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/cdeust/CortexWrote 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/cdeust/cortex/gemini-extension)<a href="https://agentmods.dev/plugins/cdeust/cortex/gemini-extension"><img src="https://agentmods.dev/badge/plugins/cdeust/cortex/gemini-extension.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
cortex 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": "cortex",
"version": "4.19.1",
"description": "Persistent local-first memory MCP server: remember/recall with thermodynamic heat and decay, knowledge graph, autonomous wiki, local SQLite store by default. Requires uv (uvx) on PATH; hooks-based auto-capture is Claude Code-only — on Gemini CLI memory is manual-tool-driven.",
"mcpServers": {
"cortex": {
"command": "uvx",
"args": ["--from", "hypermnesia-mcp[sqlite]", "hypermnesia-mcp"]
}
}
}
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 · 12 lines scan A 25851dd9079b
cortex is a plugin published in the GitHub repository cdeust/Cortex (71 stars, last pushed yesterday), 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 2026-09-06.
Other plugins, from other repositories
prism-coder
Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an…
mnemo-mcp
Persistent AI memory — store, search, and recall knowledge across sessions.
xmemo
Persistent, user-owned memory for AI agents over hosted MCP. Remember decisions, recall project context, manage TODOs, and govern memory lifecycle across sessions.
papi
Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing.
inspeximus
Self-correcting memory for Claude Code. Facts you correct stay corrected, deletions leave a signed receipt you can verify offline, and storing something never calls a model. Also ships the checks: erasureresidue asks whether the bytes actually went — on any store, not just this one.
stickies
A persistent sticky-note layer for Claude Code. Claude writes durable facts (decisions, blockers, preferences, context, todos) during a session; they survive resets and are injected back into context on the next start.