librechat-docs

librechat-docs is a skill for Claude Code, Codex from LibreChat-AI/librechat.ai. It costs 24 tokens per session (301 once invoked), scanned A, original, MIT.

A reference skill for LibreChat, an open-source chat application. It uses LibreChat’s official documentation to guide installation, configuration, use, and troubleshooting.

In plain words
What is it for?
Finding the right official documentation, checking configuration options, distinguishing where settings belong, and troubleshooting supported LibreChat features.
Why use it?
It reduces the risk of relying on outdated or invented settings when setting up or diagnosing LibreChat.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

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.

agentmods
npx agentmods add skills/librechat-ai/librechat.ai/librechat-docs
Any agent
npx skills add LibreChat-AI/librechat.ai --skill librechat-docs
Clone the repo
git clone --depth 1 https://github.com/LibreChat-AI/librechat.ai

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for librechat-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/librechat-ai/librechat.ai/librechat-docs.svg)](https://agentmods.dev/skills/librechat-ai/librechat.ai/librechat-docs)
Your own site
<a href="https://agentmods.dev/skills/librechat-ai/librechat.ai/librechat-docs"><img src="https://agentmods.dev/badge/skills/librechat-ai/librechat.ai/librechat-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00024 $0.00301
Opus 5 $0.00012 $0.00151
Sonnet 5 $0.00005 $0.00060
Haiku 4.5 $0.00002 $0.00030

Measured 6d ago against content hash bffd53838ea9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

librechat-docs 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 6d 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.

public/.well-known/agent-skills/librechat-docs/SKILL.md · 25 lines

What it actually says

LibreChat Documentation

Use LibreChat's official documentation as the source of truth for installation, configuration, features, administration, and troubleshooting.

Documentation workflow

  1. Fetch https://www.librechat.ai/llms.txt to find the most relevant documentation page.
  2. Fetch a page as Markdown by appending .md to its canonical docs URL. For example, use https://www.librechat.ai/docs/configuration/librechat_yaml.md for the custom configuration reference.
  3. Use https://www.librechat.ai/llms-full.txt only when the question spans multiple sections or the curated index is insufficient.
  4. Cite the canonical HTML documentation URL in the final answer so the user can read the rendered page.
  5. Check the changelog when behavior may differ between LibreChat releases.

Accuracy and safety

  • Do not invent configuration keys, environment variables, commands, defaults, or supported integrations.
  • Preserve the exact spelling and casing of settings shown in the documentation.
  • Distinguish settings in .env, librechat.yaml, Docker Compose overrides, and provider dashboards.
  • Use placeholders for credentials and secrets. Never ask users to publish secret values.
  • If the documentation does not answer the question, say so and direct the user to the LibreChat GitHub discussions or issue tracker.
Changes

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.

  1. 6d ago First seen · 25 lines · 24 tokens per session scan A bffd53838ea9

Subscribe to this mod's changes

librechat-docs is a skill published in the GitHub repository LibreChat-AI/librechat.ai (639 stars, last pushed yesterday), licensed MIT. It adds 24 tokens to every session and 301 once invoked, about $0.0001 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 2026-08-30.