Agent skill

Glyph Of Warding

by Hmbown in Hmbown/Wizards-of-the-Ghosts

A skill your agent uses when you need a watchful boundary around files, systems, metrics, queues, or workflows.

CC0-1.0Auto-check passed

Install Glyph Of Warding

skills CLI
$ npx skills add Hmbown/Wizards-of-the-Ghosts --skill glyph-of-warding -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Hmbown/Wizards-of-the-Ghosts glyph-of-warding --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts.git skills-src && mkdir -p .claude/skills && cp -r skills-src/generated/openclaw/glyph-of-warding .claude/skills/glyph-of-warding && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
glyph-of-warding
GitHub stars
110
Token cost
~461 tokens
SKILL.md length
224 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
CC0-1.0

At a glance

A skill your agent uses when you need a watchful boundary around files, systems, metrics, queues, or workflows.

  • Works in 5 steps: Define the boundary, signal, or… → Choose the lightest viable monitoring… → Specify trigger behavior, recipient, and… → …
  • You need a watchful boundary around files
  • SKILL.md covers Overview, When To Use, Workflow and Deliverables, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Glyph Of Warding is an agent skill from Hmbown/Wizards-of-the-Ghosts. Use this skill when you need a watchful boundary around files, systems, metrics, queues, or workflows.

Its SKILL.md is about 460 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Unofficial Hermes Agent skill pack built from fantasy spell and skill names. The licence is CC0-1.0.

When your agent uses it

  • You need a watchful boundary around files

Example prompts

  • “/glyph-of-warding”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Define the boundary, signal, or threshold to watch.
  2. Choose the lightest viable monitoring mechanism.
  3. Specify trigger behavior, recipient, and escalation path.
  4. Return the alarm definition plus test instructions.
  5. If Home Assistant is available, create or update an automation via the HA REST API that watches the specified entity and triggers an alert…

What it can do on your machine

Read from SKILL.md and the folder at commit 1f2e6a0. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Glyph Of Warding loads about 461 tokens when it runs. Until then it costs about 30 tokens; SKILL.md has 224 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~30
When it runs · the whole SKILL.md, loaded when a task matches
~461

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Hmbown/Wizards-of-the-Ghosts at commit 1f2e6a0, republished under its CC0-1.0 licence (© Hmbown). 224 words, ~461 tokens.

Download SKILL.mdSave it as .claude/skills/glyph-of-warding/SKILL.md (or your agent's skills folder).
name
glyph-of-warding
description
Use this skill when you need a watchful boundary around files, systems, metrics, queues, or workflows.
user-invocable
true

Glyph of Warding

Set monitors, watches, or trigger conditions that alert when a boundary is crossed.

Overview

Glyph of Warding is interpreted here as a literal spell with a shipping-now execution model.

Canonical source: Glyph of Warding (spell)

Provider target: OpenClaw

When To Use

  • A repo, service, or process needs a tripwire.
  • You want notification when a threshold, change, or policy breach occurs.
  • A quiet monitor is safer than constant manual checking.
  • You want to set up a Home Assistant automation that alerts you when a sensor crosses a threshold — motion detected, door opened, temperature spike.

Workflow

  1. Define the boundary, signal, or threshold to watch.
  2. Choose the lightest viable monitoring mechanism.
  3. Specify trigger behavior, recipient, and escalation path.
  4. Return the alarm definition plus test instructions.
  5. If Home Assistant is available, create or update an automation via the HA REST API that watches the specified entity and triggers an alert action (notification, light flash, webhook) when conditions are met.

Deliverables

  • A concrete monitor or alert configuration.
  • A test plan for verifying the trigger.
  • A note on false-positive and false-negative risk.

Guardrails

  • Avoid noisy alerts with no clear owner or threshold.
  • Do not silently create monitors that page humans without explicit intent.

Default Invocation

Use $glyph-of-warding to define a watch or alert around this workflow and make the trigger conditions explicit.

© Hmbown, CC0-1.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in generated/openclaw/glyph-of-warding of Hmbown/Wizards-of-the-Ghosts.

Open the folder on GitHubat commit 1f2e6a0

Compare with similar skills

Glyph Of Warding next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Glyph Of Warding compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Glyph Of Warding this skillHmbown/Wizards-of-the-Ghosts110—~461Automated safety check: PassCC0-1.0
Implementing Zero Trust With Hashicorp Boundarymukul975/Anthropic-Cybersecurity-Skills34k—~3.9kAutomated safety check: NotesApache-2.0
Architecture Boundarieslatitude-dev/latitude-llm4.7k—~3.2kAutomated safety check: PassMIT
Isolated Space Boundaryopenchamber/openchamber11k—~2kAutomated safety check: PassMIT
Enterprise Boundaryopenchamber/openchamber11k—~1.7kAutomated safety check: PassMIT
Tool Registry Boundarysimstudioai/sim30k—~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Implementing Zero Trust With Hashicorp Boundary

    mukul975/Anthropic-Cybersecurity-Skills

    Installs and configures HashiCorp Boundary as a default-deny, identity-aware proxy for infrastructure access, including controller/worker setup, Vault-backed credential brokering, session recording…

    34k GitHub stars~3.9k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • Architecture Boundaries

    latitude-dev/latitude-llm

    Layering and boundaries, web vs public API, app layout (clients, routes, logging), ports/adapters, runtime-portable domain/shared/utils code, multi-tenancy, DDD layout, or anti-patterns.

    4.7k GitHub stars~3.2k tokensUpdated 2 days ago
    Backend & APIsAuto-check passed
  • Isolated Space Boundary

    openchamber/openchamber

    A skill your agent uses when changing isolated-space trust boundaries: container hardening, networks and gatekeeper policy, exec and lifecycle, grants and credentials, code transfer and apply…

    11k GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Enterprise Boundary

    openchamber/openchamber

    A skill your agent uses when a change sends conversation content somewhere other than the session's OpenCode provider or this machine, opens a way into this machine (listening address, tunnel…

    11k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Tool Registry Boundary

    simstudioai/sim

    Keep the executable tool registry out of client-reachable module graphs — when to read @/tools/metadata instead of getTool, how to measure whether an import edge pulls the registry, and how to…

    30k GitHub stars~1.9k tokensUpdated today
    Auto-check passed
  • Boundaries Saying No

    LeoYeAI/openclaw-master-skills

    Setting and maintaining personal boundaries across all relationships.

    2.2k GitHub stars~5.2k tokensUpdated 2 mo ago
    Auto-check passed

More from Hmbown/Wizards-of-the-Ghosts

All 11 skills in this repo
  • Animate Objects

    Hmbown/Wizards-of-the-Ghosts

    This spell transforms inert → reactive. An agent skill from Hmbown/Wizards-of-the-Ghosts.

    110 GitHub stars~804 tokensUpdated 6 mo ago
    Auto-check passed
  • Dancing Lights

    Hmbown/Wizards-of-the-Ghosts

    Use this spell for lightweight indicators: status pips, progress markers, heartbeat widgets, and ambient observability that help humans orient quickly.

    110 GitHub stars~528 tokensUpdated 6 mo ago
    Auto-check passed
  • Detect Magic

    Hmbown/Wizards-of-the-Ghosts

    A skill your agent uses when you need a fast, structured scan for where the real magic is hiding in a repo, workflow, or system.

    110 GitHub stars~651 tokensUpdated 6 mo ago
    Auto-check passed
  • Dispel Magic

    Hmbown/Wizards-of-the-Ghosts

    Use this spell when you need to cleanly shut down, disable, or remove active AI tooling — the reverse of Detect Magic.

    110 GitHub stars~430 tokensUpdated 6 mo ago
    Auto-check passed
  • Foresight

    Hmbown/Wizards-of-the-Ghosts

    Foresight produces bounded forecasts with explicit uncertainty to guide decisions.

    110 GitHub stars~779 tokensUpdated 6 mo ago
    Auto-check passed
  • Heat Metal

    Hmbown/Wizards-of-the-Ghosts

    In D&D, Heat Metal makes a metal object painfully hot — the creature holding it must either endure the pain or drop it.

    110 GitHub stars~633 tokensUpdated 6 mo ago
    Auto-check passed

Questions about Glyph Of Warding

What does Glyph Of Warding do?

A skill your agent uses when you need a watchful boundary around files, systems, metrics, queues, or workflows. Glyph Of Warding is an agent skill from Hmbown/Wizards-of-the-Ghosts. Use this skill when you need a watchful boundary around files, systems, metrics, queues, or workflows.

When should I use Glyph Of Warding?

Glyph Of Warding fits situations like: you need a watchful boundary around files.

How do I install Glyph Of Warding in Claude Code?

Run `npx skills add Hmbown/Wizards-of-the-Ghosts --skill glyph-of-warding -a claude-code`. Or copy the skill folder (generated/openclaw/glyph-of-warding in Hmbown/Wizards-of-the-Ghosts) into .claude/skills/glyph-of-warding in your project. Claude Code loads it when a task matches its description.

How do I install Glyph Of Warding in Codex?

Run `npx skills add Hmbown/Wizards-of-the-Ghosts --skill glyph-of-warding -a codex`. Or copy the skill folder (generated/openclaw/glyph-of-warding in Hmbown/Wizards-of-the-Ghosts) into .agents/skills/glyph-of-warding in your project. Codex loads it when a task matches its description.

Can I use Glyph Of Warding in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Hmbown/Wizards-of-the-Ghosts --skill glyph-of-warding -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/glyph-of-warding, .gemini/skills/glyph-of-warding, .github/skills/glyph-of-warding and .opencode/skills/glyph-of-warding in your project.

What does Glyph Of Warding need to run?

SKILL.md names no scripts, command-line tools or credentials: Glyph Of Warding is instructions for the agent only.

Does Glyph Of Warding access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Glyph Of Warding safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Glyph Of Warding use?

Glyph Of Warding is published under the CC0-1.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Glyph Of Warding use?

About 461 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Glyph Of Warding?

Skills that share tags, products or a category with Glyph Of Warding: Implementing Zero Trust With Hashicorp Boundary (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Architecture Boundaries (latitude-dev/latitude-llm, 4.7k stars), Isolated Space Boundary (openchamber/openchamber, 11k stars) and Enterprise Boundary (openchamber/openchamber, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Glyph Of Warding?

Hmbown (a GitHub user) maintains it in Hmbown/Wizards-of-the-Ghosts, which has 110 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on April 5, 2026.

Source: Hmbown/Wizards-of-the-Ghosts on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.