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.
git clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/plugins/apurvbazari/claude-plugins/onboard)<a href="https://agentmods.dev/plugins/apurvbazari/claude-plugins/onboard"><img src="https://agentmods.dev/badge/plugins/apurvbazari/claude-plugins/onboard/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/plugins/apurvbazari/claude-plugins/onboard"><img src="https://agentmods.dev/badge/plugins/apurvbazari/claude-plugins/onboard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
onboard 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 5d 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": "onboard",
"version": "3.3.0",
"description": "Analyze a codebase with verified research and generate evidence-grounded Claude tooling: CLAUDE.md, path-scoped rules, skills, agents, hooks and a project .mcp.json. Offers companion LSP and MCP plugins and installs only the ones you accept, then keeps the tooling current as the code changes.",
"author": {
"name": "Apurv Bazari"
},
"repository": "https://github.com/ApurvBazari/claude-plugins",
"license": "MIT",
"keywords": [
"onboarding",
"setup",
"wizard",
"claude-md",
"codebase-analysis",
"plugin-integration",
"quality-gates",
"ai-assisted-development"
]
}
What it installs
The manifest is a name and a version. 9 skills, 5 agents travel with it, and installing the plugin installs all of them — 902 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill generation A 37 tokens
- Skill start A 35 tokens
- Skill update A 64 tokens
- Skill generate A 61 tokens
- Skill adopt A 65 tokens
- Skill maintain A 82 tokens
- Skill verify A 77 tokens
- Skill evolve A 66 tokens
- Skill research A 69 tokens
- Agent config-generator A 69 tokens
- Agent feature-evaluator A 50 tokens
- Agent research-specialist A 89 tokens
- Agent research-verifier A 90 tokens
- Agent codebase-analyzer A 48 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.
- 5d ago Changed f0366626065d
- 7d ago Changed 5b6e383e7663
- 18d ago Changed bef5295513ca
- 1mo ago Changed e69948b4bd8a
- 1mo ago First seen · 21 lines scan A c10cd11a17a5
onboard is a plugin published in the GitHub repository ApurvBazari/claude-plugins (1 stars, last pushed 2d 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 2026-08-31.
Other plugins, from other repositories
ghostty-notify
Native Ghostty desktop notifications for Claude Code (idle input / permission request / turn finished) via OSC 777. Per-tab suppression and click-to-focus are handled natively by Ghostty. Runs only under Ghostty.
apple-pim
Native macOS integration for Calendar, Reminders, Contacts, and Mail using EventKit, Contacts, and JXA frameworks.
review-colleague-pr
Review a colleague's pull request carefully and considerately from a checkout of its branch, and report a brief, read-only assessment in chat: requirements, direction, blockers, follow-ups, and questions for the author.
write-formalization-roadmap
Document-structure guide for multi-milestone formalization roadmaps in Lean, Rocq, Isabelle, HOL, and other proof assistants.
plant-defects
Deliberately break code to prove a test can see it: plant the defect an instrument claims to catch, confirm it goes red, and record it so it regresses.
media
System-wide now-playing control for macOS — see and control whatever is playing (Spotify, Apple Music, browsers) right from Claude Code. Zero dependencies, no OAuth, no app lock-in.