Borrowing it
Nothing to install: this file belongs to gustavoeenriquez/MakerAi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gustavoeenriquez/MakerAi/master/CLAUDE.mdgit clone --depth 1 https://github.com/gustavoeenriquez/MakerAiWrote 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/instructions/gustavoeenriquez/makerai/claude-md)<a href="https://agentmods.dev/instructions/gustavoeenriquez/makerai/claude-md"><img src="https://agentmods.dev/badge/instructions/gustavoeenriquez/makerai/claude-md/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/instructions/gustavoeenriquez/makerai/claude-md"><img src="https://agentmods.dev/badge/instructions/gustavoeenriquez/makerai/claude-md.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 | $0.07887 | $0.07887 |
| Opus 5.5 | $0.03155 | $0.03155 |
| Sonnet 5.5 | $0.01577 | $0.01577 |
| Haiku 4.5 | $0.00789 | $0.00789 |
Grade A, and why
MakerAi CLAUDE.md scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
# Test via curl How it starts
The opening of the file, as written. The whole thing — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
MakerAI is an AI orchestration framework for Delphi developers (v3.9). It provides components for integrating multiple LLM providers (OpenAI, Claude, Gemini, Ollama, Groq, DeepSeek, Kimi, GLM/Z.ai, Qwen/Alibaba, Grok, Mistral, Cohere, LM Studio, GenericLLM), RAG systems (vector and graph-based), MCP servers/clients, A2A agent interoperability, autonomous agents, observability, guardrails and native ChatTools into Delphi applications. Supports Delphi 10.4 Sydney through 13 Florence (limited: 10.4 Sydney; full support: 11 Alexandria+).
v3.9 highlights (oct 2026): OpenAI GPT-Live (TAiOpenAiLiveChat, voz full-duplex que escucha mientras habla y delega el razonamiento a un modelo Responses o a cualquier TAiChatConnection; demo 092 con RAG por MCP); Jev con modelos locales de Ollama (/v1/systemone: nimble, Clef con imágenes; Url en los adaptadores, precio 0 fuera de TypeSafe); 3 fugas de memoria corregidas (servidor MCP en cada tools/list, cliente MCP en Initialize, TAiRealtimeFactory); TAiMCPServer.BindAddress; íconos de paleta para los 108 componentes; demo 037 sobre PostgreSQL. Cambios de comportamiento (3): audio de OpenAI por defecto gpt-transcribe/gpt-4o-mini-tts (whisper-1 y tts-1 se apagan), IAiMCPTool.GetInputSchema devuelve un objeto del que llama (afecta tools MCP propias que devolvían un campo guardado) y el driver Responses ahora respeta Max_Tokens. Deprecados de OpenAI marcados con fecha de apagado. MAKERAI_API_LEVEL = 39.
v3.8 highlights (sep 2026): Jev (TypeSafe AI) para decisiones calibradas sin pasar por un LLM (enrutar agentes, SmartDispatch, guardrails de tools y de entrada, evals, rerank RAG con filtro de inyecciones, etiquetado masivo, enrutador de modelos, medición de consumo); driver Qwen (Alibaba) completo; skills en formato SKILL.md (TAiSkills con use_skill bajo demanda para cualquier chat, TAiSkill/TLLMNode arreglados, parser y cliente PPM comunes); Computer Use en Linux. Cambios de comportamiento (6): TLS verificado en POSIX (rompe endpoints autofirmados sin InsecureSkipVerify), IAiMemoryStorage exige el namespace (issue #127, rompe storages propios), Gemini ya ejecuta funciones de usuario, Model vacío usa los parámetros del modelo por defecto TLLMNode.DriverName vacío por defecto y tool_choice forzado solo en la primera llamada (antes loop sin fin). Defaults revisados: Gemini gemini-3.8-flash, OpenAI gpt-6-sol, Claude sigue en claude-haiku-4-5. MAKERAI_BREAKING_CHANGE = True.
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.
- 1mo ago Changed · +4 lines · +384 tokens per session fec38773d7c2
- 1mo ago Changed · +4 lines · +367 tokens per session 4d423fe14595
- 1mo ago Changed · +2 lines · +156 tokens per session e8dd369206c1
- 2mo ago First seen · 454 lines · 6,980 tokens per session scan A 8039ed84beb5
MakerAi CLAUDE.md is an instructions file published in the GitHub repository gustavoeenriquez/MakerAi (217 stars, last pushed yesterday), licensed MIT. It adds 7,887 tokens to every session, about $0.0315 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
MakerAi CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| MakerAi CLAUDE.mdgustavoeenriquez/MakerAi | Instructions file | 217 | yesterday | MIT | A | 7,887 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |