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/adelinamart/robrainWrote 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/adelinamart/robrain/claude-code)<a href="https://agentmods.dev/plugins/adelinamart/robrain/claude-code"><img src="https://agentmods.dev/badge/plugins/adelinamart/robrain/claude-code/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/adelinamart/robrain/claude-code"><img src="https://agentmods.dev/badge/plugins/adelinamart/robrain/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
robrain 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 1mo 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": "robrain",
"version": "2.4.9",
"description": "Institutional memory for AI coding agents: deterministic decision capture and pre-task warnings about previously REJECTED approaches, backed by your self-hosted RoBrain stack.",
"author": {
"name": "Rory Plans",
"url": "https://roryplans.ai"
},
"homepage": "https://github.com/adelinamart/robrain",
"repository": "https://github.com/adelinamart/robrain",
"license": "Apache-2.0",
"keywords": [
"memory",
"decisions",
"rejected-alternatives",
"institutional-memory",
"mcp"
]
}
What it installs
The manifest is a name and a version. 3 hooks travel with it, and installing the plugin installs all of them. Each is measured on its own page, and each can be installed alone.
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.
- 1mo ago First seen · 20 lines scan A 5a0769f3d8ac
robrain is a plugin published in the GitHub repository adelinamart/robrain (82 stars, last pushed 9d ago), licensed Apache-2.0. 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
acontext
Skill memory layer for Claude Code — auto-capture, learn, and reuse skills from Acontext.
cutweight
Cut your agent's token weight: one dial (light, full, ultra, off) plus weigh-in, skill diet, and session cut.
carryover
Carry your context across AI coding tools. Adds /carryover and /headroom commands plus a save-to-memory prompt at the end of each session, backed by the headroom proxy.
koshi
Koshi MCP — retrieval, context engineering, persistent memory, and quality scoring for AI agents. 100% offline.
repomemory
Persistent, structured memory for AI coding agents. Your codebase never forgets. Hybrid keyword + semantic search, auto-session capture, intelligent category routing.
aidd-telemetry
Measurement: counts the tokens of Claude Code sessions per task, ticket, model and day, locally. Opt in with the 00-init skill; ask with 01-usage.