Borrowing it
Nothing to install: this file belongs to antoniovazquezaraujo/LeTrain. 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/antoniovazquezaraujo/LeTrain/develop/AGENTS.mdgit clone --depth 1 https://github.com/antoniovazquezaraujo/LeTrainWrote 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/antoniovazquezaraujo/letrain/agents-md)<a href="https://agentmods.dev/instructions/antoniovazquezaraujo/letrain/agents-md"><img src="https://agentmods.dev/badge/instructions/antoniovazquezaraujo/letrain/agents-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/antoniovazquezaraujo/letrain/agents-md"><img src="https://agentmods.dev/badge/instructions/antoniovazquezaraujo/letrain/agents-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 | $0.01624 | $0.01624 |
| Opus 5.5 | $0.00650 | $0.00650 |
| Sonnet 5.5 | $0.00325 | $0.00325 |
| Haiku 4.5 | $0.00162 | $0.00162 |
Grade A, and why
LeTrain 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Guía para Agentes de Desarrollo
Equipo de Desarrollo
Este proyecto usa un equipo de agentes definido en .opencode/agents/:
- Dani (dani-coordinator) — Coordinador principal
- Alex (alex-java) — Experto en Java
- Bicho (bicho-testing) — Experto en testing
- Jorge (jorge-ui) — Experto en UI/UX
IMPORTANTE: Al iniciar cada sesión, lee TODOS los ficheros en .opencode/agents/ antes de hacer cualquier otra cosa. Estos ficheros definen las personalidades, reglas y formatos de respuesta de cada agente del equipo.
IMPORTANTE: Al iniciar cada sesión, lee TODOS los ficheros en instructions/. Contienen las directrices del proyecto (coding standards, build commands, estructura, convenciones) que deben aplicarse a todo el código.
IMPORTANTE: Al iniciar cada sesión, lee CONTRIBUTING.md. Define el flujo Git del proyecto: ramas feature/... o fix/... desde develop, PROHIBIDO commitear directamente a develop (está protegida), PRs en inglés y mvn clean test en verde antes de abrir o actualizar un PR.
Espacio de trabajo auxiliar (letrain-lab)
Los artefactos que no deben commitearse viven fuera del repositorio, en la carpeta hermana del repo (por defecto /home/antonio/dev/letrain-lab/):
notes/— borradores de diseño, contratos y documentos de trabajo; se revisan antes de formalizarse endocs/.demo/— prototipos independientes (pueden usar las clases compiladas del juego, p. ej.core/target/classes).wt/— worktrees temporales de los agentes:git worktree add /home/antonio/dev/letrain-lab/wt/<nombre> -b <rama> origin/develop.
Reglas: nada de letrain-lab/ se commitea; no guardar allí ni en /tmp nada que deba sobrevivir a la sesión (/tmp se borra al salir); los worktrees nunca dentro del checkout principal; al terminar una tarea, eliminar su worktree (git worktree remove) y borrar la rama.
Estructura del Proyecto
.opencode/
├── agents/
│ ├── dani-coordinator.md # Coordinador (agente principal)
│ ├── alex-java.md # Experto Java
│ ├── bicho-testing.md # Experto testing
│ └── jorge-ui.md # Experta UI/UX
├── package.json # Dependencias OpenCode
└── .gitignore
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 Changed · +7 lines · +211 tokens per session 52bc9dfda35c
- 17d ago Changed · +36 tokens per session 8abfe871d844
- 18d ago Changed · +11 lines · +208 tokens per session da69dbfd5676
- 1mo ago Changed · +10 tokens per session 5dad6e19af5f
- 1mo ago Changed · +3 lines · +107 tokens per session c53110e24515
- 1mo ago First seen · 85 lines · 1,052 tokens per session scan A d7d737d4078f
LeTrain AGENTS.md is an instructions file published in the GitHub repository antoniovazquezaraujo/LeTrain (49 stars, last pushed today), licensed Apache-2.0. It adds 1,624 tokens to every session, about $0.0065 per session on Opus 5.5. 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.
Other instructions, from other repositories
vibetags com-example-service-OrderService.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for orderservice, rules for method calculatetax, rules for method processpayment, rules for method validateorder and context & focus.
vibetags com-example-security-SecurityConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for securityconfig, locked status, rules for method getencryptionalgorithm, rules for method getkeyrotationhours and rules for method getmaxloginattempts.
vibetags com-example-concurrent-SessionCache.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for sessioncache and thread-safety guarantee.
vibetags com-example-config-AsyncTestConfig.instructions.md
Instructions for PIsberg/vibetags, covering copilot instructions for asynctestconfig and immutable type.
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.