Home / jakeselby / agent-harness · primitives/skills/sandbox/SKILL.md · GitHub

sandbox skillB

sandbox is agent-read markdown (skill) from jakeselby/agent-harness: Fence an autonomous or long-running agent loop: the built-in sandbox with network off, or a container with the worktree mounted. Use before any unattended loop, before `execute` autonomy on an unfamiliar repo, and whenever a task pulls untrusted input..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Fence the loop

A permission mode decides whether a call runs. A sandbox decides what a command can reach once it
is running, and the OS enforces that on every child process. An unattended loop needs the second
kind: nobody is at the prompt to answer for the first.

## Runtime scope

The configuration and container example below are Claude Code-specific. Do not copy those
settings into Codex. For Codex, use its native sandbox and approval controls as documented in
[the configuration reference](https://learn.chatgpt.com/docs/config-file/config-reference).
A read-only sandbox constrains filesystem writes; approval policy is a separate control.
Native hooks are not a replacement for OS confinement. Custom Codex role defaults can be
superseded by the parent turn's permissions; see `docs/runtime-controls.md` before delegating
work that requires a hard boundary. Client qualification remains in the compatibility catalog.

## The Claude Code sandbox

It "runs on macOS, Linux, and WSL2. Native Windows is not supported"; Linux and WSL2 need
`bubblewrap` and `socat` installed first. Put this in `~/.claude/settings.json` to cover every
…

Read the whole file at its exact version.

How to install

Latest version
mdr add jakeselby/agent-harness/sandbox@git:20260923.097bdb0
Exact content
mdr add jakeselby/agent-harness/sandbox@sha256:5645a919019a716b

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_c74gwzohxrdkb7e4.svg)](https://markdownregistry.com/a/art_c74gwzohxrdkb7e4)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260923.097bdb0 latest2026-09-23 097bdb0 4,395 BB view · diff
git:20260919.04aa2b52026-09-19 04aa2b5 4,432 BB view · diff
git:20260919.6cf18f72026-09-19 6cf18f7 3,767 BB view

Audit of the latest version

B  16 of 17 checks passed. Deterministic, no model, same answer every run.
  • fail: No instruction to read or print local credentials (matched: Read": ["~/.ssh", "~/.aws)
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4395 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jakeselby/agent-harness · 17 stars · license MIT · pushed 2026-09-25 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_c74gwzohxrdkb7e4
GET https://markdownregistry.com/api/v1/resolve?ref=jakeselby/agent-harness/sandbox
GET https://markdownregistry.com/api/v1/blob/5645a919019a716b33675f97d55b73e22ae12e36b4cea4c9f1f985d4b970bd69

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from jakeselby/agent-harness

AGENTS.md agents
jakeselby/agent-harness · AGENTS.md
git:20260923.a2727a5 · audit A · 17 stars
CLAUDE.md claude
jakeselby/agent-harness · CLAUDE.md
git:20260916.a87d7de · audit B · 17 stars
DESIGN.md@_bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-19 design
jakeselby/agent-harness · _bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-19/DESIGN.md
git:20260923.47f11bb · audit A · 17 stars
DESIGN.md@_bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-23 design
jakeselby/agent-harness · _bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-23/DESIGN.md
git:20260924.ef349b6 · audit A · 17 stars
CLAUDE.md@claude claude
jakeselby/agent-harness · claude/CLAUDE.md
git:20260918.a2310f4 · audit A · 17 stars
api-verification skill
jakeselby/agent-harness · primitives/skills/api-verification/SKILL.md · Prove a search, filter or API answer is real before relying on it, and budget web search across a fan-out. Use when…
git:20260923.097bdb0 · audit A · 17 stars
architecture-viewer skill
jakeselby/agent-harness · primitives/skills/architecture-viewer/SKILL.md · Open or update an architecture diagram with the selected builtin or custom viewer, preserving a neutral session…
git:20260923.097bdb0 · audit A · 17 stars
code-quality-instruments skill
jakeselby/agent-harness · primitives/skills/code-quality-instruments/SKILL.md · Measure whether a test suite is any good, not only that it passes: branch coverage, mutation score…
git:20260923.097bdb0 · audit A · 17 stars
delegation-tiering skill
jakeselby/agent-harness · primitives/skills/delegation-tiering/SKILL.md · Decide whether to spawn a subagent, and on which model tier and reasoning effort. Use when planning a fan-out, choosing…
git:20260923.c9e2ec3 · audit A · 17 stars
design-loop skill
jakeselby/agent-harness · primitives/skills/design-loop/SKILL.md · Raise the visual quality of something that already renders: build, screenshot, independent scored critique, fix…
git:20260923.c9e2ec3 · audit A · 17 stars
harness-authoring skill
jakeselby/agent-harness · primitives/skills/harness-authoring/SKILL.md · Decide where an instruction belongs and write it there, then sync and lint. Use when asked to add, change or remove a…
git:20260923.097bdb0 · audit A · 17 stars
licensing-review skill
jakeselby/agent-harness · primitives/skills/licensing-review/SKILL.md · Verify a third-party library, asset, model, font, dataset or copied snippet is safe to ship under the project's…
git:20260923.097bdb0 · audit A · 17 stars

Every file in jakeselby/agent-harness

Other files named sandbox

sandbox skill
alsk1992/cloddsbot · src/skills/bundled/sandbox/SKILL.md · Visual HTML canvas sandbox for agent-driven UI and live previews
git:20260210.cd0fc2e · audit A · 2,830 stars
sandbox skill
marcel-bich/marcel-bich-claude-marketplace · plugins/credo/skills/sandbox/SKILL.md · Do WRITING pre-work for a clarify item that is blocked by a knowledge gap - a missing measurement, a mockup, or a…
git:20260821.cb596ad · audit A · 12 stars

Browse by kind, by grade B, or by owner.