Borrowing it
Nothing to install: this file belongs to majiayu000/litellm-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/majiayu000/litellm-rs/main/.claude/skills/observability-architecture/SKILL.mdgit clone --depth 1 https://github.com/majiayu000/litellm-rsWrote 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/majiayu000/litellm-rs/observability-architecture)<a href="https://agentmods.dev/skills/majiayu000/litellm-rs/observability-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/litellm-rs/observability-architecture/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/majiayu000/litellm-rs/observability-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/litellm-rs/observability-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.01241 |
| Opus 5 | $0.00041 | $0.00620 |
| Sonnet 5 | $0.00016 | $0.00248 |
| Haiku 4.5 | $0.00008 | $0.00124 |
Grade A, and why
observability-architecture 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 11d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Observability Architecture Guide
Overview
Observability in LiteLLM-RS is built from three runtime pieces:
- HTTP metrics —
MetricsMiddleware(src/server/middleware/metrics.rs) counts requests with process-local atomics and renders Prometheus text format on demand. Noprometheuscrate is used; series are hand-rendered and use thegateway_prefix except the standalonerate_limiter_degraded_totalcounter. - Health/status routes —
src/server/routes/health.rsmounts/health,/health/ready,/health/detailed,/status,/version, and/metricson the main HTTP server. - Callback exporters — configured under
monitoring.callbacks, theOpenTelemetryIntegration(OTLP/HTTP JSON),DataDogIntegration, andLangfuseIntegrationreceive real LLM lifecycle events through theCallbackDispatcherstored inAppState(exposed asRuntimeObservability).
┌─────────────────────────────────────────────────────────────────┐
│ LiteLLM Gateway │
├─────────────────────────────────────────────────────────────────┤
│ ┌───────────────┐ ┌───────────────┐ ┌───────────────┐ │
│ │ Metrics │ │ Health/status │ │ Callback │ │
│ │ middleware │ │ routes │ │ dispatcher │ │
│ └───────┬───────┘ └───────┬───────┘ └───────┬───────┘ │
└──────────┼──────────────────┼──────────────────┼───────────────┘
▼ ▼ ▼
┌──────────────────┐ ┌──────────────────┐ ┌──────────────────┐
│ Prometheus │ │ LB / K8s probes │ │ OTLP / Datadog / │
│ scrapes /metrics │ │ + JSON status │ │ Langfuse backends│
└──────────────────┘ └──────────────────┘ └──────────────────┘
Configuration
The section is monitoring: at the top level of config/gateway.yaml (deserialized as
GatewayConfig.monitoring, src/config/models/gateway.rs). The outer monitoring models
use #[serde(deny_unknown_fields)], but callback backend payloads such as
OpenTelemetryConfig do not all make that guarantee; strictness follows the concrete
deserialized struct.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 89 lines · 81 tokens per session scan A b6bb9261e92e
observability-architecture is a skill published in the GitHub repository majiayu000/litellm-rs (112 stars, last pushed 2d ago), licensed MIT. It adds 81 tokens to every session and 1,241 once invoked, about $0.0004 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 skills, from other repositories
omni-inference
The core OpenAI-compatible inference endpoints: chat completions, embeddings, images, audio (TTS/STT), moderations, rerank, and the Responses API. The primary integration surface for AI agents.
omni-settings
Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.
omni-providers
Manage provider connections, API keys, OAuth flows, and connection tests via the REST API. List, add, update, remove, and test AI provider integrations across OmniRoute's 327-provider catalog.
omni-version-manager
Install, start, stop, restart, and update embedded services (9Router, CLIProxyAPI). Monitor service status, retrieve logs, and configure auto-start for local-only service endpoints.
omni-cli-tools
Manage CLI tool integrations exposed via the API. List, configure, and invoke CLI tool plugins that extend OmniRoute's automation surface.
cli-serve
Start, stop, and restart the OmniRoute server from the CLI. Manage daemon mode, port configuration, auto-recovery, system tray integration, and the dashboard open shortcut.