Agent skill

sandbox-agent

Run agent CLIs (codex/copilot/opencode) inside a Podman container with full internet access but filesystem exposure limited to the repo root + explicit bind mounts.

View SKILL.md on GitHub Repository
Stars 0
Forks 0

Install this agent skill to your Project

npx add-skill https://github.com/santiago-afonso/sandbox-agent/tree/main/skills/sandbox-agent

SKILL.md

sandbox-agent

Use this when you want:

  • Full egress/network for agent CLIs (web search, fetching, etc.)
  • Tight filesystem boundaries via container bind mounts (repo root + explicit allowlist)

This repo contains a wrapper script intended to be installed as sandbox-agent.

Workflow

  1. Build the image

    From the repo root (this repository):

    bash

podman build -t localhost/sandbox-agent:latest -f Containerfile .


2. **Install the wrapper**

```bash
install -m 0755 sandbox-agent ~/.local/bin/sandbox-agent
  1. (Optional) Configure extra mounts

Create ~/.config/sandbox-agent/config.sh:

bash
CODEX_CONTAINER_SANDBOX_IMAGE="localhost/sandbox-agent:latest"

# Extra read-only mounts (mapped under /home/codex/... if under $HOME)
CODEX_CONTAINER_SANDBOX_RO_MOUNTS=(
  "$HOME/.local/bin"
)

# Extra read-write mounts
CODEX_CONTAINER_SANDBOX_RW_MOUNTS=(
  "$HOME/.cache/uv"
  "$HOME/tmp"
)

  1. Login once inside the container

    bash

sandbox-agent --shell codex login


5. **Run the self-test (recommended)**

```bash
./selftest.sh

If this repo is vendored as a git submodule at ./sandbox-agent/ (for example in a dotfiles repo), either:

  • cd sandbox-agent && ./selftest.sh, or
  • run ./sandbox-agent/selftest.sh from the parent repo root.
  1. Run an agent CLI
bash
sandbox-agent codex exec "Summarize this repo"

Safety notes

  • This wrapper runs with full networking. Anything mounted into the container can be exfiltrated.
  • Keep mounts minimal; do not mount secrets, password stores, SSH keys, or large chunks of $HOME unless you intend to expose them.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

santiago-afonso/repo_clipboard

repo-clipboard

Snapshot the current directory into pseudo-XML for LLM context. Use when you need to share a repo (or a sub-tree) with Codex/LLMs, especially for code review/debugging, generating an agent-friendly “repo snapshot”, or piping context into tools like `llm` (see skill $llm-cli). Supports `.gitignore`-aware file discovery, common ignore patterns, extension filtering, regex include/exclude, optional file-list printing, line-range snippets, and writes `/tmp/repo_clipboard.{stdout,stderr}` for reuse.

1 0
Explore
santiago-afonso/codex-container-sandbox

codex-container-sandbox

Run Codex CLI inside a Podman container with full internet access but filesystem exposure limited to the repo root + explicit bind mounts; use when you want yolo/web-search without giving the agent access to your whole host filesystem.

0 0
Explore
mattpocock/skills

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

111,310 9,758
Explore
mattpocock/skills

obsidian-vault

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

111,310 9,758
Explore
mattpocock/skills

handoff

Compact the current conversation into a handoff document for another agent to pick up.

111,310 9,758
Explore
mattpocock/skills

scaffold-exercises

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

111,310 9,758
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results