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.
/plugin marketplace add esparkman/claude-rubycritic-skillnpx agentmods add plugins/esparkman/claude-rubycritic-skill/marketplacegit clone --depth 1 https://github.com/esparkman/claude-rubycritic-skillGrade A, and why
rubycritic-skill 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.
What it actually says
{
"name": "rubycritic-skill",
"owner": {
"name": "esparkman",
"email": "[email protected]"
},
"metadata": {
"description": "RubyCritic code quality analysis skill for Ruby and Rails projects",
"version": "1.0.0"
},
"plugins": [
{
"name": "rubycritic-skill",
"source": "./",
"description": "Analyze Ruby and Rails code quality with RubyCritic. Identifies code smells, complexity issues, and refactoring opportunities. Provides detailed metrics, scores files A-F, compares branches, and prioritizes high-churn problem areas.",
"version": "1.0.0",
"author": {
"name": "Evan Sparkman"
},
"homepage": "https://github.com/esparkman/claude-rubycritic-skill",
"repository": "https://github.com/esparkman/claude-rubycritic-skill",
"license": "MIT",
"keywords": [
"claude-skill",
"claude-code",
"ruby",
"rails",
"rubycritic",
"code-quality",
"static-analysis",
"refactoring",
"model-invoked"
],
"category": "code-quality",
"tags": ["ruby", "rails", "code-quality", "rubycritic", "refactoring"]
}
]
}
What ships with it
1 file beside marketplace.json 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.
- 2d ago First seen · 39 lines scan A febe1ed33292
rubycritic-skill is a plugin published in the GitHub repository esparkman/claude-rubycritic-skill (17 stars, last pushed 9mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
rudder-agent-skills
Plugin marketplace listing 5 plugins: rudder-core, rudder-cli, rudder-mcp, rudder-terraform, rudder-profiles.
justsaydone
Marketplace for the justsaydone plugin: Claude does the work and just says done, saving output tokens and usage.
justsaydone
Claude does the work and replies with one word: done. Cuts summaries, preamble, and wrap-up chatter to save output tokens and usage.
rudder-cli
Workflows for driving the rudder-cli and rudder-typer CLIs: validate, dry-run, apply, import, transformations.
rudder-core
Cross-tool RudderStack domain knowledge: data catalog, data graphs, tracking plans, instrumentation planning, instrumentation debugging, and destination delivery debugging.
rudder-mcp
Workflows for RudderStack's MCP server at mcp.rudderstack.com: connect AI/LLM agents to a RudderStack workspace and drive catalog, sources, destinations, transformations, RETL, tracking plans, and live events via MCP tool calls.