omni-budget — Claude Code skill: token limits and API budget control
Sets spending limits, token quotas and rate-limit policies per key or globally. Shows current consumption and enforces cost controls across providers.
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a claude-codeWhat omni-budget does
The skill configures spending limits, token quotas and rate-limit rules — per API key or globally across all providers. Fetches current consumption via GET /api/rate-limit, updates configuration via POST /api/rate-limit.
All requests require a Bearer token or session cookie. Get a token via POST /api/auth/login; for local development set REQUIRE_API_KEY=false. Full request specification lives in docs/openapi.yaml or at GET /api/openapi/spec.
Install with npx skills add cheaper-inference/OmniRoute --skill omni-budget -a claude-code, which places the config in ~/.claude/skills/omni-budget/SKILL.md. For Cursor the path is .cursor/skills/omni-budget/SKILL.md, for Codex .agents/skills/omni-budget/SKILL.md.
What it helps with
- set spending limit per API key or globally
- check current token consumption
- configure rate-limit policy for a provider
- control budget across cross-provider requests
Example prompts for the agent
- Show current token consumption by key
- Set a 1000 tokens per minute limit for OpenAI
- Display rate-limit configuration
How to install omni-budget
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a claude-code2Manually: put the files in place
~/.claude/skills/omni-budget/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/omni-budget/
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a codex2Manually: put the files in place
.agents/skills/omni-budget/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a cursor2Manually: put the files in place
.cursor/skills/omni-budget/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install cheaper-inference/OmniRoute omni-budget2Manually: put the files in place
.github/skills/omni-budget/SKILL.md1Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a gemini-cli2Platform CLI
gemini skills install https://github.com/cheaper-inference/OmniRoute --path skills/omni-budgetManually: put the files in place
.devin/skills/omni-budget/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add cheaper-inference/OmniRoute --skill omni-budget -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about omni-budget
How to install omni-budget in Claude Code?
Run npx skills add cheaper-inference/OmniRoute --skill omni-budget -a claude-code, the skill lands in ~/.claude/skills/omni-budget/SKILL.md.
What does omni-budget do?
Sets spending limits, token quotas and rate-limit policies per API key or globally, shows consumption and enforces cost controls across providers.
How do I get a token to work with omni-budget?
Get a token via POST /api/auth/login. For local development you can set REQUIRE_API_KEY=false and skip the token.
Source text
SKILL.md · MIT
---
name: omni-budget
description: Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
---
<!-- generated by src/lib/agentSkills/generator.ts; manual edits will be overwritten -->
## Overview
Configure spending limits, token quotas, and rate-limit policies per API key or globally. Inspect current consumption and enforce cost controls across providers.
## Authentication
All requests require a valid Bearer token or session cookie. Obtain a token via `POST /api/auth/login` or configure `REQUIRE_API_KEY=false` for local development.
## Endpoints
### GET /api/rate-limit
Get rate limit configuration
```bash
curl http://localhost:20128/api/rate-limit \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
```
### POST /api/rate-limit
Update rate limit configuration
```bash
curl -X POST http://localhost:20128/api/rate-limit \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
```
## Payloads
See the full OpenAPI specification at `GET /api/openapi/spec` or `docs/openapi.yaml` for detailed request/response schemas.
© cheaper-inference · MIT · cheaper-inference/OmniRoute