@cheaper-inference
Organization
52 skills1 repository 79.4K
Run or inspect local Release-Green checks for a specific code revision or combined pull request candidate. Report blocking failures, diagnostic differences, and missing evidence, compare against the base revision, and identify remaining CI checks.
Repair confirmed failures in CI, the automated build and test process, starting with the base branch. Then prepare affected pull requests individually, recording checks for the exact code candidate and unresolved issues for owner review.
Configure Codex CLI to connect through OmniRoute on Linux, macOS, or Windows. The workflow detects the operating system and shell, creates configuration files and seven profiles, sets environment variables, and verifies the setup.
Manage API key authentication and session tokens. Start here to authenticate requests via Bearer token, obtain session cookies, and configure login requirements for the OmniRoute API.
The English summary is being prepared. Showing the original description.
Register and manage webhook endpoints, which receive event notifications from OmniRoute. Choose events such as completed requests or exceeded quotas, test delivery, inspect delivery history, and manage retries when notifications need another attempt.
Create and run automated tests that score LLM answers against expected outputs or judging criteria. Monitor progress, inspect individual results, compare models on the same tests, and use score thresholds in CI, an automated checking workflow.
Connect AI agents to OmniRoute through MCP, a protocol for accessing tools. Use tools for request routing, memory, cache, providers, and audits, with three connection methods and permission scopes that control which operations are available.
Find agent skills on GitHub, score their relevance using rule-based checks, scan for malware and embedded secrets, and import them into supported agent directories, including Hermes, Claude Code, Gemini CLI, and OpenCode.
Synchronize OmniRoute configuration, provider connections, and settings with cloud storage. Manage authentication for the cloud worker, a remote service, along with its credentials and remote backup destinations.
Create, list, rotate, and revoke OmniRoute API keys. Control per-key scopes, spending limits, and expiration. Keys gate access to all proxy and management endpoints.
The English summary is being prepared. Showing the original description.
Create and manage secure tunnels that make OmniRoute accessible over the internet. Use ngrok, Cloudflare Tunnel, or a custom tunnel to share access with remote agents and automated build and test pipelines.
Configure prompt compression, which shortens text sent to AI models, through the OmniRoute command line. Adjust RTK filters, Caveman rules, and combined compression modes, then preview the results using real prompts.
Create, list, rotate, and revoke OmniRoute API keys from the CLI. Manage OAuth flows for provider authentication and inspect key scopes and expiration.
The English summary is being prepared. Showing the original description.
Keep coding changes small by questioning unnecessary work and reusing existing code, standard libraries, and native platform features. Apply this approach to implementation, bug fixes, reviews, and dependency choices while preserving validation, security, and accessibility.
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 375-provider catalog.
The English summary is being prepared. Showing the original description.
Start, stop, and restart the OmniRoute server from the command line. Configure its port, background operation, automatic recovery, and system tray integration, or open the dashboard to manage the running server.
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.
Review AI call logs by provider, model, time range, status, and cost. Aggregate token usage, export logs, configure budgets, and inspect response times and prompt cache statistics to understand usage and performance.
Create, list, switch, and delete model routing combinations from the command line. Request suggestions using task descriptions, cost limits, and response time limits, with an option to explain recommendations or activate a suggested setup.
Query available AI models across all configured providers. List models, resolve model aliases, and browse the full model catalog including provider-specific variants.
The English summary is being prepared. Showing the original description.
Submit groups of AI requests as batch jobs with the OmniRoute command line. Manage input files, monitor or cancel jobs, save results and errors, and incorporate batch processing into automated build and deployment workflows.
Configure compression for command output, prose, and chat history before sending them to AI providers. Choose suitable engines, adjust language rules, and preview compressed text and reported savings before enabling a mode.
Manage Omni Skills, plugins, and persistent memory from the command line. Find and install skills, run them with supplied input, inspect execution history, and maintain saved information alongside plugin installations.
Query OmniRoute through A2A, a protocol for communication between agents. Get provider and model recommendations, check remaining quotas, find providers with required features, estimate request costs, and review system health.
Is this your account? Link GitHub to bring it onto your creator page (Japanese)