sandbox SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 4 indexed copies. Same content hash, so the same checks give both the same grade.

sandbox from jakeselby/agent-harness is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add jakeselby/agent-harness/sandbox@git:20261009.a4aa40b

Pins git:20261009.a4aa40b in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
jakeselby/agent-harness
Path
directory/model-citizen/primitives/skills/sandbox/SKILL.md
Versions recorded
3
Latest version
git:20261009.a4aa40b, committed Oct 9, 2026
First version recorded
Sep 28, 2026
Size
4,454 bytes
Repository stars
24
License
MIT

Fence an autonomous or long-running agent loop with the built-in sandbox and 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.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file 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superseded by the parent turn's permissions; see `docs/runtime-controls.md` before delegating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. Merge [claude-settings.json](claude-settings.json) into
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add jakeselby/agent-harness/sandbox@sha256:cad29b2b44b06160

The line at the top of this page pins the label git:20261009.a4aa40b, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uwkbjh242nnsy73j.svg)](https://markdownregistry.com/a/art_uwkbjh242nnsy73j)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 3 versions of this file, between Sep 28, 2026 and Oct 9, 2026, about one every 5 days. Its first recorded version is graded B and its latest A.

versioncommittedcommitsizeaudit
git:20261009.a4aa40b latest2026-10-09 a4aa40b 4,454 BA view · diff
git:20261006.39b41722026-10-06 39b4172 4,143 BA view · diff
git:20260928.ca93e6d2026-09-28 ca93e6d 4,187 BB view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (4454 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 instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

jakeselby/agent-harness · 24 stars · license MIT · pushed 2026-10-15 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uwkbjh242nnsy73j
GET https://markdownregistry.com/api/v1/resolve?ref=jakeselby/agent-harness/sandbox
GET https://markdownregistry.com/api/v1/blob/cad29b2b44b061606b21a892edbe07c4ae1108845d4a50387d22cfe6a6625345

Your AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from jakeselby/agent-harness

AGENTS.md AGENTS.md file
jakeselby/agent-harness · AGENTS.md
git:20261004.61824f0 · audit A · 24 stars
CLAUDE.md CLAUDE.md file
jakeselby/agent-harness · CLAUDE.md
git:20260916.a87d7de · audit B · 24 stars
DESIGN.md@_bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-19 DESIGN.md file
jakeselby/agent-harness · _bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-19/DESIGN.md
git:20260923.47f11bb · audit A · 24 stars
DESIGN.md@_bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-23 DESIGN.md file
jakeselby/agent-harness · _bmad-output/planning-artifacts/ux-designs/ux-agent-harness-2026-09-23/DESIGN.md
git:20260928.3df90ff · audit A · 24 stars
CLAUDE.md@claude CLAUDE.md file
jakeselby/agent-harness · claude/CLAUDE.md
git:20260926.42228ff · audit A · 24 stars
api-verification SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/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:20260929.1af83d7 · audit A · 24 stars
architecture-viewer SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/primitives/skills/architecture-viewer/SKILL.md · Open or update an architecture diagram with the selected builtin or custom viewer, preserving a neutral session…
git:20260928.ca93e6d · audit A · 24 stars
code-quality-instruments SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/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:20260928.ca93e6d · audit A · 24 stars
delegation-tiering SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/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:20261006.b2bd78a · audit A · 24 stars
design-loop SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/primitives/skills/design-loop/SKILL.md · Raise the visual quality of something that renders through a build, screenshot, independent scored critique and fix…
git:20261006.b2bd78a · audit A · 24 stars
harness-authoring SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/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:20260928.ca93e6d · audit A · 24 stars
licensing-review SKILL.md skill
jakeselby/agent-harness · directory/model-citizen/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:20260928.ca93e6d · audit A · 24 stars

Every file in jakeselby/agent-harness

Other files named sandbox

sandbox SKILL.md 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 · 2,990 stars
sandbox SKILL.md skill
jakeselby/model-citizen · directory/model-citizen/primitives/skills/sandbox/SKILL.md · Fence an autonomous or long-running agent loop with the built-in sandbox and network off, or a container with the…
git:20261009.a4aa40b · audit A · 24 stars
sandbox SKILL.md skill
jakeselby/agent-harness · primitives/skills/sandbox/SKILL.md · Fence an autonomous or long-running agent loop with the built-in sandbox and network off, or a container with the…
git:20261009.a4aa40b · audit A · 24 stars
sandbox SKILL.md skill
jakeselby/model-citizen · primitives/skills/sandbox/SKILL.md · Fence an autonomous or long-running agent loop with the built-in sandbox and network off, or a container with the…
git:20261009.a4aa40b · audit A · 24 stars
sandbox SKILL.md 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:20261002.fd2015d · audit A · 12 stars

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