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.
/plugin marketplace add vedantnimbarte/kortex-memorynpx agentmods add plugins/vedantnimbarte/kortex-memory/plugingit clone --depth 1 https://github.com/vedantnimbarte/kortex-memoryGrade A, and why
kortex-memory 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": "kortex-memory",
"displayName": "Kortex Memory",
"version": "0.1.0",
"description": "Persistent, governed memory for Claude Code. Remember decisions once; recall them in every future session, across every tool on the team.",
"author": {
"name": "Kortex Memory",
"url": "https://github.com/vedantnimbarte/kortex-memory"
},
"homepage": "https://github.com/vedantnimbarte/kortex-memory",
"repository": "https://github.com/vedantnimbarte/kortex-memory",
"keywords": ["memory", "mcp", "rag", "context", "recall"],
"userConfig": {
"mcp_url": {
"type": "string",
"title": "Kortex MCP endpoint",
"description": "The SSE endpoint of your Kortex MCP server, e.g. https://kortex.example.com:8765/sse. For a local `make dev` stack this is http://localhost:8765/sse.",
"default": "http://localhost:8765/sse",
"required": true
},
"api_key": {
"type": "string",
"title": "Kortex API key",
"description": "A kx_* key from `kortex key create`. Scoped to one org, so it decides which memories this machine can read and write.",
"sensitive": true,
"required": true
}
},
"mcpServers": "./.mcp.json",
"skills": "./skills/"
}
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 · 32 lines scan A f61804950bb4
kortex-memory is a plugin published in the GitHub repository vedantnimbarte/kortex-memory (2 stars, last pushed 2d 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 2026-08-31.
Other plugins, from other repositories
akb-claude-code
Bridge Claude Code's session lifecycle into AKB's agent-memory vault.
akb-sessions
Ingest coding sessions into an AKB vault as structured notes.
declaude
Rewrites Claude-English into plain English: sycophantic openers, hedging filler and padded phrasing out, facts, code blocks, names and numbers untouched. Runs an open-weights model on dedicated GPUs, so text never reaches a commercial AI provider.
fastapi-best-practices
FastAPI best practices — 3 skills, 41 rules total, grounded in the official FastAPI docs, with incorrect/correct examples. Core skill (33 rules: models, params, structure, DI, errors, async, streaming, background/config, lifespan, middleware, docs) plus dedicated fastapi-security (5 rules) and fastapi-testing (3…
audiolla
Self-hosted audio-production API — stem separation, mastering, MIR analysis, DSP chains, MIDI, and AI restoration over REST and MCP.
open-python-skills
Plugin marketplace listing 1 plugin: open-python-skills.