cheaper-inference/omniroute944 installs

omni-settings

Q: How do I install this agent skill?

Run npx skills add https://github.com/cheaper-inference/omniroute --skill omni-settings.

Q: Is this agent skill safe to install?

Review the displayed partner audits, complete source, permissions, dependencies, and exact revision before installing.

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

How do I install this agent skill?

npx skills add https://github.com/cheaper-inference/omniroute --skill omni-settings

view source ↗

Is this agent skill safe to install?

Socketpass
No alerts
Snykpass
Risk: LOW · No issues
Gen Agent Trust Hubpass
This skill provides documentation and endpoint references for managing the global settings of an application (Omni). It allows an agent to read and update various configurations, including security policies, system prompts, and third-party integrations (e.g., Qdrant, Notion, Obsidian). The skill operates on a local service and includes documentation for secure handling of sensitive data, such as masking API keys and requiring passwords for security-sensitive updates. No malicious patterns were detected.

What does this agent skill do?

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.

How can the creator link this skill?

Add the canonical catalog link to the repository README so users can inspect current installs and available audits. The publishing guide covers the complete discovery path.

<a href="https://skillzs.dev/skills/cheaper-inference/omniroute/omni-settings">View omni-settings on skillZs</a>