claude md agents

Lolner95/AIGX

Agent

This repository uses AIGX (AI Genome Exchange) — its AI-agent rules live in a .aigx/ directory with a per-file boundary index. You don't need to guess the conventions; they are in the genome. Read this section before editing.

solanabr/solana-ai-kit

Agent Claude Code

Senior Solana game architect for game system design, Unity/C# architecture, on-chain game state, player progression, NFT integration, and PlaySolana ecosystem. Use for high-level game design decisions, architecture reviews, and planning complex game systems. Use when: Designing new Solana games from scratch, planning…

solanabr/solana-ai-kit

Agent Claude Code

Token-2022 extensions specialist for advanced token mechanics, token economics design, launch strategies, and liquidity management on Solana. Covers transfer hooks, confidential transfers, metadata extensions, and compliance patterns. Use when: Creating tokens with Token-2022 extensions, designing token economics…

solanabr/solana-ai-kit

Agent Claude Code

Unity and C# specialist for Solana game development. Builds game systems using Solana.Unity-SDK, handles wallet integration, NFT display, transaction signing, and real-time gameplay. Expert in Unity patterns, async C#, and PlaySolana SDK. Use when: Implementing Unity game code, wallet connection, NFT loading…

MCKRUZ/claude-code-mastery

Agent

Senior code reviewer. Use after code changes for quality review.

MCKRUZ/claude-code-mastery

Agent

Technical documentation writer. Creates and updates docs.

MCKRUZ/claude-code-mastery

Agent

Security-focused code auditor. Auto-spawned for auth, payment, and identity code.

curtischoutw/claude-institution

Agent

A review agent that examines code or designs for security risks and ways they may fail. It checks inputs, permissions, secrets, concurrent operations, partial failures, and injection attacks, where untrusted data changes a command or query.

curtischoutw/claude-institution

Agent

A review agent that looks for unnecessary complexity in code or software designs. It proposes a concrete simpler replacement when it finds overengineering.

curtischoutw/claude-institution

Agent

A review agent that tries to disprove a claim, conclusion, or code change. It checks assumptions, uses repository tools and commands, and reports whether the claim survived its scrutiny.

rakib-nyc/skillassay

Agent

Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.

rakib-nyc/skillassay

Agent

Compare two outputs WITHOUT knowing which skill produced them.

rakib-nyc/skillassay

Agent

Evaluate expectations against an execution transcript and outputs.

marky291/claude-drift

Agent

Maps a project's "Claude flow" — discovers every Claude artifact (CLAUDE.md, skills, agents, commands, settings, hooks, .mcp.json), reads enough of the codebase to understand the project's actual reality, and ranks each artifact by how likely it has drifted, so the deep audit can be prioritized. The reasoning-based…

marky291/claude-drift

Agent

Audits a single Claude artifact (CLAUDE.md, skill, command, agent, or settings/hooks/.mcp.json) against the project's actual code and reasons about where it has drifted — both broken references AND context drift (stale architecture/workflow/convention descriptions). Returns evidenced findings with concrete fixes. The…