Borrowing it
Nothing to install: this file belongs to mcpc-tech/code-runner-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mcpc-tech/code-runner-mcp/main/.agent/skills/code-runner/SKILL.mdgit clone --depth 1 https://github.com/mcpc-tech/code-runner-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mcpc-tech/code-runner-mcp/code-runner)<a href="https://agentmods.dev/skills/mcpc-tech/code-runner-mcp/code-runner"><img src="https://agentmods.dev/badge/skills/mcpc-tech/code-runner-mcp/code-runner/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mcpc-tech/code-runner-mcp/code-runner"><img src="https://agentmods.dev/badge/skills/mcpc-tech/code-runner-mcp/code-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.02008 |
| Opus 5.5 | $0.00024 | $0.00803 |
| Sonnet 5.5 | $0.00012 | $0.00402 |
| Haiku 4.5 | $0.00006 | $0.00201 |
Grade A, and why
code-runner 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
code-runner-mcp Skill
This skill helps you use the code-runner-mcp tools and CLI to execute
JavaScript/TypeScript (via Deno) or Python (via Pyodide/WASM) code in a secure,
isolated sandbox with on-demand package installation.
Available Tools
Two MCP tools are registered when the server is running:
| Tool | Language | Runtime |
|---|---|---|
javascript-code-runner |
JS / TS | Deno (subprocess) |
python-code-runner |
Python | Pyodide (WASM) |
Both tools return combined stdout + stderr as text.
CLI Usage
No Deno?
- Install:
npm i -g deno- Or skip install entirely: replace
deno run --allow-allwithnpx -y deno run --allow-allSilent mode — suppress Deno's download/progress output:
deno run --allow-all --quiet jsr:@mcpc/code-runner-mcp/cli js "console.log('hello')"
# Inline code
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli js "console.log('hello')"
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli py "print(1 + 2)"
# From a file
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli js --file ./script.ts
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli py --file ./analysis.py
# Piped from stdin
echo "print('piped')" | deno run --allow-all jsr:@mcpc/code-runner-mcp/cli py
cat app.ts | deno run --allow-all jsr:@mcpc/code-runner-mcp/cli js
# Python with package mapping
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli py --file analysis.py \
--packages '{"sklearn":"scikit-learn","PIL":"Pillow"}'
# Python with host filesystem mount
deno run --allow-all jsr:@mcpc/code-runner-mcp/cli py --file script.py \
--nodefs-root /tmp --nodefs-mount /tmp
CLI Flags
| Flag | Alias | Description |
|---|---|---|
--file <path> |
-f |
Read code from a file |
--packages <json> |
-p |
Python: map import→PyPI names (JSON) |
--nodefs-root <dir> |
Python: host dir to mount | |
--nodefs-mount <dir> |
Python: mount point in Pyodide FS | |
--help |
-h |
Show help |
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.
- 2mo ago First seen · 190 lines · 60 tokens per session scan A 36a2b65be05b
code-runner is a skill published in the GitHub repository mcpc-tech/code-runner-mcp (5 stars, last pushed 5mo ago), licensed MIT. It adds 60 tokens to every session and 2,008 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
code-runner compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| code-runnermcpc-tech/code-runner-mcp | Skill | 5 | 5mo ago | MIT | A | 60 | Claude Code, Codex |
| effect-v4ComposioHQ/composio | Skill | 31k | yesterday | MIT | A | 159 | Claude Code, Codex |
| langgraph-docslangchain-ai/deepagents | Skill | 31k | yesterday | MIT | A | 62 | Claude Code, Codex |
| stripe-projectse2b-dev/E2B | Skill | 15k | yesterday | Apache-2.0 | A | 51 | Claude Code, Codex |
| migrating-vercel-ai-sdk-and-eve-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 107 | Codex |
| migrating-mastra-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 73 | Codex |
| migrating-pi-to-pydantic-aipydantic/pydantic-ai | Skill | 21k | yesterday | MIT | A | 88 | Codex |