isolate-cli SKILL.md skillA

isolate-cli from sergeyklay/.agents is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add sergeyklay/.agents/isolate-cli@v1.1

Pins v1.1 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
sergeyklay/.agents
Path
.agents/skills/isolate-cli/SKILL.md
Versions recorded
5
Latest version
v1.1, committed Sep 13, 2026
First version recorded
Sep 3, 2026
Size
18,431 bytes
Repository stars
6
License
Apache-2.0

Run a third-party CLI as a subprocess without leaking into it or leaving state on the host, and prove both. Use when a script or skill shells out to an external tool, when a run must leave no trace outside the repository, when private input (a diff, a prompt, a credential) must not reach the tool's session log, when a policy or deny-list handed to the tool must actually be in force, when a claim about the tool's own behaviour (which paths it searches, which config file wins) must be settled…

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

# Confine an External CLI

A CLI invoked as a subprocess is not a function call. It reads the operator's global configuration, writes per-run state under the home directory keyed to the directory it ran in, and treats a config file it cannot compile as advice rather than as an instruction. None of those three shows up in an exit code: the private content piped in lands in a plaintext log outside the repository, the host accumulates state nobody audits, and the confinement believed to be in force is absent.

This skill is the mechanics of running such a tool and being able to say afterwards what it read, what it wrote, and what it left behind. Whether the run's *result* is evidence is a separate question and belongs to `prove-checks`.

## Trigger

- A script or skill invokes a third-party CLI as a subprocess: an agent CLI, a linter with a cache, a package manager, a formatter, anything with a state store outside the working directory.
- A second tool or provider branch is added to a script that already does this.
- The tool is handed a policy, deny-list, allow-list or sandbox configuration.
- The content piped in is private: an unmerged diff, a prompt, a credential, customer data.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add sergeyklay/.agents/isolate-cli@sha256:d8cea9128c910c32

The line at the top of this page pins the label v1.1, 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_44fqpocebi7pg5ql.svg)](https://markdownregistry.com/a/art_44fqpocebi7pg5ql)

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

Versions

The registry has recorded 5 versions of this file, between Sep 3, 2026 and Sep 13, 2026, about one every 3 days.

versioncommittedcommitsizeaudit
v1.1 latest2026-09-13 16a0e75 18,431 BA view · diff
v1.12026-09-08 baf794f 17,693 BA view · diff
v1.12026-09-08 7141f0b 18,388 BA view · diff
v1.02026-09-06 7dbaedb 17,712 BA view · diff
v1.02026-09-03 c449755 16,231 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 (18431 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

sergeyklay/.agents · 6 stars · license Apache-2.0 · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_44fqpocebi7pg5ql
GET https://markdownregistry.com/api/v1/resolve?ref=sergeyklay/.agents/isolate-cli
GET https://markdownregistry.com/api/v1/blob/d8cea9128c910c323d1c9c3a1f7c507fd937fbba167eb1c746034fe3e837901b

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 sergeyklay/.agents

AGENTS.md@.agents AGENTS.md file
sergeyklay/.agents · .agents/AGENTS.md
git:20261013.ff72bf0 · audit A · 6 stars
audit-agent SKILL.md skill
sergeyklay/.agents · .agents/skills/audit-agent/SKILL.md · Audits AI-agent runs and session snapshots for token usage, cache traffic, cost, duration, turns, tool calls, failures…
v2.2 · audit A · 6 stars
babysit-pr SKILL.md skill
sergeyklay/.agents · .agents/skills/babysit-pr/SKILL.md · Resolve reviewer comments on a pull request or pasted feedback using a six-step evidence-grounded protocol. Use when…
v2.1 · audit A · 6 stars
check-dependabot SKILL.md skill
sergeyklay/.agents · .agents/skills/check-dependabot/SKILL.md · Validate a Dependabot configuration against the published JSON Schema and audit its groups against the repository's…
v1.0 · audit A · 6 stars
compare-it SKILL.md skill
sergeyklay/.agents · .agents/skills/compare-it/SKILL.md · Produce structured architectural comparison documents that evaluate two tools, technologies, or solutions against…
v1.1 · audit A · 6 stars
context-files SKILL.md skill
sergeyklay/.agents · .agents/skills/context-files/SKILL.md · Create or validate project context files (AGENTS.md, CLAUDE.md, GEMINI.md). Use when bootstrapping a new project…
v1.1 · audit A · 6 stars
create-pr SKILL.md skill
sergeyklay/.agents · .agents/skills/create-pr/SKILL.md · Use when asked to create a pull request, open a PR, or submit changes for review. Handles branch verification, change…
v1.4 · audit A · 6 stars
delegate-work SKILL.md skill
sergeyklay/.agents · .agents/skills/delegate-work/SKILL.md · Brief a background agent, confirm the brief arrived, and verify its report before acting on it. Use when writing the…
v1.0 · audit A · 6 stars
explain-it SKILL.md skill
sergeyklay/.agents · .agents/skills/explain-it/SKILL.md · Explain technical concepts, mechanisms, and systems to a technically fluent reader who is unfamiliar with the specific…
v2.1 · audit A · 6 stars
git-commit SKILL.md skill
sergeyklay/.agents · .agents/skills/git-commit/SKILL.md · Use when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits…
v1.1 · audit A · 6 stars
improve-self SKILL.md skill
sergeyklay/.agents · .agents/skills/improve-self/SKILL.md · Detect when a missing Agent Skill would have made the current task faster or more reliable, then scaffold a candidate…
v1.1 · audit A · 6 stars
jira-syntax SKILL.md skill
sergeyklay/.agents · .agents/skills/jira-syntax/SKILL.md · Use when writing Jira issue descriptions, comments, or work logs. Also use when converting Markdown to Jira wiki…
v1.1 · audit A · 6 stars

Every file in sergeyklay/.agents

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