agentleFS
memi-designmemi-design/design-skills/skills/approval-sandbox-policies/SKILL.md

approval-sandbox-policies

Skill7 starsChanged 4 months agoMITView on GitHub

Define approval, sandbox, filesystem, and command policy for local autonomous agents.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this Note when a Memoire or Studio run needs agent approvals, sandbox mode, command allowlist, secure agent run.

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Approval Sandbox Policies

Define approval, sandbox, filesystem, and command policy for local autonomous agents.

When to Use

Use this Note when a Memoire or Studio run needs agent approvals, sandbox mode, command allowlist, secure agent run.

Workflow

  1. Classify every run as read-only, workspace-write, or full-access before launching an agent.
  2. Bind filesystem writes to the project root unless the task explicitly requires external paths.
  3. Allowlist narrow commands by absolute path or stable prefix, not broad shell access.
  4. Require approval for network, package install, credential, desktop automation, and deletion steps.
  5. Store the final policy next to the session transcript so future agents inherit the boundary.

Sources

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.