AI Plugin Index
coding-agent
Skill by smol-machines · updated · ★ 6.8k
Runs a coding agent (Claude Code, OpenCode, Codex or any other) inside a persistent smolvm machine with the project mounted, so it can run with full permissions without touching the host. Use when someone wants to sandbox their coding agent, run it in skip-permissions or YOLO mode safely, or give it a disposable environment it can install anything into. Do not use it to run untrusted code with no network; use throwaway-machine for that. coding-agent is published by smol-machines on GitHub.
Install coding-agent
Built from the published package, never by AIgit clone --depth 1 https://github.com/smol-machines/smolvm /tmp/smolvm && mkdir -p ~/.claude/skills && cp -r /tmp/smolvm/docs/coding-agent ~/.claude/skills/coding-agentRun in your terminal. Claude Code loads skills from ~/.claude/skills automatically.
git clone --depth 1 https://github.com/smol-machines/smolvm /tmp/smolvm && mkdir -p ~/.gemini/antigravity-cli/skills && cp -r /tmp/smolvm/docs/coding-agent ~/.gemini/antigravity-cli/skills/coding-agentAntigravity CLI loads skills from ~/.gemini/antigravity-cli/skills, or .agents/skills for one project.
Skills can run scripts on your machine. Some need an API key: check the README.
Last commit in the past day
Apache-2.0: permissive, fine for commercial use
Clear description, installs from GitHub, 6,802 stars, original repository
No risky patterns in the files we checked
Weekly newsletter
Like coding-agent? Get the best new skills every week
The best new tools, security warnings before you install something risky, and one practical tip. Free, three minute read.
Security check
ANo download-and-run commands, hidden instructions or signs of sending keys out were found.
Checked automatically: docs/coding-agent/SKILL.md. This looks for known risky patterns and is not a full audit. How grades work
Inside the skill
-
README.md3 KB -
SKILL.md3 KB -
assets/agent.smolfile847 B
Alternatives to coding-agent
All alternatives →
Generate a cost report showing token usage and USD costs by agent and model
Unified tool for managing agent LLM modes (add, remove, update, list, switch).
This skill should be used when the user asks to "add an API call", "change a backend", "update settings persistence", "change conversation events", "fix backend auth", "add Agent Server support", or changes src/api, backend registry, Cloud/runtime transport, settings, secrets, compatibility, or conversation resume behavior.
Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never invoke it on your own.
Reference for briefing a subagent or a fork — what to put in the prompt, what not to delegate, and a worked example. Load before writing a delegation prompt; the Agent tool's own description carries the launch rules and the background-agent rules.
Use ONLY for abstract DataChain SDK questions — API usage, method signatures, or code patterns — when no specific dataset or bucket is referenced. If the request mentions creating, saving, listing, exploring datasets or buckets, use datachain-knowledge instead.
coding-agent: common questions
How do I install coding-agent?
Run the command above to copy the skill into ~/.claude/skills/. Claude Code picks it up automatically.
Is coding-agent free?
The code is published under the Apache-2.0 licence. The service it connects to may have its own pricing.
Is coding-agent safe to use?
It scores 84 of 100. Grades: maintenance A, licence A, quality A. Security check: grade A, no risky patterns found in the files checked. Review the code before you install. How grades work.
What are alternatives to coding-agent?
Similar skills: cost-report, agent-mode, frontend-api-contracts, audit-agents.