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.
npx agentmods add skills/jsturtevant/local-code-interpreter-tool/execute-codenpx skills add jsturtevant/local-code-interpreter-tool --skill execute-codegit clone --depth 1 https://github.com/jsturtevant/local-code-interpreter-toolWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00042 | $0.00947 |
| Opus 5 | $0.00021 | $0.00474 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade C, and why
execute-code scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh How it starts
The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute Code Skill
Execute JavaScript or Python code in a secure Hyperlight VM sandbox with full isolation.
This skill is standalone and shareable - it can be copied to any .claude/skills/ directory and works independently of the original repository.
Requirements
- Linux with KVM support (
/dev/kvm) - Python 3.8+
- Git (for cloning hyperlight-nanvix)
- Rust toolchain (installed automatically by setup script)
When to Use
Use this skill when:
- The user asks to run, execute, or test code
- You need to verify calculations or algorithm correctness
- You want to demonstrate code behavior with actual output
Standalone Installation
To use this skill in a new project or share it with others:
1. Copy the Skill
# Copy the entire execute-code directory to your project
cp -r /path/to/execute-code ~/.claude/skills/
# Or for project-specific use:
cp -r /path/to/execute-code /your/project/.claude/skills/
2. Run Setup
cd ~/.claude/skills/execute-code
./scripts/setup.sh
The setup script will:
- Create a virtual environment in
.venv - Install Rust nightly toolchain (if not present)
- Clone and build
hyperlight-nanvixfrom source - Configure everything for standalone use
3. Activate and Use
source .venv/bin/activate
python3 scripts/run.py --lang javascript --code 'console.log("Hello!");'
Quick Start
JavaScript
python3 scripts/run.py --lang javascript --code 'console.log(2 + 2);'
Python
python3 scripts/run.py --lang python --code 'print(2 + 2)'
Usage Notes
- JavaScript: Use
console.log()to see output - Python: Use
print()to see output - Code runs in VM-isolated sandbox (hyperlight-nanvix)
- The skill is self-contained with its own virtual environment
Examples
Calculate Fibonacci
python3 scripts/run.py --lang javascript --code '
const fib = n => n <= 1 ? n : fib(n-1) + fib(n-2);
for (let i = 0; i < 10; i++) console.log("fib(" + i + ") =", fib(i));
'
What ships with it
4 files beside SKILL.md 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.
- yesterday First seen · 135 lines · 42 tokens per session scan C 7efe887d1597
execute-code is a skill published in the GitHub repository jsturtevant/local-code-interpreter-tool (2 stars, last pushed 7mo ago), licensed MIT. It adds 42 tokens to every session and 947 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…