detect-magic

detect-magic is a skill for Claude Code, Codex from Hmbown/Wizards-of-the-Ghosts. It costs 31 tokens per session (774 once invoked), scanned A, original, CC0-1.0.

A structured inspection skill for finding where automation, AI models, agents, and tool connections live in a repository or system. It maps entry points and places where actions or side effects can occur.

In plain words
What is it for?
Use it to scan repositories, inventory model providers and tool registries, inspect shell bridges, webhooks, and schedulers, and perform pre-change checks.
Why use it?
It reduces surprises before you change an unfamiliar codebase or workflow. It helps reveal hidden capabilities, risky edges, and missing visibility.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it to scan repositories, inventory model providers and tool registries, inspect shell bridges, webhooks, and schedulers, and perform pre-change checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hmbown/wizards-of-the-ghosts/detect-magic
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 Hmbown/Wizards-of-the-Ghosts --skill detect-magic
Clone the repo
git clone --depth 1 https://github.com/Hmbown/Wizards-of-the-Ghosts

Made for: Claude Code, Codex.

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 detect-magic

README.md
[![agentmods](https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-magic/github.svg)](https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-magic)
Your own site
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-magic"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-magic/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.

agentmods 80×15 button for detect-magic

Your own site · 80×15
<a href="https://agentmods.dev/skills/hmbown/wizards-of-the-ghosts/detect-magic"><img src="https://agentmods.dev/badge/skills/hmbown/wizards-of-the-ghosts/detect-magic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 774 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00031 $0.00774
Opus 5 $0.00015 $0.00387
Sonnet 5 $0.00006 $0.00155
Haiku 4.5 $0.00003 $0.00077

Measured 9d ago against content hash 7cbfb1f4c040, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

detect-magic 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.

generated/hermes/investigation-and-preparation/detect-magic/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Detect Magic

Surface hidden AI affordances, agents, automations, and tool hooks before acting.

What This Skill Does

Use this skill when you need a fast, structured scan for where the real magic is hiding in a repo, workflow, or system. In this grimoire, Detect Magic is treated as a metaphorical spell with a shipping-now delivery profile. Canonical reference input: Detect Magic (spell).

When To Use

  • You need a preflight scan of a repo or system before making any changes.
  • You need to map where automation, model behavior, and side effects actually live.
  • You want to inventory hidden capability surfaces: model providers, tool registries, shell bridges, webhooks, schedulers.
  • You need to identify surprising affordances, dangerous edges, or missing observability.
  • The request involves AI tooling, agents, starter kits, or model behavior scanning.

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. Inventory obvious entrypoints: README, package manifests, setup docs, scripts/, CI/CD folders, env templates.
  3. Trace outward to hidden capability surfaces: model providers, tool registries, function-calling schemas, MCP config, plugin loaders, shell bridges.
  4. Identify background jobs, cron, schedulers, queues, workers, webhooks, event consumers, notification hooks.
  5. Call out surprising affordances, dangerous edges, missing observability, and fan-out points.
  6. Return a compact map of confirmed mechanisms, inferred mechanisms, and unknowns needing follow-up.
  7. Separate confirmed findings from inference every time — use explicit uncertainty language.
  8. Package the result as the deliverables below, with confidence, assumptions, and unresolved risk called out explicitly.

Deliverables

  • A concise capability inventory mapping all discovered execution surfaces.
  • A risk list covering hidden side effects or untrusted execution paths.
  • A shortlist of follow-up skills or next actions (e.g. $identify, $zone-of-truth, $glyph-of-warding).

Read the full file on GitHub · 74 lines

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. 9d ago First seen · 74 lines · 31 tokens per session scan A 7cbfb1f4c040

Subscribe to this mod's changes

detect-magic 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 31 tokens to every session and 774 once invoked, about $0.0002 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.