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 agents/lehre-labs/llmsdottxt-mcp/docs-platformsgit clone --depth 1 https://github.com/lehre-labs/llmsdottxt-mcpWrote 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/agents/lehre-labs/llmsdottxt-mcp/docs-platforms)<a href="https://agentmods.dev/agents/lehre-labs/llmsdottxt-mcp/docs-platforms"><img src="https://agentmods.dev/badge/agents/lehre-labs/llmsdottxt-mcp/docs-platforms.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 | $0.00000 | $0.01022 |
| Opus 5 | $0.00000 | $0.00511 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
docs-platforms 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Platforms
llmsdottxt-mcp auto-discovers and fetches /llms.txt and /llms-full.txt from dependency docs. Platform detection enables optimized fetches; all standards-compliant platforms work via generic fallback.
Legend
- Auto-detected, optimized headers/URLs
- [~] Supported via generic
/llms.txtfallback (any standards-compliant platform) - Planned, not yet implemented
Hosted Documentation Platforms
| Platform | Status | Auto llms.txt | llms-full.txt | .md pages | Details |
|---|---|---|---|---|---|
| Mintlify | [x] | Yes | Yes | Yes | X-Llms-Txt header, well-known paths |
| Fern | [~] | Yes | Yes | Yes | Bot-specific markdown serving |
| GitBook | [x] | Yes | Yes | Yes | .gitbook.io URL + body marker |
| ReadMe | [x] | Yes (toggle) | No | Yes (.md suffix) | .readme.io URL pattern |
| Redocly | [x] | Yes (toggle) | No | No | .redoc.ly URL pattern |
Static Site Generator Plugins
| Framework | Plugin | Status | llms.txt | llms-full.txt | .md |
|---|---|---|---|---|---|
| Docusaurus | docusaurus-plugin-llms | [x] | Yes | Yes | Yes |
| Read the Docs | sphinx-llms-txt | [x] | Yes | Yes | No |
| Astro Starlight | starlight-llms-txt | [~] | Yes | Yes | Yes |
| MkDocs | mkdocs-llmstxt | [x] | Yes | Yes | No |
| VitePress | vitepress-plugin-llms | [~] | Yes | Yes | Yes |
| Hugo | Custom output format | [~] | Yes | Manual | No |
| Eleventy | eleventy-plugin-llms-txt | [ ] | Yes | No | No |
| Gatsby | gatsby-plugin-llms-txt | [ ] | Yes | No | No |
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 · 59 lines · 0 tokens per session scan A 8c9ed57bbbab
docs-platforms is an agent published in the GitHub repository lehre-labs/llmsdottxt-mcp (1 stars, last pushed 12d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,022 tokens. 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 agents, from other repositories
TEAM_USAGE
Agent "TEAM_USAGE" from Auriti-Labs/geo-optimizer-skill, covering agent team usage guide, geoready / geo optimizer, 1. agent inventory, 2. read-only reviewers and 3. code-writing implementation agents.
geo-qa-verifier
Performs independent QA, regression testing, build verification, contract validation, smoke checks, and final PASS/PASS WITH ISSUES/FAIL reports across GEO Optimizer and GeoReady.
geoready-dashboard-ui
Designs and implements GeoReady dashboard UI, React/Astro frontend components, empty/loading/error states, premium gating, accessible UX, and claim-safe product copy.
geoready-platform-api
Designs and implements GeoReady platform backend, API routes, database models, migrations, services, entitlements, scheduler jobs, and integration with GEO Optimizer JSON output.
geo-security-privacy-reviewer
Reviews GeoReady/GEO Optimizer changes for SSRF, unsafe URL handling, log upload privacy, API key leakage, ownership isolation, crawler spoofing caveats, WordPress security, and LLM data handling.
geo-wordpress-connector-architect
Designs the future lightweight WordPress connector for GeoReady, including API-key connection, site metadata, sitemap/CPT/WooCommerce/ACF detection, admin widget, security, and least-privilege architecture.