FreePublished on GitHubEnglish overview

omni-settings

Read and update global OmniRoute settings through its API. Adjust system prompts, reasoning budgets that control model thinking requests, IP filters, login requirements, and rules for data sent to providers.

OriginalShow the original description

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

cheaper-inference/OmniRoute

AI rating70/ 100 See how to install

Good for

Review and update the shared system prompt
Preserve client reasoning settings for Codex
Configure IP filters and login requirements
Review rules for outgoing request data

Overview

What it does

This skill covers reading and updating global OmniRoute settings through its API. These include system prompts that provide shared instructions to AI, reasoning budgets, IP filters, login requirements, and rules for outgoing data. It also lists configuration APIs for memory, compression, proxies, caching, and databases.

When it helps

It is intended for operators who need to adjust behavior across the application. It is especially useful when you want reasoning settings specified by clients such as Codex to remain intact when requests pass through OmniRoute.

Example requests

“Check the current system prompt and update the shared instructions.”
“Check the thinking budget so that Codex reasoning settings are preserved.”
“Review the IP filter and login requirement settings.”

Notes

A valid Bearer token or session cookie is required. The thinking budget controls how outgoing requests are rewritten. passthrough preserves the client's reasoning settings and is described as necessary for Codex's thinking display. auto removes reasoning-related settings, which may leave the thinking panel empty. Consult the OpenAPI specification for detailed input and output formats.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?: AGoodThe material explicitly identifies reading and updating global settings and lists the settings involved.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?: BPartly lackingHTTP methods and paths are listed, but the supplied excerpt contains no request bodies or response examples.
SafetyAre sending data, deleting files, and running commands disclosed?: BPartly lackingIt lists APIs for clearing history and changing settings, but the supplied excerpt gives no impact scope or confirmation procedures.
Easy setupDoes it need few tools or API keys, and are they documented?: BPartly lackingA Bearer token or cookie is required; a login endpoint is given, but connection configuration is not explained.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 22, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Files included (2)

SKILL.md14.7 KB
references/endpoints.md45.4 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Overview

Read and update global application settings: system prompts, thinking budget, IP filters, payload rules, combo defaults, and require-login configuration.

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

Payloads

See the full OpenAPI specification at GET /api/openapi/spec or docs/openapi.yaml for detailed request/response schemas.

GET /api/settings/thinking-budget — behavior

Returns proxy-level thinking/reasoning request rewrite settings:

Field	Meaning
`mode`	`passthrough` (leave client reasoning alone — required for Codex visible thinking), `auto` (strips all client thinking fields), `custom`, `adaptive`
`customBudget`	Fixed budget when `mode=custom`
`effortLevel`	Base effort when `mode=adaptive`

Not compression and not "decrypt encrypted reasoning". Full guide: docs/guides/THINKING_BUDGET.md.

Example — keep client-controlled reasoning (Codex/Desktop):

curl -X PUT https://localhost:20128/api/settings/thinking-budget \
  -H "Authorization: Bearer $OMNIROUTE_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"mode":"passthrough","customBudget":10240,"effortLevel":"medium"}'

Warning: mode=auto deletes reasoning / reasoning_effort / Claude thinking from the outbound body before upstream. That can empty thinking panels even when the client requested Ultra + summary.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

More skills from this repository

cli-a2a

FreeSummaryAI rating 90

Use the command line to send tasks to OmniRoute's A2A server, which supports communication between agents. Inspect execution history and logs, monitor or cancel tasks, and interactively test the JSON-RPC 2.0 communication protocol.

Check server status and available skills
Invoke a skill with JSON input
Inspect task history and logs