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 sweep-redsgit 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/sweep-reds)<a href="https://agentmods.dev/skills/diegosouzapw/omniroute/sweep-reds"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/sweep-reds/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/sweep-reds"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/sweep-reds.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00057 | $0.00707 |
| Opus 5.5 | $0.00023 | $0.00283 |
| Sonnet 5.5 | $0.00011 | $0.00141 |
| Haiku 4.5 | $0.00006 | $0.00071 |
Grade A, and why
sweep-reds scanned grade A with 0 findings 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 14d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sweep reds: base first, then affected PRs
Read ../_shared/base-green.md and ../_shared/validation-gate.md.
Success means verified required checks, not a disappearing incident or green wrapper.
Boundaries
- Never merge, close PRs or change release-freeze state through this skill.
- Never stash, alter the shared checkout, or touch another session's active worktree.
- Never weaken assertions, expand tolerances, suppress failures or raise a baseline to make a check green. A proven workflow defect requires an explicitly scoped gate-repair task; ordinary sweep authorization does not authorize CI mutation.
- Run live credentialed/paid tests, deployment or trust approvals only with the appropriate owner authorization. Missing access is HOLD, not PASS.
A. Base health
- Resolve live main/release refs and freeze state read-only. Confirm the intended development branch; a frozen branch remains off limits.
- Follow the shared exact-SHA evidence protocol. Closed/missing incidents mean UNKNOWN unless current applicable executions establish PASS. A quick observer receipt is partial; the last incident comment is only a diagnostic worklist.
- Reproduce each signature on an isolated pinned base. Keep setup/install failures separate from assertions. Open one owned branch/worktree per independently reviewable repair, with RED-to-GREEN proof; avoid duplicating another session's PR.
- Prepare/babysit the fix PR under the authorized scope, then hand it to the owner. Do not claim the base is repaired until the fix is integrated and the new exact base passes. The authorized observer, not this skill, manages its incident.
B. PR queue
Inventory requested open PRs and their current head/base/candidate identities. Classify required failure, advisory failure, pending, stale, cancelled and approval needed separately. Work one PR at a time, checking ownership before each mutation.
An inherited label requires the same measured signature on the exact base, not membership in an old incident list. For stale evidence, obtain a newly constructed candidate under the current base; a rerun still uses the original run identity. Updating a contributor branch or approving a fork run needs its own authority.
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.
- 14d ago First seen · 62 lines · 57 tokens per session scan A 7ff04919c452
sweep-reds is a skill published in the GitHub repository diegosouzapw/OmniRoute (77,375 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 707 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-03.
Other skills, from other repositories
test-setup
Scaffold the test framework and CI — tests/ directory, engine test runner, GitHub Actions workflow. Once, before the first sprint.
ci-speedup
Cuts the wait from push to green by measuring a pipeline's critical path from run timestamps, then splitting, sharding, trimming setup and sharing test module state, with a before/after ledger. Use when asked to "speed up CI", "CI is slow", "why does a PR take 15 minutes", "CI is the bottleneck", or when agents merge…
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
audit-harness
Use when auditing HARNESS.md, pre-commit hooks, pre-push hooks, architecture gates, or CI workflows for tunacode-cli. This skill treats any mismatch, skipped gate, or failing check as a critical failure and requires manual one-by-one execution rather than make targets, batch wrappers, or summary-only audits.
github-release-management
GitHub release orchestration — automated versioning, testing, deployment, and rollback. Use when cutting a release, tagging a version, drafting release notes, or coordinating a deploy/rollback workflow.
verification-quality
Truth scoring, code-quality verification, and automatic rollback with a high accuracy threshold. Use when validating agent output before it ships, gating changes on quality, or adding a verify-and-rollback safety loop.