xpr-code-sandbox
Execute JavaScript code in a sandboxed VM for data processing and computation.
Setup & Installation
Install command
clawhub install paulgnz/xpr-code-sandboxIf the CLI is not installed:
Install command
npx clawhub@latest install paulgnz/xpr-code-sandboxOr install with OpenClaw CLI:
Install command
openclaw skills install paulgnz/xpr-code-sandboxor paste the repo link into your assistant's chat
Install command
https://github.com/openclaw/skills/tree/main/skills/paulgnz/xpr-code-sandboxWhat This Skill Does
Runs JavaScript code in an isolated V8 sandbox with no network or filesystem access. Supports both full scripts via `execute_js` and quick single-expression evaluation via `eval_expression`. Data is passed in via JSON input and results are returned directly.
Lets an agent perform arbitrary computation mid-workflow without spinning up a separate runtime or exposing the host environment.
When to Use It
- Calculate compound interest across a loan schedule
- Transform and reshape a JSON API response
- Validate a sorting algorithm before deploying
- Convert a CSV of numbers into aggregated statistics
- Compute date differences and format timestamps
View original SKILL.md file
## Code Sandbox You have sandboxed JavaScript execution tools for computation and data processing: **Full scripts:** - `execute_js` — run JavaScript code in an isolated V8 sandbox - Pass data via the `input` parameter (JSON) — access it as `INPUT` in your code - Use `console.log()` to capture intermediate values (returned in `logs` array) - Available globals: `JSON`, `Math`, `Date`, `Array`, `Object`, `String`, `Number`, `RegExp`, `Map`, `Set`, `parseInt`, `parseFloat`, `isNaN`, `isFinite`, `encodeURIComponent`, `decodeURIComponent`, `atob`, `btoa` - No network access, no filesystem, no imports — pure computation only - Default timeout 5 seconds, max 30 seconds - 10MB output limit **Quick expressions:** - `eval_expression` — evaluate a single JavaScript expression and return the result - Use for quick math: `"15 * 4500 * 0.01"` → `675` - Date calculations: `"new Date().toISOString()"` - Array operations: `"[1,2,3].map(x => x*x)"` → `[1, 4, 9]` **Best practices:** - Use `execute_js` for multi-step data processing, algorithm testing, code validation - Use `eval_expression` for quick math, string ops, date calculations - Pass large datasets via `input` parameter rather than embedding in code - Combine with `parse_csv` (structured-data skill) for CSV → transform → output workflows - Combine with `store_deliverable` to save computed results as job evidence
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Calculate compound interest across a loan schedule
- 1Calculate compound interest across a loan schedule
- 2Transform and reshape a JSON API response
- 3Validate a sorting algorithm before deploying
- 4Convert a CSV of numbers into aggregated statistics
- 5Compute date differences and format timestamps
Execute JavaScript code in a sandboxed VM for data processing and computation.
Security Audits
These signals reflect official OpenClaw status values. A Suspicious status means the skill should be used with extra caution.