agentmods.dev

cerebro

A persistent codebase memory plugin for AI coding sessions. It stores a project's structure and file summaries in an MCP server, a standard way for tools to provide context to an AI agent, and includes agents and session hooks.

In plain words
What is it for?
Use it to cache codebase structure and summaries, provide that knowledge through the MCP server, and run the included agents and hooks during sessions.
Why use it?
The stored summaries let sessions query known project information instead of repeatedly reading the same files. This can provide continuity between coding sessions.

Plugin for Claude Code

6 1mo ago A scan tokens not measured original MIT
View the source file marcodavidd020/cerebro-code-memory
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 marcodavidd020/cerebro-code-memory
agentmods
npx agentmods add plugins/marcodavidd020/cerebro-code-memory/plugin
Clone the repo
git clone --depth 1 https://github.com/marcodavidd020/cerebro-code-memory

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

cerebro 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.

plugin/.claude-plugin/plugin.json · 11 lines

What it actually says

{
  "name": "cerebro",
  "version": "0.2.1",
  "description": "Persistent code-knowledge memory: an MCP brain that caches a codebase's structure and summaries so AI sessions query it instead of re-reading files. Bundles the MCP server, cerebro-first subagents, and session hooks.",
  "author": { "name": "Marco Toledo", "url": "https://github.com/marcodavidd020/cerebro-code-memory" },
  "homepage": "https://github.com/marcodavidd020/cerebro-code-memory",
  "license": "MIT",
  "mcpServers": "./.mcp.json",
  "hooks": "./hooks/hooks.json"
}
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.

  1. yesterday First seen · 11 lines scan A 2a35323737ed

Subscribe to this mod's changes

cerebro is a plugin published in the GitHub repository marcodavidd020/cerebro-code-memory (6 stars, last pushed 1mo 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.

Memory and contextResearchaianthropicclaudeclaude-codecode-intelligencecode-search
Related

Other plugins, from other repositories

repobrain

Plugin marketplace listing 1 plugin: repobrain.

study8677/repobrain · not measured

repobrain

Repository knowledge engine plugin. Bundles CLI-backed slash commands (rb-setup / rb-init / rb-refresh / rb-ask) plus the agent-repo-init skill. Works in both Claude Code and Codex CLI.

study8677/repobrain · not measured

codanna

Claude Code plugins for codanna, the code-intelligence CLI and MCP server: x-ray and graph views over a codanna index.

bartolli/codanna · not measured

codanna-toolset

Codanna toolset for Claude Code: x-ray (semantic search + relationship traversal with 3D neighbourhood, radial tree and edge-bundle views) and graph (the whole index as a module disc with hubs at the centre, timeline and heatmap). Needs the codanna CLI.

bartolli/codanna · not measured

sverklo-marketplace

Plugins for sverklo — the local-first code intelligence MCP server.

sverklo/sverklo · not measured

codestory

CodeStory grounding for coding agents over the local codestory-cli runtime.

TheGreenCedar/CodeStory · not measured