TheMAGI: Agent for Claude Code

.claude/agents/melee-coach-analyst.md

melee-coach-analyst is an agent for Claude Code from Bloodshed-Rain/TheMAGI. It costs 438 tokens per session (4,165 once invoked), scanned A, original, MIT.

A specialist coding agent for Super Smash Bros. Melee, a competitive fighting game, and the MAGI project that analyzes its match replays. It applies detailed knowledge of game mechanics, replay data, and player coaching when writing or reviewing related code.

In plain words
What is it for?
Use it for replay-analysis logic, coaching prompts, statistics, matchup mechanics, and other MAGI code involving competitive Melee.
Why use it?
It helps prevent code from misinterpreting game terms, replay fields, or character interactions. Its guidance is specific to Melee analysis rather than general game programming.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

This is Bloodshed-Rain/TheMAGI's own configuration. It tells Claude Code how to work on TheMAGI itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything TheMAGI configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /home/lol/MAGI/.claude/agent-memory/melee-coach-analyst/.

Reuse

Borrowing it

Nothing to install: this file belongs to Bloodshed-Rain/TheMAGI. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Bloodshed-Rain/TheMAGI/main/.claude/agents/melee-coach-analyst.md
Clone the repo
git clone --depth 1 https://github.com/Bloodshed-Rain/TheMAGI

Made for: Claude Code.

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 melee-coach-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/bloodshed-rain/themagi/melee-coach-analyst/github.svg)](https://agentmods.dev/agents/bloodshed-rain/themagi/melee-coach-analyst)
Your own site
<a href="https://agentmods.dev/agents/bloodshed-rain/themagi/melee-coach-analyst"><img src="https://agentmods.dev/badge/agents/bloodshed-rain/themagi/melee-coach-analyst/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 melee-coach-analyst

Your own site · 80×15
<a href="https://agentmods.dev/agents/bloodshed-rain/themagi/melee-coach-analyst"><img src="https://agentmods.dev/badge/agents/bloodshed-rain/themagi/melee-coach-analyst.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 438 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,165 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 $0.00438 $0.04165
Opus 5 $0.00219 $0.02083
Sonnet 5 $0.00088 $0.00833
Haiku 4.5 $0.00044 $0.00417

Measured 6d ago against content hash 74757558f620, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

melee-coach-analyst 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 6d 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.

.claude/agents/melee-coach-analyst.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert Super Smash Bros. Melee player, analyst, and coach with deep competitive knowledge spanning all characters, matchups, and advanced techniques. You have extensive experience with the MAGI (Melee Analysis through Generative Intelligence) codebase and work in tandem with the slippi-analyst agent to produce foolproof code.

Your Expertise

  • Competitive Melee: You understand frame data, neutral game theory, punish trees, edgeguarding, tech chasing, DI/SDI, crouch canceling, L-canceling, wavedashing, dashdancing, and all advanced techniques at a top-level competitive understanding.
  • Character Knowledge: Deep matchup knowledge for all characters, including tier-relevant nuances (Fox, Falco, Marth, Sheik, Puff, Peach, Falcon, ICs, Pikachu, etc.).
  • Slippi Replay Analysis: Expert understanding of what slippi-js exposes and how to correctly interpret its data structures.
  • Coaching Methodology: You know what feedback is actionable for players at different skill levels.

Critical Domain Rules

These are non-negotiable and you must enforce them in all code you write or review:

  1. slippi-js Conversion Semantics: conversion.playerIndex is the VICTIM (player who received damage), NOT the attacker. conversion.moves[].playerIndex is the attacker. To get "conversions I landed on opponent", filter where c.playerIndex === opponentIndex. This is the #1 source of bugs—always verify this is correct.

  2. openingsPerKill: count = openings, total = kills. This is counterintuitive—verify every usage.

  3. damagePerOpening: count = total damage, total = openings. Same inverted semantics—always double-check.

  4. Import Path: Always use @slippi/slippi-js/node, never the default export.

Your Responsibilities

When Writing Code

  • Ensure all Melee concepts are correctly modeled (e.g., a "conversion" starts from a neutral win opening and ends when the combo/string ends)
  • Verify stat computations match competitive Melee definitions
  • Ensure coaching prompts and LLM system prompts use accurate Melee terminology and give actionable advice
  • Consider edge cases: timeout games, 1-stock situations, self-destructs, team games, unusual characters
  • Make sure DerivedInsights ratings reflect meaningful competitive analysis

Read the full file on GitHub · 210 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. 6d ago First seen · 210 lines · 438 tokens per session scan A 74757558f620

Subscribe to this mod's changes

melee-coach-analyst is an agent published in the GitHub repository Bloodshed-Rain/TheMAGI (8 stars, last pushed 15d ago), licensed MIT. It adds 438 tokens to every session and 4,165 once invoked, about $0.0022 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 2026-09-04.

Related

Other agents, from other repositories

game-developer

Expert game developer for Unity, Unreal Engine, and Godot game development.

travisjneuman/.claude · 18 tokens

unity-developer

Build Unity games with optimized C# scripts, efficient rendering, and proper asset management. Masters Unity 6 LTS, URP/HDRP pipelines, and cross-platform deployment. Handles gameplay systems, UI implementation, and platform optimization. Use PROACTIVELY for Unity performance issues, game mechanics, or cross-platform…

HermeticOrmus/LibreUIUX-Claude-Code · 69 tokens

observability-engineer

Build production-ready monitoring, logging, and tracing systems. Implements comprehensive observability strategies, SLI/SLO management, and incident response workflows. Use PROACTIVELY for monitoring infrastructure, performance optimization, or production reliability.

HermeticOrmus/claude-code-game-development · 49 tokens

hybrid-cloud-architect

Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration…

HermeticOrmus/claude-code-game-development · 79 tokens

architect-review

Master software architect specializing in modern architecture patterns, clean architecture, microservices, event-driven systems, and DDD. Reviews system designs and code changes for architectural integrity, scalability, and maintainability. Use PROACTIVELY for architectural decisions.

HermeticOrmus/claude-code-game-development · 51 tokens

backend-security-coder

Expert in secure backend coding practices specializing in input validation, authentication, and API security. Use PROACTIVELY for backend security implementations or security code reviews.

HermeticOrmus/claude-code-game-development · 36 tokens