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/mcpc-tech/code-runner-mcp/code-runnernpx skills add mcpc-tech/code-runner-mcp --skill code-runnergit clone --depth 1 https://github.com/mcpc-tech/code-runner-mcpWhat 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 | $0.00060 | $0.02008 |
| Opus 5 | $0.00030 | $0.01004 |
| Sonnet 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 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.
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.
- yesterday 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 3mo ago), licensed MIT. It adds 60 tokens to every session and 2,008 once invoked, about $0.0003 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 2026-08-31.
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…