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.
npx skills add Hmbown/Wizards-of-the-Ghosts --skill mage-handgit clone --depth 1 https://github.com/Hmbown/Wizards-of-the-GhostsWrote 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.
[](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/mage-hand)<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/mage-hand"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/mage-hand/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/mage-hand"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/mage-hand.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00021 | $0.00905 |
| Opus 5 | $0.00010 | $0.00452 |
| Sonnet 5 | $0.00004 | $0.00181 |
| Haiku 4.5 | $0.00002 | $0.00090 |
Grade A, and why
mage-hand scanned grade A with 0 findings 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 9d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mage Hand
Manipulate files, records, and lightweight system state with precision and minimal blast radius.
Sigil
__
.-' `-.
/ .--. \\
| / /\\ \\ |
| | \\/ | |
\\ `--' /
`-.__.-'
What This Skill Does
Use this skill for small, careful remote manipulations where dexterity matters more than force. In this grimoire, Mage Hand is treated as a hybrid spell with a shipping-now delivery profile. Canonical reference input: Mage Hand (spell).
When To Use
- Trigger this spell when the request asks for surgical, narrow edits to existing objects with explicit boundaries on what NOT to touch. Look for:
- Specific identifiers: file paths, ticket IDs, record keys, field names, audience names
- Constraint language: "only", "but don't touch", "leave X alone", "if X then stop"
- Single-field or single-value changes: "change max_attempts from 3 to 4", "patch reply_to_email"
- Conditional execution with early-exit: "only if each has approval, otherwise stop and return the exception list"
- Audit expectations: "show the diff", "tell me the exact line", "report skipped IDs"
- Small batch operations with per-item validation: "move tickets A, B, C but skip any missing X"
Prerequisites
- No extra runtime dependencies beyond Hermes Agent and the normal toolset for this session.
Procedure
- Restate the target, the success condition, and any no-touch boundaries before taking action.
- Restate boundaries before acting: Name the exact target, the success condition, and what must NOT be touched.
- Scope to the smallest edit surface: Change one field, one line, one ticket state. Do not rewrite surrounding content.
- Apply with diff or state proof: Show what changed. Confirm adjacent values are untouched.
- Report exceptions, not just successes: If any item in a batch fails validation or lacks a prerequisite, stop and return the failure list. Do not silently skip.
- Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.
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.
- 9d ago First seen · 89 lines · 21 tokens per session scan A 2799e6894f75
mage-hand is a skill published in the GitHub repository Hmbown/Wizards-of-the-Ghosts (107 stars, last pushed 5mo ago), licensed CC0-1.0. It adds 21 tokens to every session and 905 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
linter-agent
Use when detecting and fixing code style violations, enforcing project conventions, ensuring consistent formatting.
perf-agent
Use when measure before optimizing, target actual bottlenecks proven by profiling, verify with benchmarks.
n8n-workflows
Use when n8n workflow automation — nodes, triggers, expressions, credentials, webhooks, error handling. Use when working with n8n workflows.
pipedream-workflows
Use when pipedream serverless workflows — triggers, code steps, pre-built actions, data stores, HTTP. Use when working with pipedream workflows.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".