shell-execution-sandbox SKILL.md skillA
shell-execution-sandbox from tylerjrbuell/reactive-agents-ts is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add tylerjrbuell/reactive-agents-ts/shell-execution-sandbox@v2.0Pins v2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- tylerjrbuell/reactive-agents-ts
- Path
apps/docs/skills/shell-execution-sandbox/SKILL.md- Versions recorded
- 4
- Latest version
- v2.0, committed Nov 6, 2026
- First version recorded
- Apr 10, 2026
- Size
- 6,346 bytes
- Repository stars
- 31
- License
- MIT
Enable and configure the sandboxed shell execution tool with command allowlists, Docker isolation, and audit logging for agents that run terminal commands.
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
# Shell Execution Sandbox
> **Disclaimer — your machine, your risk.** `shell-execute` runs real processes on the host (or in an optional Docker sandbox you configure). Allowlists and blocklists reduce accidents but are not a guarantee. Only enable for trusted codebases and accounts; review allowed command names and working-directory rules before production use. Cortex exposes this as an **explicit opt-in** in the Lab builder with the same warning.
## Agent objective
Produce a builder with shell execution enabled, the correct allowlist for the task, and appropriate safety config — without exposing destructive commands.
## When to load this skill
- Agent needs to run terminal commands (git, file operations, build tools)
- Agent generates and executes code (Node, Bun, Python)
- Task requires reading directory structure, running tests, or processing files
- CI/CD or automation agent workflows
## Implementation baseline
```ts
const agent = await ReactiveAgents.create()
.withProvider("anthropic")
.withReasoning({ defaultStrategy: "plan-execute-reflect", maxIterations: 15 })
.withTools({
allowedTools: ["shell-execute", "file-read", "checkpoint"],
…Read the whole file at its exact version.
How to install
mdr add tylerjrbuell/reactive-agents-ts/shell-execution-sandbox@sha256:ab73dc71a5573265The line at the top of this page pins the label v2.0, 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.
[](https://markdownregistry.com/a/art_35zvgs5dfahqupws)
5 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Apr 10, 2026 and Nov 6, 2026, about one every 70 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v2.0 latest | 2026-11-06 | 15d7b26 | 6,346 B | A | view · diff |
| v2.0 | 2026-07-21 | 848f5ae | 5,203 B | A | view · diff |
| v2.0 | 2026-04-10 | a75b596 | 5,229 B | A | view · diff |
| v2.0 | 2026-04-10 | edbdd5f | 4,715 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6346 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
tylerjrbuell/reactive-agents-ts · 31 stars · license MIT · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_35zvgs5dfahqupws GET https://markdownregistry.com/api/v1/resolve?ref=tylerjrbuell/reactive-agents-ts/shell-execution-sandbox GET https://markdownregistry.com/api/v1/blob/ab73dc71a55732656d17343908ccc8ca537caad997381cadf4310e6db7b7d87a
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.