OmniRoute is an AI gateway that gives coding agents one endpoint for accessing models from many providers, with quota-aware fallback between them. It is for people using Claude Code, Codex, Cursor, OpenCode, Cline, Copilot, and similar tools who want a single route to their available AI models.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add diegosouzapw/OmniRoute --skill omni-api-keysgit clone --depth 1 https://github.com/diegosouzapw/OmniRouteWrote 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.
[](https://agentmods.dev/skills/diegosouzapw/omniroute/omni-api-keys)<a href="https://agentmods.dev/skills/diegosouzapw/omniroute/omni-api-keys"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/omni-api-keys/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.
<a href="https://agentmods.dev/skills/diegosouzapw/omniroute/omni-api-keys"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/omni-api-keys.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
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 →
- high Tool Misuse · line 57 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 146 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 175 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 204 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 22 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.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.01672 |
| Opus 5.5 | $0.00016 | $0.00669 |
| Sonnet 5.5 | $0.00008 | $0.00334 |
| Haiku 4.5 | $0.00004 | $0.00167 |
Grade A, and why
omni-api-keys scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:20128/api/keys \ Copies of this mod
1 near-identical copy found in the catalogue:
- omni-api-keys — 100% identical, 173 lines differ
How it starts
The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
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.
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/keys
List API keys
curl http://localhost:20128/api/keys \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
POST /api/keys
Create API key
curl -X POST http://localhost:20128/api/keys \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
GET /api/keys/{id}
Get API key
curl http://localhost:20128/api/keys/{id} \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
PATCH /api/keys/{id}
Update API key
curl -X PATCH http://localhost:20128/api/keys/{id} \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
DELETE /api/keys/{id}
Delete API key
curl -X DELETE http://localhost:20128/api/keys/{id} \
-H "Authorization: Bearer $OMNIROUTE_TOKEN"
POST /api/keys/{id}/access
Add or remove allowed models and combos on an API key atomically
Adds or removes allowed models and combos on an API key without lost updates. Serialized per key ID using an in-process async lock. Keys allowing all models (modelAccessMode: all) or all combos (allowedCombos containing 'combo/*') require switchToRestricted: true when adding new models or combos, otherwise returning a 409 Conflict. When switching to restricted mode, the allowlist becomes exactly the net added items (at least one required). Direct concurrent PATCH calls to /api/keys/{id} completely overwrite the policy outside this lock.
curl -X POST http://localhost:20128/api/keys/{id}/access \
-H "Authorization: Bearer $OMNIROUTE_TOKEN" \
-H "Content-Type: application/json" \
-d '{}'
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.
- 8d ago Changed · +2 lines 3c3b147db818
- 11d ago Changed 4c04bb6fb364
- 17d ago Changed · +19 lines 5c71b8e407b3
- 1mo ago Changed · +136 lines 862f384e6209
- 1mo ago First seen · 80 lines · 40 tokens per session scan A 050d7310c8eb
omni-api-keys is a skill published in the GitHub repository diegosouzapw/OmniRoute (80,849 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 1,672 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
workflow-ai-coding
Edit, validate, debug, publish, and inspect ReachAI Workflow drafts through the Workflow AI Coding REST API. Use when asked to create or modify a workflow graph, add/update/delete nodes or edges, validate GraphSpec, dry-run or debug-run a workflow, inspect trace/run output, check release readiness, publish a validated…
reachai-onboarding
Integrate Java business systems with ReachAI SDK registration, SDK instance heartbeat, gateway/embed access, and optional API Management handoff. Use when asked to connect a Spring Boot service to ReachAI, add reachai-capability-sdk or reachai-spring-boot2-starter, configure…
keirouter
Entry point for KeiRouter — local/remote AI gateway with OpenAI-compatible REST for chat, image, TTS, embeddings, web search, web fetch. Use when the user mentions KeiRouter, KEIROUTERURL, or wants AI without writing provider boilerplate. This skill covers setup + indexes capability skills; fetch the relevant…
ai-wrapper-product
AI Wrapper Product workflow skill. Use this skill when the user needs Expert in building products that wrap AI APIs (OpenAI, Anthropic, and the operator should preserve the upstream workflow, copied support files, and provenance before merging or handing off.
stripe-projects
Provision SaaS services + sync creds via Stripe Projects.
cqrs-implementation
Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.