Hold Person logo

Hold Person

Community
Hmbown
hold-person

Hold Person = hard freeze. Nothing moves. In-flight operations stop. Requires authority. Used for security incidents, fraud, compliance holds, misbehaving systems. Sleep = graceful suspension. State is preserved and queued. Operations resume automatically. Used for maintenance windows, temporary pauses, planned downtime.

Overview

PublisherHmbown
RepositoryWizards-of-the-Ghosts
Skill namehold-person
Stars
106
Forks
10
Bundled files
Instructions only
LicenseCC0-1.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Hmbown on GitHub. Read the source before you install it.

Installation

Install the Hold Person AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
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/influence-and-behavior/hold-person .claude/skills/hold-person
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hold Person in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hold Person on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hold Person is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Hold Person

Freeze a process, account, or workflow in place with administrative authority.

What This Skill Does

Hold Person = hard freeze. Nothing moves. In-flight operations stop. Requires authority. Used for security incidents, fraud, compliance holds, misbehaving systems. Sleep = graceful suspension. State is preserved and queued. Operations resume automatically. Used for maintenance windows, temporary pauses, planned downtime. In this grimoire, Hold Person is treated as a hybrid spell with a prototype delivery profile. Canonical reference input: Hold Person (spell).

When To Use

  • Activate Hold Person when the user needs to hard-freeze an account, process, workflow, or system pending investigation, review, or resolution, with these conditions:
  • Something must stop immediately and completely — no partial operation
  • The frozen state must be preserved intact (not deleted, not terminated)
  • The freeze is temporary and reversible — release conditions matter
  • Administrative authority is required — someone must be authorized to impose and lift the hold
  • The freeze is targeted — specific accounts, pipelines, endpoints, or jobs, not mass org-wide changes

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. Verify authority: Who can impose this hold? Is the requester authorized? Document the authorization chain. If authority is unclear, flag it before proceeding.
  3. Define freeze scope: What exactly stops? What continues? What happens to in-flight operations? Be specific: which accounts, which pipelines, which endpoints. Preserve all state — nothing is deleted.
  4. Set release conditions: Who can unfreeze? Under what circumstances? What audit trail is required? What happens if the hold exceeds a time threshold (e.g., auto-escalate after 48 hours)? A hold without release criteria is a permanent lockout — that's a different and more dangerous action.
  5. Deliver the hold plan: Provide the hold specification (what is frozen, by whose authority, under what conditions) and release procedures (how to unfreeze, who authorizes it, what audit trail is required).
  6. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • Hold specification: frozen scope, authority chain, conditions
  • Release procedures: unfreeze steps, authorization requirements, audit trail
  • Guardrails: never impose without authority, always define release conditions, preserve state

Pitfalls / Guardrails

  • Call out the glue, permissions, or missing infrastructure before you imply this is fully operational.
  • Do NOT use Hold Person for:
  • Do not use for: Graceful pause with queuing (use Sleep): "pause during maintenance", "queue and deliver later", "no state lost"
  • Do not use for: OS-level process control (use Stun): "SIGSTOP/SIGCONT", "stun for diagnostic", "quick memory check"
  • Do not use for: Mass/organization-wide freezes: "all 500 users", "entire role", "every account"
  • Do not use for: Permanent termination or deletion: "revoke permanently", "delete access", "shut down for good"
  • Do not use for: Simple scheduling delays: "run two hours later", "shift the cron", "delay until upstream is ready"
  • Do not use for: Stop restarting without preservation: "just stop the restart loop", "keep it down until I say"

Verification

  • Check that the result includes every deliverable promised above.
  • Check that confirmed facts, assumptions, and inferences are visibly separated.
  • Check which parts are concrete actions versus framing, so the user can tell what is real now.
  • Check that any missing glue code, permissions, or future work is labeled before the skill is treated as ready.

Example Invocation

text
/hold-person design an administrative hold for this [account/process/workflow] with proper authorization and release conditions

Frequently asked questions

What does the Hold Person AI skill do?

Hold Person = hard freeze. Nothing moves. In-flight operations stop. Requires authority. Used for security incidents, fraud, compliance holds, misbehaving systems. Sleep = graceful suspension. State is preserved and queued. Operations resume automatically. Used for maintenance windows, temporary pauses, planned downtime.

Why use Hold Person on TypingMind?

Because you install it once and use it with any model. Hold Person is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hold Person in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Hmbown/Wizards-of-the-Ghosts/tree/main/generated/hermes/influence-and-behavior/hold-person. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hold Person?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hold Person?

As many as you like. As long as a model supports skills, you can use Hold Person with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hold Person AI skill free?

Yes. It is published on GitHub by Hmbown under the CC0-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇