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 skills add MauricioPerera/llms-txt-skills --skill llms-txt-awaregit clone --depth 1 https://github.com/MauricioPerera/llms-txt-skillsWrote 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/skills/mauricioperera/llms-txt-skills/llms-txt-aware)<a href="https://agentmods.dev/skills/mauricioperera/llms-txt-skills/llms-txt-aware"><img src="https://agentmods.dev/badge/skills/mauricioperera/llms-txt-skills/llms-txt-aware/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/skills/mauricioperera/llms-txt-skills/llms-txt-aware"><img src="https://agentmods.dev/badge/skills/mauricioperera/llms-txt-skills/llms-txt-aware.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 | $0.00127 | $0.02204 |
| Opus 5 | $0.00063 | $0.01102 |
| Sonnet 5 | $0.00025 | $0.00441 |
| Haiku 4.5 | $0.00013 | $0.00220 |
Grade A, and why
llms-txt-aware 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 12d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
llms-txt-aware
Esta skill te obliga, antes de interactuar con cualquier dominio web, a buscar su archivo llms.txt y usarlo como fuente de verdad. El archivo entero es contexto operativo, no solo la sección ## Skills.
Cuándo activar
Activá esta skill cada vez que vayas a:
- Hacer un
web_fetcho request HTTP a un dominio que todavía no chequeaste en esta conversación. - Llamar una API REST/GraphQL pública sin documentación local previa.
- Scrapear contenido HTML de un sitio.
- Construir una URL del sitio (paths, endpoints, querystrings, headers).
- Inferir el comportamiento esperado de un servicio remoto.
No la actives para:
- Búsquedas web genéricas (
web_search). - Dominios que ya chequeaste y cacheaste en este mismo turno.
- Recursos binarios directos (imágenes, PDFs, descargas).
- Sitios que ya tenés documentados localmente (docs en el repo del usuario, OpenAPI a mano, etc).
Procedimiento
Paso 1: extraer el origen
Dado una URL objetivo como https://demo.ejemplo.com/api/x/y?z=1, el origen es https://demo.ejemplo.com. Trabajá siempre a nivel de origen, no de path.
Paso 2: probar el /llms.txt
Hacé GET {origen}/llms.txt con timeout corto (5 a 10 segundos).
Estados posibles y qué hacer con cada uno:
200 OKconContent-Type: text/markdown,text/plaino body que empieza con#: seguir al paso 3.200 OKpero el body es HTML (la SPA devuelve el index): tratarlo como 404, no existe llms.txt real.404,403,5xx, timeout, o redirect que termina en HTML: cachear "no llms.txt" para este origen y seguir tu flujo normal.
Fallback opcional: si el principal devuelve 404, probá una sola vez {origen}/.well-known/llms.txt. Si tampoco está, cortás ahí.
Paso 3: leer el archivo COMPLETO
Esto es lo crítico. NO te limites a la sección ## Skills. El archivo entero es manual del sitio. Tenés que extraer y usar:
# Títuloy> tagline: identidad y propósito del sitio.- Secciones de endpoints, paths, métodos HTTP, headers requeridos.
- Parámetros con sus tipos, si son obligatorios u opcionales, defaults y límites.
- Respuestas esperadas: códigos HTTP, content-types, forma del payload.
- Cache, rate limits, política de retry.
- Ejemplos canónicos de URLs y bodies.
- Constraints explícitos: paths que NO existen, endpoints que NO hay que llamar.
- Notas para agentes (suelen aparecer como
## Notes for agents,## For LLMs,## Agent guidance). - Sección
## Skillssi está, para descubrir skills publicadas (ver paso 5).
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.
- 12d ago First seen · 161 lines · 127 tokens per session scan A 6f0604e555d8
llms-txt-aware is a skill published in the GitHub repository MauricioPerera/llms-txt-skills (2 stars, last pushed 13d ago), licensed MIT. It adds 127 tokens to every session and 2,204 once invoked, about $0.0006 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 skills, from other repositories
dingtalk_channel_connect
Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bot, Stream mode, binding or configuring a channel. Supports pausing when a login page is detected and resuming after the user logs in.
browser_cdp
Use this skill when the user explicitly wants to connect to a running Chrome browser, scan local CDP ports, specify a cdpport, or share a single browser across multiple agents/tools. By default browser opens no debugging port; pass an explicit cdpport only when the user wants another local tool to attach.
browser_cdp
Browser connection controls for finding local debugging ports, attaching to an already running Chrome browser, or sharing one browser between tools.
browser_visible
Browser launch controls for choosing whether a Chromium-based browser window is visible, which browser program to run, and which startup options to pass.
browser_visible
Use this skill when the user needs to control the browser launch mode for browser. By default browser is managed by Playwright and opens no debugging port (pass an explicit cdpport to let another local tool attach); headed controls whether the window is visible, and privatemode is kept for backward compatibility and…
ego-browser
When you need a browser, read this Skill by default. Use it to open and operate websites, fill forms, click buttons, take screenshots, extract page data, sign in, and perform other browser automation tasks, as well as web app testing, dogfooding, QA, bug investigation, and app-quality review. ego-browser (ego-lite) is…