Arnie016/codex-prompt-templates / skills/sandbox-source-intake
sandbox-source-intake
VerifiedSafely clone, inspect, and triage fresh GitHub repos without overusing disk or running risky code. Use when the user asks to clone many repos, evaluate bleeding-edge tools, install MCP servers, run unknown scripts, or harvest patterns from public repos.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 1.5 KB |
SKILL.md
View on GitHub---
name: sandbox-source-intake
description: >
Safely clone, inspect, and triage fresh GitHub repos without overusing disk or
running risky code. Use when the user asks to clone many repos, evaluate
bleeding-edge tools, install MCP servers, run unknown scripts, or harvest
patterns from public repos.
---
# Sandbox Source Intake
Use this before trusting a fresh repo.
## Clone Policy
- Use shallow clones: `git clone --depth 1 <url> sources/<name>`.
- Prefer a small curated set over bulk cloning.
- Check `du -sh sources` after each batch.
- Skip or sparse-clone very large repos unless needed.
## Inspection Order
1. README and license.
2. Manifests: `package.json`, `pyproject.toml`, `Cargo.toml`, `go.mod`.
3. Install scripts, Dockerfiles, GitHub Actions.
4. Tool/MCP configs and permissions.
5. Source entry points.
## Red Flags
- raw executable zip/binary download as primary install
- curl-piped shell
- postinstall scripts that fetch remote code
- account/session control without a narrow use case
- broad filesystem or shell tools exposed through MCP
- unclear license
## Output
```md
# Source Intake Report
Repo:
Local path:
Disk size:
License:
Runtime:
Install risk:
Useful patterns:
Do not run:
Next action:
```
Then use `$repo-intelligence-brief` for safe repos.
## Validation
- Clone depth, disk size, license, runtime, and install risk are recorded.
- No untrusted install scripts, binaries, package installs, or servers were run.
- Risky repos are marked inspiration-only until reviewed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |