magic

magic is a skill for Claude Code from Alexander-Tyagunov/magician. It costs 46 tokens per session (188 once invoked), scanned A, original, MIT.

A structured research workflow that investigates a question using multiple sources, including web pages, official documentation, and the codebase when relevant.

In plain words
What is it for?
Use it to research, compare, investigate, audit, or evaluate a technical or general topic.
Why use it?
It helps turn a broad research request into organized evidence and a guided result instead of relying on a quick, unsupported answer.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions Codex.

Part of the magician plugin — 26 skills, 4 agents, 10 hooks shipped together

Good fit Use it to research, compare, investigate, audit, or evaluate a technical or general topic.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alexander-tyagunov/magician/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 Alexander-Tyagunov/magician --skill magic
Clone the repo
git clone --depth 1 https://github.com/Alexander-Tyagunov/magician

Made for: Claude Code.

Or install magician, the plugin that ships this one along with the rest of its 26 skills, 4 agents, 10 hooks.

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 magic

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexander-tyagunov/magician/magic/github.svg)](https://agentmods.dev/skills/alexander-tyagunov/magician/magic)
Your own site
<a href="https://agentmods.dev/skills/alexander-tyagunov/magician/magic"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/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 magic

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexander-tyagunov/magician/magic"><img src="https://agentmods.dev/badge/skills/alexander-tyagunov/magician/magic.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 188 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 $0.00046 $0.00188
Opus 5 $0.00023 $0.00094
Sonnet 5 $0.00009 $0.00038
Haiku 4.5 $0.00005 $0.00019

Measured 11d ago against content hash 1becb328cdc4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

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 11d 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.

.codex-plugin/skills/magic/SKILL.md · 11 lines

What it actually says

$magic — Codex Adapter

Read ../../references/codex-adapter.md, then read ../../../skills/magic/SKILL.md and follow the source skill through that Codex adapter. Keep the source skill's gates, safety checks, and completion criteria.

Feature-detect every research capability. Use official documentation tools or primary-source web browsing when available; use Context7 only when installed. For codebase grounding invoke the absolute <plugin-root>/bin/kg path with the Codex MAGICIAN_HOME defined by the shared adapter. Translate consultant/researcher Claude profiles into generic self-contained agent prompts, or research locally when agent tools are unavailable.

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. 11d ago First seen · 11 lines · 46 tokens per session scan A 1becb328cdc4

Subscribe to this mod's changes

magic is a skill published in the GitHub repository Alexander-Tyagunov/magician (14 stars, last pushed 10d ago), licensed MIT. It adds 46 tokens to every session and 188 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 2026-08-30.

Related

Other skills, from other repositories

daily-briefing

Search for today's latest AI news and create/update a comprehensive briefing in Notion, with optional Obsidian vault publishing for graph visualization.

hoangsonww/AI-News-Briefing · 26 tokens

custom-brief

Deep-research a specific topic and produce a comprehensive news-focused briefing with optional Notion/Obsidian/Teams/Slack publishing.

hoangsonww/AI-News-Briefing · 26 tokens

eval-dashboard

Build the interactive offline eval dashboard (eval/dashboard/index.html) — Chart.js trend, axis radar, composite histogram, per-card stacked bars, sortable card table. Use when the user wants to "see eval results", "open dashboard", "visualize quality", or "compare cards".

hoangsonww/AI-News-Briefing · 57 tokens

eval-drift

Detect quality drift in published briefings by comparing the trailing-7d median composite score against the trailing-30d median (MAD-scaled). Use when the user asks to "check drift", "compare last week to baseline", or "is briefing quality slipping".

hoangsonww/AI-News-Briefing · 53 tokens

eval-regression

Re-judge every pinned golden card in eval/golden/ and fail if any composite has dropped more than 0.5 points vs its baseline. Use when the user asks to "run regression", "check golden set", or wants CI-style quality gating after a prompt or judge change.

hoangsonww/AI-News-Briefing · 58 tokens

eval-report

Emit a Markdown weekly digest of briefing quality scores (coverage, composite stats, axis medians, per-day table). Use when the user asks for a "weekly report", "eval summary", or "quality digest" for a specific date range.

hoangsonww/AI-News-Briefing · 49 tokens