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/julymetodiev/post-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/julymetodiev/post-cortex/claude-code)<a href="https://agentmods.dev/plugins/julymetodiev/post-cortex/claude-code"><img src="https://agentmods.dev/badge/plugins/julymetodiev/post-cortex/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/julymetodiev/post-cortex/claude-code"><img src="https://agentmods.dev/badge/plugins/julymetodiev/post-cortex/claude-code.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
post-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 today.
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": "post-cortex",
"displayName": "post-cortex",
"version": "0.7.0",
"description": "Long-term project memory for Claude Code: the post-cortex MCP server (cloud by default, or your own daemon), the post-cortex-memory skill, and hooks that keep the memory in front of every session.",
"author": {
"name": "Julius ML",
"url": "https://github.com/julymetodiev"
},
"homepage": "https://post-cortex.com",
"privacyPolicyUrl": "https://post-cortex.com/privacy",
"repository": "https://github.com/julymetodiev/post-cortex",
"license": "MIT",
"keywords": [
"memory",
"mcp",
"knowledge-graph",
"semantic-search",
"context",
"post-cortex"
],
"userConfig": {
"url": {
"type": "string",
"title": "post-cortex URL",
"description": "Base URL of the post-cortex server, without a trailing slash. Keep the default for post-cortex cloud; for a self-hosted daemon use e.g. http://127.0.0.1:3737.",
"default": "https://api.pcx.is",
"required": true
},
"api_key": {
"type": "string",
"title": "post-cortex API key",
"description": "Bearer token for the server: your post-cortex cloud API key, or the auth_token of your own daemon. Leave empty for a local daemon without auth_token.",
"sensitive": true
}
},
"icon": ".claude-plugin/icon.png"
}
What it installs
The manifest is a name and a version. 4 hooks, 1 MCP server 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 ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed 5d907107b5cb
- yesterday Changed cc6d6fa9f97c
- 2d ago First seen · 39 lines scan A cdbd2e0be961
post-cortex is a plugin published in the GitHub repository julymetodiev/post-cortex (20 stars, last pushed today), 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 2026-11-16.
post-cortex compared with plugins from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| post-cortexjulymetodiev/post-cortex | Plugin | 20 | today | MIT | A | — | Claude Code |
| memoraagentic-box/memora | Plugin | 749 | 8d ago | MIT | A | — | Claude Code |
| ElpisMasihMoafi/Elpis | Plugin | 54 | today | Apache-2.0 | A | — | Gemini CLI |
| khiveohdearquant/khive | Plugin | 34 | today | Apache-2.0 | A | — | Claude Code |
| alice-memorysamrusani/AliceMemory | Plugin | 5 | yesterday | MIT | A | — | Claude Code |
| rekal-skillsjanbjorge/rekal | Plugin | 52 | 2mo ago | MIT | A | — | Claude Code |
| inite-braininite-ai/inite-brain-service | Plugin | 43 | today | AGPL-3.0 | A | — | Gemini CLI |