quarantine

quarantine is a skill for Claude Code from mehrad-dm/mastermind. It costs 121 tokens per session (1,316 once invoked), scanned C, original, MIT.

A protection setup for keeping secrets and confidential project material out of a Git repository. Git is a system for tracking code changes and sharing them with others.

In plain words
What is it for?
Use it to create a local, ignored storage area, maintain a list of sensitive terms, and check commits and pushes for protected material.
Why use it?
It reduces the risk of accidentally committing private data, credentials, proprietary code, or identifying names.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the mastermind plugin — 23 skills, 4 agents, 1 hook shipped together

Good fit Use it to create a local, ignored storage area, maintain a list of sensitive terms, and check commits and pushes for protected material.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mehrad-dm/mastermind/quarantine
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add mehrad-dm/mastermind --skill quarantine
Clone the repo
git clone --depth 1 https://github.com/mehrad-dm/mastermind

Made for: Claude Code.

Or install mastermind, the plugin that ships this one along with the rest of its 23 skills, 4 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for quarantine

README.md
[![agentmods](https://agentmods.dev/badge/skills/mehrad-dm/mastermind/quarantine.svg)](https://agentmods.dev/skills/mehrad-dm/mastermind/quarantine)
Your own site
<a href="https://agentmods.dev/skills/mehrad-dm/mastermind/quarantine"><img src="https://agentmods.dev/badge/skills/mehrad-dm/mastermind/quarantine.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,316 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.01316
Opus 5 $0.00060 $0.00658
Sonnet 5 $0.00024 $0.00263
Haiku 4.5 $0.00012 $0.00132

Measured 8d ago against content hash 79056af5c83d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade C, and why

quarantine scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

leak-test.md && rm -rf /tmp/mm-throwaway.git`
skills/quarantine/SKILL.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Lab Init: a safe place for project data

The Lab is where MasterMind keeps raw, project-specific material: codebase notes, captured patterns, signature profiles, anything with real names. It is local and gitignored; only the genericized, name-free output ever graduates to a shareable field pack. This exists because raw material sitting in a publishable tree is how confidential data leaks. Make it structural, not a habit.

Golden rule: patterns leave the quarantine, identities never do. Company/product/person/package names stay in lab/. Only the general rule, stripped of every name, goes into a field pack.

What it sets up

lab/
├── .denylist        ← your sensitive terms (gitignored); feeds the guards
├── raw/             ← untouched captures from a codebase
├── analysis/        ← working notes, `signature` profiles
└── MANIFEST.md      ← what's here, what's distilled, what's pending
.githooks/
├── pre-commit       ← blocks staged lab/ paths, denylisted terms, and real secrets
└── pre-push         ← scans every commit being pushed (catches --no-verify + old history)

Steps (idempotent: safe to re-run)

Run from the target repo root. The skill's files live in assets/ next to this SKILL.md.

  1. Create the quarantine (preserving any existing content):

    • mkdir -p lab/raw lab/analysis
    • If lab/.denylist is missing, copy assets/denylist.templatelab/.denylist, then help the user fill it: company, product/app names, internal package scopes (@acme/*), colleague names, private domains/hosts. Never commit this file.
    • If lab/MANIFEST.md is missing, copy assets/MANIFEST.template.mdlab/MANIFEST.md.
  2. Gitignore the quarantine: if lab/ isn't already ignored, append assets/gitignore-snippet.txt to the repo's .gitignore. Verify with git check-ignore lab/.

  3. Install the guards:

    • mkdir -p .githooks && cp assets/pre-commit assets/pre-push .githooks/ && chmod +x .githooks/pre-commit .githooks/pre-push
    • git config core.hooksPath .githooks
    • If the repo already has a core.hooksPath or a hook manager (Husky, etc.), leave theirs in place. Tell the user, and offer to chain the guard into their existing pre-commit instead.

Read the full file on GitHub · 82 lines

Files

What ships with it

6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 82 lines · 0 tokens per session scan C 79056af5c83d

Subscribe to this mod's changes

quarantine is a skill published in the GitHub repository mehrad-dm/mastermind (24 stars, last pushed 8d ago), licensed MIT. It adds 121 tokens to every session and 1,316 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.