code_execution

A coding add-on for running Python programs, calculations, and data processing in a restricted environment. It supports common tasks such as arithmetic, JSON handling, statistics, dates, and collection processing.

In plain words
What is it for?
Running calculations, transforming structured data, processing text, testing small algorithms, and executing Python scripts with supported standard-library modules.
Why use it?
It provides a controlled place to execute small scripts and inspect results without setting up a separate runtime. The restrictions make clear which operations and libraries are available.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/frontier-ai-next/mgarlbot/code_execution
Any agent
npx skills add frontier-ai-next/mgarlbot --skill code_execution
Clone the repo
git clone --depth 1 https://github.com/frontier-ai-next/mgarlbot

Made for: Claude Code, Codex.

Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 261 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.00014 $0.00261
Opus 5 $0.00007 $0.00130
Sonnet 5 $0.00003 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured 3d ago against content hash b76fe8e30d8a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code_execution 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 3d ago.

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.

skills/code_execution/SKILL.md · 45 lines

What it actually says

Code execution

Use the code interpreter (sandboxed Python).

Simple math

result = 2 ** 10
print(f"2^10 = {result}")

Data handling

import json
data = {"name": "test", "values": [1, 2, 3]}
print(json.dumps(data, indent=2))

Commonly allowed modules (safe mode)

  • math, statistics
  • json
  • re
  • datetime
  • collections
  • itertools, functools
  • random

Rules

  1. Use code_interpreter for math and in-sandbox data work.
  2. Use shell for filesystem operations on the host.
  3. Imports are restricted — only allowed modules work.
  4. Always print() results; otherwise output may be empty.
  5. Prefer one coherent code block for multi-step logic.
Changes

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.

  1. 3d ago First seen · 45 lines · 14 tokens per session scan A b76fe8e30d8a

Subscribe to this mod's changes

code_execution is a skill published in the GitHub repository frontier-ai-next/mgarlbot (17 stars, last pushed 26d ago), licensed MIT. It adds 14 tokens to every session and 261 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-30.