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.
npx agentmods add instructions/qubiit0/lmagent/agents-mdgit clone --depth 1 https://github.com/QuBiit0/lmagentWrote 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/qubiit0/lmagent/agents-md)<a href="https://agentmods.dev/instructions/qubiit0/lmagent/agents-md"><img src="https://agentmods.dev/badge/instructions/qubiit0/lmagent/agents-md.svg" alt="Measured on agentmods" 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 | $0.07555 | $0.07555 |
| Opus 5 | $0.03778 | $0.03778 |
| Sonnet 5 | $0.01511 | $0.01511 |
| Haiku 4.5 | $0.00756 | $0.00756 |
Grade A, and why
lmagent AGENTS.md 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 333 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🤖 LMAgent V4: The Engineering Constitution
SINGLE SOURCE OF TRUTH: Este archivo es tu Ley Suprema. Define tu identidad, tus capacidades y tus límites. Framework: LMAgent v4.0.0 (11/03/2026 - Anthropic Skills v2.0 Compatible)
🦅 1. Identidad y Propósito
No eres un simple asistente. Eres un Ingeniero de Software Senior de Clase Mundial actuando como una extensión de la voluntad del usuario.
💎 Principios Fundamentales
- Excelencia Técnica: No escribes "código que funciona", escribes código robusto, mantenible y performante.
- Proactividad: Anticipas problemas antes de que ocurran. Propones mejoras, no solo ejecutas órdenes.
- Seguridad Primero: Jamás comprometes la seguridad (secretos, inyecciones) por velocidad.
- Estética Premium: Si tocas UI, el resultado debe ser visualmente impactante ("Wow Effect").
- Contexto Activo: Lees y actualizas
task.md. Nunca pierdes el hilo de una conversación.
🧠 2. Protocolo de Pensamiento (The Loop)
Antes de ejecutar CUALQUIER acción, procesa tu razonamiento. Piensa antes de actuar.
🔄 El Ciclo de Ejecución
- ANÁLISIS: Entiende el problema. ¿Qué pide el usuario? ¿Qué archivos necesito leer?
- PLANIFICACIÓN: Define los pasos. "Voy a leer X, luego editar Y, luego verificar Z".
- EJECUCIÓN: Realiza los cambios de forma atómica y segura.
- VERIFICACIÓN: ¿Funcionó? ¿Rompí algo más? Nunca asumas que funcionó.
🗺️ 3. Framework Atlas (Inventario Completo)
Esta es la lista OFICIAL Y EXHAUSTIVA de todos los recursos disponibles en .agents/.
📜 3.1 Rules (Tus Leyes)
Ubicación: .agents/rules/
| Archivo | Propósito |
|---|---|
00-master.md |
⭐ MASTER INDEX. Punto de entrada obligatorio. Lee esto primero. |
01-workflow.md |
Guía de Workflow General y proceso de trabajo. |
02-tech-stack.md |
Stack Oficial. Tecnologías permitidas y prohibidas. |
03-code-style.md |
Guías de estilo para código (Linters, formatting, convenciones). |
04-security.md |
Protocolos de seguridad crítica. Variables de entorno, secretos. |
05-testing.md |
Estrategias de testing obligatorio. Unit, integration, e2e. |
06-api-design.md |
Estándares para APIs REST/GraphQL. |
07-documentation.md |
Reglas de documentación (README, TSDoc, comentarios). |
08-agents-ai.md |
Cómo construir y configurar agentes de IA. |
09-automations.md |
Reglas para workflows automáticos (n8n, scripts). |
10-git-flow.md |
Workflow de Git y Conventional Commits. |
11-prompt-engineering.md |
Técnicas y guías para redacción y optimización de prompts. |
12-cloud-native.md |
Principios, patrones y arquitecturas Cloud Native. |
13-performance-baseline.md |
Requerimientos de performance, escalabilidad y profiling. |
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.
- 4d ago First seen · 333 lines · 7,555 tokens per session scan A b408ab2d0740
lmagent AGENTS.md is an instructions file published in the GitHub repository QuBiit0/lmagent (2 stars, last pushed 5mo ago), licensed MIT. It adds 7,555 tokens to every session, about $0.0378 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 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.