Is the Code Execution skill free?

Yes. The skill itself is free from mhattingpete/claude-skills-marketplace. SkillProof publishes the install command and an independent test verdict at no cost.

How do I install Code Execution?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Code Execution with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Code Execution

Run local Python for bulk code ops, returning summaries instead of full source

by mhattingpete · mhattingpete/claude-skills-marketplace

Tested · Didn't pass

Read why it failed Download source ↗

Test report

Verdict: Tested · Didn't pass
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · efe4fd6

Installed the runtime exactly as setup.sh does (pip install -e .) into a temp venv under a temp HOME. The documented entrypoint `from execution_runtime import fs, code, transform, git` failed with ImportError: security/__init__.py imports module-level `mask_result`, which only exists as a PIIDetector method (line 200), and the fallback imports a non-existent `mcp_server`. Bypassing the broken facade with `from api import code_transform`, rename_identifier correctly renamed `oldName`->`newName` across 3 files and returned {'files_modified': 3, 'total_replacements': 12}. A naive baseline regex rename produced a byte-identical output file, so file output is no better than baseline; the only difference is the compact summary return vs full source in context.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 4/10
Docs & honesty 2/5

What Code Execution does

A skill that directs Claude to run local Python via an execution_runtime package (fs/code/transform/git APIs) for bulk file operations, renames, and metadata-only code analysis, returning compact summaries to save context tokens. Triggers on bulk operations across 10+ files, multi-step refactors, or mentions of efficiency. The documented import path is broken on a clean install, so it currently requires a source patch to use.

How to install Code Execution

# BROKEN on clean install: the documented `from execution_runtime import ...` raises
# ImportError (mask_result is a PIIDetector method, not a module function; fallback
# imports non-existent mcp_server). Underlying api/ modules work if you patch that.
git clone --depth 1 https://github.com/mhattingpete/claude-skills-marketplace.git /tmp/code-execution-src
mkdir -p ~/.claude/skills
cp -R /tmp/code-execution-src/code-operations-plugin/skills/code-execution ~/.claude/skills/code-execution
# Runtime (required for the skill to do anything):
#   cd /tmp/code-execution-src/execution-runtime && pip install -e .
# Then to actually import it, fix execution_runtime/security/__init__.py and
# execution_runtime/__init__.py: remove `mask_result` from the imports, OR add a
# module-level `def mask_result(...)` wrapper in security/pii_detector.py.
# Without that patch, `from execution_runtime import fs, code, transform, git` fails.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Code Execution

/code-execution Run local Python for bulk code ops, returning summaries instead of full source

It also activates on plain-language prompts like these:

Process these 50 files locally instead of one by one
Run this bulk marketplace API workflow efficiently
Execute this iterative data processing task locally

Frequently asked questions

Is the Code Execution skill free?: Yes. The skill itself is free from mhattingpete/claude-skills-marketplace. SkillProof publishes the install command and an independent test verdict at no cost.
Does Code Execution work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Didn't pass. Installed the runtime exactly as setup.sh does (pip install -e .) into a temp venv under a temp HOME. The documented entrypoint `from execution_runtime import fs, code, transform, git` failed with ImportError: security/__init__.py imports module-level `mask_result`, which only exists as a PIIDetector method (line 200), and the fallback imports a non-existent `mcp_server`. Bypassing the broken facade with `from api import code_transform`, rename_identifier correctly renamed `oldName`->`newName` across 3 files and returned {'files_modified': 3, 'total_replacements': 12}. A naive baseline regex rename produced a byte-identical output file, so file output is no better than baseline; the only difference is the compact summary return vs full source in context.
How do I install Code Execution?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Code Execution with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.