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 5.5 | $0.00051 | $0.00882 |
| Sonnet 5.5 | $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 2mo 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.
- 2mo 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 2mo ago), licensed MIT. It adds 127 tokens to every session and 2,204 once invoked, about $0.0005 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 2026-08-31.
llms-txt-aware compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| llms-txt-awareMauricioPerera/llms-txt-skills | Skill | 2 | 2mo ago | MIT | A | 127 | Claude Code |
| dingtalk_channel_connectagentscope-ai/QwenPaw | Skill | 37k | 2d ago | Apache-2.0 | A | 69 | Claude Code, Codex |
| browser_cdpagentscope-ai/QwenPaw | Skill | 37k | 2d ago | Apache-2.0 | A | 85 | Claude Code, Codex |
| browser_visibleagentscope-ai/QwenPaw | Skill | 37k | 2d ago | Apache-2.0 | A | 108 | Claude Code, Codex |
| browser_visibleagentscope-ai/QwenPaw | Skill | 37k | 2d ago | Apache-2.0 | A | 75 | Claude Code, Codex |
| skill-bodycitrolabs/ego-lite | Skill | 22k | today | MIT | A | 0 | Claude Code, Codex |
| ego-browsercitrolabs/ego-lite | Skill | 22k | today | MIT | A | 125 | Claude Code, Codex |