extensions
This is the raw dev repo for "QuanuX" (Quant-Linux). Official releases are available via @QuanuX org. Quantitative Framework for Research, Development and Deployment of Proprietary Trading Strategies. Website under development.
Install / Use
npx skills add quantDIY/QuanuX --skill extensionsInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
SecuritySupported Platforms
Our assessment of extensions
extensions scores 69/100 on our quality scale, 1066th of 1,122 Security skills we index.
Its SKILL.md is 4.1 KB long, well organised into 12 sections with 3 code examples: a solid amount of guidance for an agent.
It has no GitHub stars yet, so there is no community track record; judge it on its content.
Maintenance, license and trust
- The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
- Our last check on 2026-09-26 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 78/100, with 2 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-09-24. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
extensions compared with similar skills
All 4 of these similar skills score higher than extensions; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| extensions (this skill)by quantDIY | 69 | 0 | 6mo ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 15d ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 15d ago | SKILL.md |
| designby nextlevelbuilder | 100 | 133.6k | 4d ago | SKILL.md |
| ui-ux-pro-maxby nextlevelbuilder | 100 | 133.6k | 4d ago | SKILL.md |
Frequently asked questions
- How do I install extensions?
- Run
npx skills add quantDIY/QuanuX --skill extensions. The install tabs above show the steps for each supported agent. - Which AI agents does extensions work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is extensions safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 78/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is extensions still maintained?
- The repository was last updated about 6 months ago. That is recent enough to be usable, but agent tooling moves fast, so check the instructions against your agent's current version.
Skill content
View source on GitHubname: quanux-extension-standards description: The authoritative "School of Architecture" for building QuanuX Extensions (Sidecars). Enforces the QXP protocol, Go runtime preference, and privacy-first security model. metadata: version: 1.0.0 author: QuanuX priority: 10
QuanuX Extension Standards (QXP)
"Bolt-on, don't Build-in."
This skill defines the architecture for extending QuanuX. We prefer Sidecar Processes over monolithic plugin systems. This ensures isolation, stability, and polyglot capability, though Go is the standard.
1. The "Sidecar" Philosophy
An extension is a standalone binary that runs alongside the Core Server.
- Isolation: If the extension crashes, Core survives.
- Performance: Extensions perform heavy lifting (websocket streaming, encoding) outside the Python GIL.
- Privacy: Extensions run locally. No data leaves the machine unless the extension explicitly does so (and the user configured it).
2. Directory Structure
All extensions reside in the root /extensions directory.
/extensions
/my-extension
/cmd # (Optional) if complex
main.go # Entrypoint (Go)
extension.yaml # Manifest
README.md
3. The Manifest (extension.yaml)
Every extension MUST have a manifest.
name: "sierra-chart-bridge"
display_name: "Sierra Chart Connector"
version: "0.0.1"
runtime: "go" # or "node", "python" (Go preferred)
command: "./dist/sierra-bridge" # Relative to extension dir
- "market.data.read"
- "strategy.execute"
env:
- "QUANUX_BRIDGE_KEY" # Injected by quanuxctl
upstream_repo: "https://github.com/my/repo.git" # (Optional) Enable Package Management
4. Package Management (Lifecycle)
Extensions can opt-in to managed upgrades by defining upstream_repo in extension.yaml.
- Versioning:
quanuxctlwill querygit ls-remote --tagson the upstream repo. - Build Script:
quanuxctlpassesQUANUX_EXT_VERSIONenvironment variable tobuild.sh.- Your
build.shMUST prioritize this variable over hardcoded versions. - Example:
VERSION=${QUANUX_EXT_VERSION:-"v1.0.0"}.
- Your
- Commands: This enables
quanuxctl upgrade,upgradeable, andinstall -v.
5. Communication Protocol
Inbound (Core -> Extension)
- Extensions SHOULD expose an HTTP or gRPC server.
- They
LISTENon a configurable port (default range 9000-9100).
Outbound (Extension -> Core)
- Extensions connect to QuanuX Core via WebSocket or HTTP.
- Auth: Use
QUANUX_BRIDGE_KEY(injected via ENV) to authenticate with Core.
5. Security & Secrets
- NO Hardcoded Creds: Never store API keys in code.
- Keyring: Use the System Keyring via
quanuxctlorserver/security/secrets.py. - Injection: Secrets are injected as Environment Variables at runtime.
6. Implementation Guide (Go)
New extensions should use the standard Go layout:
package main
import (
"net/http"
"os"
"log"
)
func main() {
// 1. Read Config (Env Vars)
bridgeKey := os.Getenv("QUANUX_BRIDGE_KEY")
if bridgeKey == "" {
log.Fatal("QUANUX_BRIDGE_KEY required")
}
// 2. Setup Server
mux := http.NewServeMux()
mux.HandleFunc("/health", healthHandler)
// 3. Start
port := os.Getenv("PORT")
if port == "" { port = "9000" }
log.Fatal(http.ListenAndServe(":"+port, mux))
}
## 7. Remote Connectivity & Port Forwarding
**Protocol**: Extensions MUST support remote deployments where the Target App (e.g. Sierra Chart) is on a different machine than QuanuX Core.
- **Configurable Host/Port**:
- NEVER hardcode `localhost`.
- ALWAYS accept `QUANUX_<NAME>_HOST` and `QUANUX_<NAME>_PORT`.
- **Tunneling Support**:
- This design explicitly supports **SSH Tunneling** (e.g. `ssh -R`) and **Reverse Proxies**.
- Example: QuanuX (Cloud) -> Connects to `localhost:11099` (Tunneled) -> User PC (Sierra Chart).
- Extensions must handle connection drops gracefully (reconnect logic) to support tunnel restarts.
8. Specialized Extensions
- Rithmic Integration - Official Protobuf Implementation & Developer Guide.
Related Skills
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
design
133.6kComprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini, Atlas Cloud, or MuAPI AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG…
ui-ux-pro-max
133.6kUI/UX design intelligence for web, mobile, and desktop. This skill should be used when designing, building, reviewing, or fixing interfaces, including pages, components, design systems, accessibility, interaction, responsive layout, typography, color, charts, and stack-specific UI implementation.
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
