litellm-rs: Skill for Claude Code

.claude/skills/config-architecture/SKILL.md

config-architecture is a skill for Claude Code from majiayu000/litellm-rs. It costs 74 tokens per session (2,789 once invoked), scanned A, original, MIT.

A guide to how LiteLLM-RS reads, substitutes, validates, and applies YAML configuration at startup.

In plain words
What is it for?
Use it when changing configuration models, environment-variable substitution, startup validation, or configuration loading.
Why use it?
It clarifies configuration errors and the fact that changing the file requires restarting the service because there is no automatic reload.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is majiayu000/litellm-rs's own configuration. It tells Claude Code how to work on litellm-rs itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything litellm-rs configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/majiayu000/litellm-rs/main/.claude/skills/config-architecture/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/majiayu000/litellm-rs

Made for: Claude Code.

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 config-architecture

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/litellm-rs/config-architecture/github.svg)](https://agentmods.dev/skills/majiayu000/litellm-rs/config-architecture)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/litellm-rs/config-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/litellm-rs/config-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.

agentmods 80×15 button for config-architecture

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/litellm-rs/config-architecture"><img src="https://agentmods.dev/badge/skills/majiayu000/litellm-rs/config-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,789 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 61
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00074 $0.02789
Opus 5 $0.00037 $0.01394
Sonnet 5 $0.00015 $0.00558
Haiku 4.5 $0.00007 $0.00279

Measured 11d ago against content hash 05b68c3e70b0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

config-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.

.claude/skills/config-architecture/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Configuration Architecture Guide

Overview

LiteLLM-RS loads a single YAML file into type-safe Rust models (GatewayConfig in src/config/models/gateway.rs and its children), substitutes ${VAR} / $VAR tokens from the process environment during load, fills missing fields from serde defaults, then validates the whole tree once at startup.

There is no hot reload. Configuration is read once at startup; src/utils/config/optimized.rs states this explicitly ("Hot reload is not supported"). Restart the process to pick up changes. AppState.config (src/server/state.rs) is atomically swappable by explicit code paths, but nothing watches the file.

Load Order

┌─────────────────────────────────────────────────────────────────┐
│  1. YAML file                                                   │
│     --config PATH (default: "config/gateway.yaml", src/main.rs) │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│  2. Environment substitution (substitute_env_vars)              │
│     ${VAR} = required (hard error if unset)                     │
│     $VAR   = best-effort (left literal if unset)                │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│  3. serde parse + defaults                                      │
│     #[serde(default ...)] fills omitted fields;                 │
│     deny_unknown_fields rejects keys on structs that opt in     │
└─────────────────────────────────────────────────────────────────┘
                              ↓
┌─────────────────────────────────────────────────────────────────┐
│  4. Validation (Validate trait)                                 │
│     runs inside Config::from_file / Config::from_env            │
│     failure aborts startup                                      │
└─────────────────────────────────────────────────────────────────┘

Read the full file on GitHub · 232 lines

Files

What ships with it

3 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.

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. 11d ago First seen · 232 lines · 74 tokens per session scan A 05b68c3e70b0

Subscribe to this mod's changes

config-architecture is a skill published in the GitHub repository majiayu000/litellm-rs (112 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 2,789 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.