normalize
For each uncovered command group:
- Classify it as GREEN / YELLOW / RED using
${CLAUDE_SKILL_DIR}/references/risk-classification.md. - Normalize it to the narrowest useful permission pattern:
bundle exec rspec spec/models/user_spec.rb→Bash(bundle exec rspec *)bundle exec rails test test/models/user_test.rb→Bash(bundle exec rails test *)bundle exec rubocop app/models/user.rb→Bash(bundle exec rubocop *)bundle exec rails db:migrate→Bash(bundle exec rails db:migrate *)git status --short→Bash(git status *)
- Prefer specific project commands over broad umbrellas like
Bash(bundle *)unless the user explicitly wants broad trust. - Also review the extractor output for:
- deprecated
Bash(name:*)patterns - exact duplicates
- obvious garbage entries like heredoc fragments or
Bash(done)
- deprecated
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.
- 1mo ago First seen · 139 lines · 42 tokens per session scan D 5caae5f9a15a
rb:permissions is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 16d ago), licensed MIT. It adds 42 tokens to every session and 1,262 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
lighting-report-extract
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.