A plugin that turns an Obsidian folder into an AI-curated second brain: a searchable knowledge system built from notes and sources. It organizes source material into wiki pages and supports different ways of questioning it.

Use it to maintain a private vault with raw sources, compiled wiki pages, and deliverables, then query the collection using several review approaches.

It separates original source files from generated knowledge pages and helps preserve disagreements instead of smoothing them into one answer.

corpus-core — Plugin by evb87-tech

Install

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.

Claude Code

/plugin marketplace add evb87-tech/corpus

agentmods

npx agentmods add plugins/evb87-tech/corpus/corpus-core

Clone the repo

git clone --depth 1 https://github.com/evb87-tech/corpus

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

corpus-core 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.

corpus-core/.claude-plugin/plugin.json · 23 lines

What it actually says

{
  "name": "corpus-core",
  "version": "0.1.0",
  "description": "Engine for an LLM-curated second brain. Karpathy LLM-wiki pattern with anti-lissage spec, FR-by-default content, three query postures.",
  "author": {
    "name": "evb87-tech",
    "url": "https://github.com/evb87-tech"
  },
  "homepage": "https://github.com/evb87-tech/corpus",
  "repository": "https://github.com/evb87-tech/corpus",
  "license": "MIT",
  "keywords": ["second-brain", "wiki", "knowledge-management", "obsidian", "karpathy", "anti-lissage"],
  "dependencies": [],
  "userConfig": {
    "vaultPath": {
      "type": "directory",
      "title": "Corpus vault path",
      "description": "Absolute path to your corpus vault directory (raw/, wiki/, output/). Run /init-vault to scaffold one if needed.",
      "sensitive": false
    }
  }
}

Changes

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 · 23 lines scan A 262f2cd949c5

Subscribe to this mod's changes

corpus-core is a plugin published in the GitHub repository evb87-tech/corpus (1 stars, last pushed 4mo 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.

Code review Data and AI LLM Writing and docs claude-code claude-code-marketplace claude-code-plugin knowledge-management obsidian

corpus-core

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

superbrain

memex-local

remember

obsidian

robonuggets

codex-obsidian-loop