opencode-sandbox-safety
Use when evaluating safety, isolation, temp dirs, secrets, MCP side effects, or worktree choices for opencode-child runs.
Skill by mcrescenzo
Chalk Labs
Need help deploying opencode-sandbox-safety?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/mcrescenzo-opencode-sandbox-safety
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/opencode-sandbox-safety
What's inside
- Skill name
opencode-sandbox-safety- Description
- Use when evaluating safety, isolation, temp dirs, secrets, MCP side effects, or worktree choices for opencode-child runs.
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# opencode Sandbox Safety `opencode-child` starts real local opencode processes. Treat plugins and child prompts as arbitrary local code execution. When a child run may edit files (plugin authoring, config changes, or prompts that call file-editing tools), point it at a scratch project directory or a git worktree instead of a directory you care about, so an unexpected edit or permission grant cannot touch real work. Use these defaults: - Bind to `127.0.0.1`. - Use random ports. - Prefer scratch project dirs or worktrees for edit tests. - Keep `dangerouslySkipPermissions` off unless `trustMode` is explicitly `full-trust`. - Stop every child and verify the PID is gone. `safe` mode is best-effort local isolation, not a security sandbox. It may still inherit auth, environment, config, commands, agents, tools, or MCP behavior depending on opencode and project configuration.
From mcrescenzo/opencode-child, MIT.
More from mcrescenzo/opencode-child
- 0.474score
opencode-child-orchestration
mcrescenzo
Use when starting, inspecting, restarting, stopping, or prompting disposable child opencode servers with the opencode-child plugin tools.
SkillCFreshness: CClaude Code +9 - 0.469score
opencode-permission-triage
mcrescenzo
Use when a child opencode session has pending permission requests or permission-related hangs during opencode-child testing.
SkillCFreshness: CClaude Code +9 - 0.469score
opencode-server-api-debugging
mcrescenzo
Use when child opencode server startup, health checks, event streams, session prompts, registry inspection, or stop behavior fails.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 7, 2026 (3 months ago)
- Last release
- Jul 22, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/mcrescenzo/opencode-child
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from mcrescenzo
- 0.474score
opencode-child-orchestration
mcrescenzo
Use when starting, inspecting, restarting, stopping, or prompting disposable child opencode servers with the opencode-child plugin tools.
SkillCFreshness: CClaude Code +9 - 0.469score
opencode-permission-triage
mcrescenzo
Use when a child opencode session has pending permission requests or permission-related hangs during opencode-child testing.
SkillCFreshness: CClaude Code +9 - 0.469score
opencode-server-api-debugging
mcrescenzo
Use when child opencode server startup, health checks, event streams, session prompts, registry inspection, or stop behavior fails.
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get opencode-sandbox-safety running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
opencode-sandbox-safety skill. Agent Mart. https://agentmart.dev/skills/mcrescenzo-opencode-sandbox-safety (last updated 2026-10-24)