Mind Blank

Use this spell when sensitive information must not cross boundaries — between agent sessions, between tasks, between tenants, or between domains with different trust levels.

113 stars 11 forksDevOps & Cloud

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add Hmbown/Wizards-of-the-Ghosts --skill mind-blank
Manual install
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git /tmp/Wizards-of-the-Ghosts
mkdir -p ~/.claude/skills
cp -r /tmp/Wizards-of-the-Ghosts/generated/hermes/monitoring-and-protection/mind-blank ~/.claude/skills/mind-blank

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Mind Blank
Isolate context to prevent information leakage between sessions, tasks, or domains.
## What This Skill Does
Use this spell when sensitive information must not cross boundaries — between agent sessions, between tasks, between tenants, or between domains with different trust levels.
In this grimoire, Mind Blank is treated as a literal spell with a prototype delivery profile.
Canonical reference input: Mind Blank (spell).
## When To Use

- You are switching between tasks with different confidentiality levels and need a clean context boundary.
- PII, credentials, or sensitive business logic from one workflow must not leak into another.
- You need to ensure an agent operating in one domain cannot be interrogated about another.

## Prerequisites

- No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.

## Procedure

1. Restate the target, the success condition, and any no-touch boundaries before taking action.
2. Identify the information boundary: what must be compartmented and from whom.
3. Establish the isolation mechanism: session reset, context stripping, PII redaction, or scoped tool access.
4. Verify the boundary holds by confirming the protected information is inaccessible from the other side.
5. Document what was isolated, what remains accessible, and how to lift the boundary when appropriate.
Read the full skill on GitHub

Details

Skill name
mind-blank
Path
generated/hermes/monitoring-and-protection/mind-blank/SKILL.md
License
CC0-1.0
Repo updated
5 April 2026

FAQ

What does the Mind Blank skill do?

Use this spell when sensitive information must not cross boundaries — between agent sessions, between tasks, between tenants, or between domains with different trust levels.

How do I install the Mind Blank skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add Hmbown/Wizards-of-the-Ghosts --skill mind-blank. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Mind Blank popular?

It lives in Hmbown/Wizards-of-the-Ghosts, which has 113 GitHub stars and 11 forks.

Related skills

Acrobatics

113

Hmbown/Wizards-of-the-Ghosts

Use this skill when the work is a choreography problem: brittle sequencing, async handoffs, or constrained flows that must stay upright end to end. It shines on API dances, dependency ordering, and recovery logic where grace matters more than brute force.

Productivity & Notes11

Animal Friendship

113

Hmbown/Wizards-of-the-Ghosts

Animal Friendship is the first-contact spell for unfamiliar APIs, vendors, and services. It treats integration work as relationship-building: learn the temperament, respect the boundaries, and earn a stable exchange before asking for anything ambitious. The goal is not domination but trustable cooperation.

Productivity & Notes11

Animal Handling

113

Hmbown/Wizards-of-the-Ghosts

Use this skill when the system is not fully broken but behaves like a skittish animal: flaky CI, fragile legacy services, or moody dependencies. It focuses on coaxing, pacing, and stable handling rather than heroic rewrites.

Other11

Mislead

113

Hmbown/Wizards-of-the-Ghosts

Mislead is defensive deception: honeypots, canary tokens, decoy endpoints, fake datasets, and other convincing false presences that reveal who is snooping. The goal is not to trick legitimate users for sport. The goal is to create an instrumented fake that attracts unauthorized curiosity while the real system remains elsewhere. This makes the spell powerful and ethically sharp-edged. It needs explicit boundaries, isolation, and a clear monitoring objective before it should be deployed.

DevOps & Cloud11

Light

113

Hmbown/Wizards-of-the-Ghosts

Use this cantrip when a system, process, or codebase has blind spots that need illumination - not detection of hidden things, but creation of visibility where none exists.

DevOps & Cloud11

Mivas Run

49

bluejay-ai-dev/mivas-bench

Walks a consumer through running MIVAS Bench end to end, interview first: what model they are benchmarking, where the model is served (vendor API, or their own endpoint on an inference provider), and where the Docker container runs (local, any Kubernetes, or any container hosting platform). Then a gated ladder: preflight, deploy, three Bluejay smoke calls, harness + benchmark integrity, full industry run. Use when someone says /mivas-run, "run MIVAS myself", "set up mivas-bench", "deploy a harness for MIVAS", "smoke my harness on Bluejay", "benchmark my voice model on healthcare/legal/customer

DevOps & Cloud

Browse the most popular Claude skills, all devops & cloud skills, or write your own with the skills generator.