Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add bethanychamberlain/claude-skills-librechat/plugin install librechat-opsWrote 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/bethanychamberlain/claude-skills-librechat/monitoring)<a href="https://agentmods.dev/skills/bethanychamberlain/claude-skills-librechat/monitoring"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/monitoring/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/bethanychamberlain/claude-skills-librechat/monitoring"><img src="https://agentmods.dev/badge/skills/bethanychamberlain/claude-skills-librechat/monitoring.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 | $0.00054 | $0.01305 |
| Opus 5 | $0.00027 | $0.00652 |
| Sonnet 5 | $0.00011 | $0.00261 |
| Haiku 4.5 | $0.00005 | $0.00130 |
Grade A, and why
monitoring 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 10d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LibreChat Monitoring & Observability
You are an expert in LibreChat observability. Your goal is to help users set up logging, metrics, cost tracking, and LLM tracing for their LibreChat deployment.
Before Starting
Check for context first:
If librechat-context.md exists in the current working directory, read it before asking questions.
Use that context and only ask for information not already covered or specific to this task.
If librechat-context.md does not exist, ask the user:
- What LibreChat version are you running?
- How is it deployed? (Docker local / Docker remote / Kubernetes)
- What do you want to monitor? (logs / metrics / LLM costs / all)
How This Skill Works
Mode 1: Set Up Monitoring
When adding monitoring capabilities to a LibreChat deployment.
- Determine what monitoring they need (logs, Prometheus metrics, Langfuse, token tracking)
- For logging: Load
${CLAUDE_PLUGIN_ROOT}/references/logging-config.md - For Langfuse: Load
${CLAUDE_PLUGIN_ROOT}/references/langfuse-setup.md - For token/cost tracking: Load
${CLAUDE_PLUGIN_ROOT}/references/token-tracking.md - Provide exact
.envandlibrechat.yamlchanges with restart commands
Mode 2: Analyze Logs
When diagnosing issues from logs.
- Show how to access logs:
docker compose logs apior check/app/logs/directory - Explain LibreChat's log file structure:
debug-YYYY-MM-DD.log-- debug-level output (enabled by default)error-YYYY-MM-DD.log-- errors with stack tracesmeiliSync-YYYY-MM-DD.log-- MeiliSearch sync activity
- Logs rotate every 14 days
- Guide them through common error patterns
- If the issue needs config changes, suggest the config skill (librechat-core)
Mode 3: Cost Tracking
When setting up or reviewing token usage and spending.
- Load
${CLAUDE_PLUGIN_ROOT}/references/token-tracking.md - Explain the balance system in
librechat.yaml(enabled, startBalance, autoRefill) - Show how to manage balances with CLI commands
- Explain the Transactions collection in MongoDB
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.
- 10d ago First seen · 115 lines · 54 tokens per session scan A 7199cb2a1b5d
monitoring is a skill published in the GitHub repository bethanychamberlain/claude-skills-librechat (3 stars, last pushed 5mo ago), licensed MIT. It adds 54 tokens to every session and 1,305 once invoked, about $0.0003 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
TEMPLATE
../../../agents/personas/TEMPLATE.md.
world-model-diagnostic
Twenty-minute diagnostic mapping a team to a world-model paradigm (vector DB, structured ontology, signal-fidelity). Use when you say "run the world model diagnostic", "audit our world model", "which world model architecture fits us", or "audit where we automate judgment". Use for AI readiness assessments and…
benchmark-models
Cross-model benchmark. Runs one prompt or skill through Claude, GPT (Codex CLI), and Gemini side by side and compares latency, tokens, cost, tool calls, and optionally output quality via an Anthropic-API judge. Answers "which model is actually best for this skill?" with data. Use when you say "benchmark models"…
data-pipeline
ETL/ELT pipeline design. Trigger when the user wants to create data flows, transformations, or orchestration.
chain-llm-pattern
Build multi-step LLM reasoning chains in n8n using Groq, OpenAI, or Claude for structured data extraction, categorization, scoring, and analysis. Use this skill whenever the user wants to chain multiple LLM calls together in an n8n workflow — phrases like "extract entities then categorize", "multi-step LLM prompt"…
AgentDB Learning Plugins
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.