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 hoblin/claude-ruby-marketplacenpx agentmods add plugins/hoblin/claude-ruby-marketplace/rpigit clone --depth 1 https://github.com/hoblin/claude-ruby-marketplaceWrote this? Show the measurements
A badge for your README with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them.
[](https://agentmods.dev/plugins/hoblin/claude-ruby-marketplace/rpi)Grade A, and why
rpi 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 3d 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": "rpi",
"version": "1.12.2",
"description": "RPI workflow: Research, Planning, Implementation. Context engineering system with structured agents and commands for AI-assisted development.",
"author": {
"name": "hoblin"
},
"repository": "https://github.com/hoblin/claude-ruby-marketplace",
"license": "MIT",
"keywords": [
"context-engineering",
"rpi-workflow",
"research",
"planning",
"implementation",
"handoffs",
"session-continuity"
]
}
What it installs
The manifest is a name and a version. 12 commands, 12 agents travel with it, and installing the plugin installs all of them — 921 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Command review-pr A 39 tokens
- Command create_plan A 9 tokens
- Command research_codebase A 11 tokens
- Command iterate_plan A 11 tokens
- Command resume_handoff A 11 tokens
- Command create_handoff A 10 tokens
- Command validate_plan A 11 tokens
- Command feature A 0 tokens
- Command create_note A 12 tokens
- Command implement_plan A 12 tokens
- Command thoughts_init A 6 tokens
- Command commit A 10 tokens
- Agent thoughts-analyzer A 61 tokens
- Agent documentation-researcher A 64 tokens
- Agent review-rails A 64 tokens
- Agent review-tests-minitest A 67 tokens
- Agent review-ticket-delivery A 68 tokens
- Agent review-docs A 57 tokens
- Agent review-generic A 57 tokens
- Agent review-performance A 60 tokens
- Agent review-tests-rspec A 65 tokens
- Agent codebase-analyzer A 47 tokens
- Agent web-search-researcher A 118 tokens
- Agent codebase-pattern-finder A 51 tokens
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.
- 3d ago First seen · 20 lines scan A 1cbb4573a496
rpi is a plugin published in the GitHub repository hoblin/claude-ruby-marketplace (36 stars, last pushed 23d 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
rad-code-review
The specialist lanes and memory that the built-in /code-review doesn't have. Invokes the built-in engine for general bug-finding (quick/standard/deep map to its effort levels), then adds what it lacks: a mechanical hallucinated-imports validator (lockfile-verified across Python/JS/TS/Rust/Go, with a vendored denylist…
rad-context-prompter
Write, debug, reverse-engineer, and migrate AI prompts — now including agentic loops and goal conditions. The prompt-engineering skill covers writing patterns and platform-specific shape (Claude, GPT, Gemini, Claude Code, OpenAI Codex/AGENTS.md, image generators, agentic tools). The loop-goal-engineering skill authors.
github-workflows
PR finalization (single, repo-wide, or org-wide including bots), repo refresh, rebase-merge, merge, review thread resolution, issue shaping, issue sweeping that reconciles open issues against reality, and diagnosing silent GitHub Actions failures.
rad-a11y
WCAG 2.2 AA accessibility toolkit for Claude Code. Six skills covering semantic HTML, ARIA patterns, keyboard/focus, forms, automated testing setup, and a static-analysis review pass; one autonomous reviewer agent. Four pure-stdlib Python validators (scan-jsx-patterns, check-tailwind-contrast with real WCAG sRGB ma.
rad-chrome-extension
MV3 Chrome extension development standards (WXT, React, TypeScript) with two pure-stdlib Python validators that catch what LLM eyeballing misses. Skills cover architecture, MV3 security (CSP, remote code ban, content script isolation), permission minimization and CWS compliance, typed messaging, storage selection…
ai-cli-harness-better-practices
Harness-agnostic session continuity: goal statements, status snapshots, handoffs, cold resume, replanning, and wrap-up. No git or GitHub required.