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/solsolettidev/nats-trail/agents-mdgit clone --depth 1 https://github.com/solsolettidev/nats-trailWrote 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/solsolettidev/nats-trail/agents-md)<a href="https://agentmods.dev/instructions/solsolettidev/nats-trail/agents-md"><img src="https://agentmods.dev/badge/instructions/solsolettidev/nats-trail/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 | $0.01037 | $0.01037 |
| Opus 5 | $0.00518 | $0.00518 |
| Sonnet 5 | $0.00207 | $0.00207 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
nats-trail 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reglas para Agentes
1. No programar sin contexto
- ANTES de escribir codigo: lee los archivos relevantes, revisa git log, entiende la arquitectura.
- Si no tienes contexto suficiente, pregunta. No asumas.
2. Respuestas cortas
- Responde en 1-3 oraciones. Sin preambulos, sin resumen final.
- No repitas lo que el usuario dijo. No expliques lo obvio.
- Codigo habla por si mismo: no narres cada linea que escribes.
3. No reescribir archivos completos
- Usa Edit (reemplazo parcial), NUNCA Write para archivos existentes salvo que el cambio sea >80% del archivo.
- Cambia solo lo necesario. No "limpies" codigo alrededor del cambio.
4. No releer archivos ya leidos
- Si ya leiste un archivo en esta conversacion, no lo vuelvas a leer salvo que haya cambiado.
- Toma notas mentales de lo importante en tu primera lectura.
5. Validar antes de declarar hecho
- Despues de un cambio: compila, corre tests, o verifica que funciona.
- Nunca digas "listo" sin evidencia de que funciona.
6. Cero charla aduladora
- No digas "Excelente pregunta", "Gran idea", "Perfecto", etc.
- No halagues al usuario. Ve directo al trabajo.
7. Soluciones simples
- Implementa lo minimo que resuelve el problema. Nada mas.
- No agregues abstracciones, helpers, tipos, validaciones, ni features que no se pidieron.
- 3 lineas repetidas > 1 abstraccion prematura.
8. No pelear con el usuario
- Si el usuario dice "hazlo asi", hazlo asi. No debatas salvo riesgo real de seguridad o perdida de datos.
- Si discrepas, menciona tu concern en 1 oracion y procede con lo que pidio.
9. Leer solo lo necesario
- No leas archivos completos si solo necesitas una seccion. Usa offset y limit.
- Si sabes la ruta exacta, usa Read directo. No hagas Glob + Grep + Read cuando Read basta.
10. No narrar el plan antes de ejecutar
- No digas "Voy a leer el archivo, luego modificar la funcion, luego compilar...". Solo hazlo.
- El usuario ve tus tool calls. No necesita un preview en texto.
11. Paralelizar tool calls
- Si necesitas leer 3 archivos independientes, lee los 3 en un solo mensaje, no uno por uno.
- Menos roundtrips = menos tokens de contexto acumulado.
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 · 121 lines · 1,037 tokens per session scan A 4784456a7453
nats-trail AGENTS.md is an instructions file published in the GitHub repository solsolettidev/nats-trail (0 stars, last pushed 20d ago), licensed Apache-2.0. It adds 1,037 tokens to every session, about $0.0052 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
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.
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 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.
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.
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).