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 jbdamask/McBrainnpx agentmods add plugins/jbdamask/mcbrain/marketplacegit clone --depth 1 https://github.com/jbdamask/McBrainGrade A, and why
mcbrain 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 yesterday.
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": "mcbrain",
"owner": {
"name": "John Damask",
"email": "[email protected]"
},
"metadata": {
"description": "McBrain — a persistent, LLM-maintained personal knowledge base built on Karpathy's LLM Wiki pattern.",
"version": "5.0.0",
"pluginRoot": "./plugins"
},
"plugins": [
{
"name": "mcbrain",
"source": "./plugins/mcbrain",
"description": "Build and operate McBrain — a personal LLM-maintained knowledge base in Obsidian. Bundles cooperating skills for one-shot vault setup, day-to-day operations (ingest/query/lint/synth), and a local research tracker that drains queued tasks and writes findings back into the vault.",
"version": "5.0.0",
"author": {
"name": "John Damask",
"email": "[email protected]"
},
"category": "knowledge-management",
"keywords": [
"knowledge-base",
"obsidian",
"wiki",
"second-brain",
"research",
"llm-wiki"
]
}
]
}
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.
- yesterday First seen · 34 lines scan A 1b9fae473645
mcbrain is a plugin published in the GitHub repository jbdamask/McBrain (2 stars, last pushed 2mo 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
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
nextjs
Official Claude Code plugin marketplace for Next.js, serving the skills that ship in the vercel/next.js repository.
claude-plugins-official
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
knowledge-work-plugins
Plugin marketplace listing 97 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
ecc
Plugin marketplace listing 1 plugin: ecc.
ecc
Harness-native ECC plugin for engineering teams - 68 agents, 286 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses.