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 rules/librechat-ai/librechat.ai/librechat-documentationgit clone --depth 1 https://github.com/LibreChat-AI/librechat.aiWhat 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 | $0.00966 | $0.00966 |
| Opus 5 | $0.00483 | $0.00483 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
librechat-documentation 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 3d 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreChat Documentation Rules
Config Version Updates
When updating the LibreChat config version (e.g., from v1.2.6 to v1.2.7), follow these steps:
1. Create Changelog Files
Main Changelog File
Create: pages/changelog/config_v{VERSION}.mdx
Template:
---
date: YYYY/MM/DD
title: ⚙️ Config v{VERSION}
---
import { ChangelogHeader } from '@/components/changelog/ChangelogHeader'
import Content from '@/components/changelog/content/config_v{VERSION}.mdx'
<ChangelogHeader />
---
<Content />
Content File
Create: components/changelog/content/config_v{VERSION}.mdx
Format:
- Use bullet points starting with
- - Group related changes together
- Include links to detailed documentation using
[Feature Name](/docs/configuration/librechat_yaml/object_structure/{feature}) - Describe what was added/changed and its purpose
- Keep descriptions concise but informative
Example:
- Added `memory` configuration to control memory functionality for conversations
- Configure memory persistence and personalization settings
- Set token limits and message window sizes for memory context
- Configure agents for memory processing with provider-specific settings
- Supports both predefined agents (by ID) and custom agent configurations
- See [Memory Configuration](/docs/configuration/librechat_yaml/object_structure/memory) for details
2. Create Object Structure Documentation
For new root-level configurations, create: pages/docs/configuration/librechat_yaml/object_structure/{feature}.mdx
Structure:
- Title:
# {Feature} Configuration - Overview: Brief description of the feature
- Example: Complete YAML example showing all options
- Field Documentation: Use
<OptionTable>components for each field - Subsections: For complex nested objects
- Notes: Important considerations at the end
3. Update Navigation
Add the new feature to: pages/docs/configuration/librechat_yaml/object_structure/_meta.ts
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.
- 3d ago First seen · 146 lines · 966 tokens per session scan A c7feb9da821a
librechat-documentation is a cursor rule published in the GitHub repository LibreChat-AI/librechat.ai (637 stars, last pushed 4d ago), licensed MIT. It adds 966 tokens to every session, about $0.0048 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.
Other cursor rules, from other repositories
rtfmbro
Cursor rule "rtfmbro" from marckrenn/rtfmbro-mcp, covering cursor instructions for package documentation, package documentation policy and workflow.
css-styling
CSS architecture, tokens, and styling rules for this Docusaurus site. Apply when creating or modifying components, styles, layouts, or any UI-facing code.
workflow
Compatibility shell — routes tasks to skill-based-architecture's self-hosted SKILL.md at repo root.
global
Cursor rule "global" from KroMiose/nekro-agent, covering 项目背景(简要), 开发规范, 文档, 开发指南 and 功能/页面开发完整流程.
rendering-and-memoization
React anti-patterns R9, R11, R12 — index-as-key in dynamic lists, context overuse for frequent updates, inline functions breaking memoization. Load on a review hit for any of these codes, or when tuning render performance.
react-antipatterns
Routing index for React anti-patterns R1-R21 (hooks, effects, state, rendering, web vitals). Names every code and points at the themed file holding its Do/Don't example and fix. Load this to resolve a code, then load only the themed file you need.