ls-skill-sandbox-tester SKILL.md skillA

ls-skill-sandbox-tester from cruxexperts/localsetup is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add cruxexperts/localsetup/ls-skill-sandbox-tester@v1.0

Pins v1.0 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
cruxexperts/localsetup
Path
ls/skills/ls-skill-sandbox-tester/SKILL.md
Versions recorded
5
Latest version
v1.0, committed Oct 21, 2026
First version recorded
Oct 21, 2026
Size
14,227 bytes
Repository stars
6
License
a license file GitHub does not identify

Test normalized skills in a bounded temporary staging copy before production. Creates a provenance-marked copy under platform temp, rejects symlinked inputs, runs smoke checks with a minimal environment, and uses ls-debug-reproducible-failures on failure; no writes return to the repo until user approval. Use when validating a framework-compliant skill end-to-end on a supported platform.

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

# Skill Sandbox Tester

**Purpose:** Validate skills in a bounded temporary staging copy so bugs are found and fixed before production promotion. The helpers enforce copy provenance, temporary-root containment, symlink rejection, and environment minimization; **ls-debug-reproducible-failures** owns the fix loop. No changes return to the repository until the user approves.

## When to use this skill

- User wants to "test this skill," "validate the skill after import," "run the skill in a sandbox," or "make sure the skill works before we use it."
- After a skill has been vetted and normalized (not right after import), user wants to run it safely in a sandbox and fix any issues before production.
- User wants to confirm a skill runs correctly on a supported platform listed in PLATFORM_REGISTRY without affecting the repo.

## How it actually works
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add cruxexperts/localsetup/ls-skill-sandbox-tester@sha256:80bc4714ade5a717

The line at the top of this page pins the label v1.0, 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_hyvh326u7anxq2wq.svg)](https://markdownregistry.com/a/art_hyvh326u7anxq2wq)

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

Versions

The registry has recorded 5 versions of this file, all committed on Oct 21, 2026.

versioncommittedcommitsizeaudit
v1.0 latest2026-10-21 67214c1 14,227 BA view · diff
v1.02026-10-21 18205cf 14,217 BA view · diff
v1.02026-10-21 8b5ce8a 14,211 BA view · diff
v1.02026-10-21 a1ea173 14,203 BA view · diff
v1.02026-10-21 460970e 14,197 BA 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 (14227 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

cruxexperts/localsetup · 6 stars · license a license file GitHub does not identify · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_hyvh326u7anxq2wq
GET https://markdownregistry.com/api/v1/resolve?ref=cruxexperts/localsetup/ls-skill-sandbox-tester
GET https://markdownregistry.com/api/v1/blob/80bc4714ade5a71776cb3802eda5ecf1e0e338a5ca48dcaf28b25db261f623b3

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 cruxexperts/localsetup

AGENTS.md AGENTS.md file
cruxexperts/localsetup · AGENTS.md
git:20261028.0289471 · audit A · 6 stars
ls-accessibility-wcag-review SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-accessibility-wcag-review/SKILL.md · Guide accessibility reviews for UI, documents, and workflows. Use for
v1.0 · audit A · 6 stars
ls-agent-capability-routing SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-agent-capability-routing/SKILL.md · Use when choosing a LocalSetup Agent-* lane for exploration, research, bounded implementation, or review. Consult the…
v1.0 · audit A · 6 stars
ls-agent-email-inbox SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-agent-email-inbox/SKILL.md · Guide agent email inbox workflows with prompt-injection defenses. Use
v1.0 · audit A · 6 stars
ls-agentlens-codebase-navigation SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-agentlens-codebase-navigation/SKILL.md · Navigate and understand codebases using agentlens hierarchical documentation. Use when exploring new projects, finding…
v1.0 · audit A · 6 stars
ls-agentq-ship-ingest SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-agentq-ship-ingest/SKILL.md · Use for Agent Q signed encrypted file-drop or mail ship and ingest, private registry v2 setup, queue status, and…
v1.1 · audit A · 6 stars
ls-alirezarezvani-skills-inventory SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-alirezarezvani-skills-inventory/SKILL.md · Inventory wrapper for the alirezarezvani Claude skills bundle. Use when
v1.0 · audit A · 6 stars
ls-ansible-server-provisioning SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-ansible-server-provisioning/SKILL.md · Infrastructure automation with Ansible. Use for server provisioning, configuration management, application deployment…
v1.1 · audit A · 6 stars
ls-antigravity-awesome-skills SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-antigravity-awesome-skills/SKILL.md · Inventory wrapper for the Antigravity awesome skills bundle. Use when
v1.0 · audit A · 6 stars
ls-arbiter-human-review SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-arbiter-human-review/SKILL.md · Push decisions to Arbiter Zebu for async human review. Use when you need human input on plans, architectural choices…
v1.3 · audit A · 6 stars
ls-architecture-decision-review SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-architecture-decision-review/SKILL.md · Guide architecture analysis and decision records. Use for ADRs, tradeoff
v1.0 · audit A · 6 stars
ls-backblaze-b2-storage SKILL.md skill
cruxexperts/localsetup · ls/skills/ls-backblaze-b2-storage/SKILL.md · Safely plan and execute Backblaze B2 S3-compatible storage operations and B2 native bucket, key, and notification…
v1.1 · audit A · 6 stars

Every file in cruxexperts/localsetup

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