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 merge-prsgit 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/merge-prs)<a href="https://agentmods.dev/skills/diegosouzapw/omniroute/merge-prs"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/merge-prs/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/merge-prs"><img src="https://agentmods.dev/badge/skills/diegosouzapw/omniroute/merge-prs.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 | $0.00047 | $0.01006 |
| Opus 5.5 | $0.00019 | $0.00402 |
| Sonnet 5.5 | $0.00009 | $0.00201 |
| Haiku 4.5 | $0.00005 | $0.00101 |
Grade A, and why
merge-prs 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 13d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute analyzed PR plans
Read ../_shared/base-green.md, ../_shared/validation-gate.md,
../_shared/merge-gates.md, ../_shared/protected-surfaces.md and
../_shared/credit-preservation.md before execution. Their authority and evidence
boundaries apply throughout; no throughput exception waives required checks.
1. Reconcile and choose
Refresh live PR states/heads/bases, worktree ownership, freeze state and existing
plans under _tasks/pipeline/prs/1-analyzed/. Preserve other sessions' claims.
No plan means return to review; an explicit owner request for inline review may
authorize a bounded mini-analysis, not skip validation or merge authorization.
Present the organization report by readiness and contributor/theme, including review rating, scope, risks, mandatory fixes and recommendation. Sound ideas that need substantial work may be offered for uplift; do not dispatch it without the owner's choice. The owner selects the items/groups, then receives a merge dossier: what enters, leaves or changes; authorship; dependencies; validation; risks; rollback; order and final candidate identity. Obtain explicit authorization for that group. General permission to continue development is not merge permission. An explicit owner instruction naming PRs and requesting their merge can satisfy the selection/dossier decision; record the scope, but retain all safety gates.
Claim only selected eligible plans via the pipeline's atomic move into
2-implementing/; if another session wins, stop that item. Stage owned paths only
in the separate private _tasks repo and regenerate its index when appropriate.
Merged items go to 3-done/ with actual evidence; closed/unmerged items are not
reported as delivered. Age alone does not establish that a claim is abandoned.
2. Repair without losing credit
Create an isolated worktree at the observed contributor head. Verify identity before changing anything and recheck the remote predecessor before every push. Implement only the approved mandatory items, with RED-to-GREEN proof and affected suites. Preserve original authorship and appropriate maintainer co-authorship. Do not stash, reset a contributor branch, overwrite unrelated edits or force-push over concurrent work. Reconstruct only in a separate recovery branch after owner review; locked forks follow the credit-preservation protocol and stay open.
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.
- 13d ago First seen · 85 lines · 47 tokens per session scan A 8990df4e9d26
merge-prs is a skill published in the GitHub repository diegosouzapw/OmniRoute (77,028 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 1,006 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
babysit
Watch a pull request or review cycle until it is ready to merge. Use when asked to babysit, monitor, or keep checking PR comments, reviews, and CI until all actionable issues are resolved.
code-review
Review the current diff, or a PR number/branch/path target, for correctness bugs (plus reuse/simplification/efficiency cleanups where the model's review recipe covers them) at the given effort level (low|medium|high|xhigh|max: from few high-confidence findings up to many, some of them uncertain; ultra: deep…
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
pr-review
Review open PRs two ways - default is a per-PR deep review with severity-tagged findings, inline comments, and a verdict; --survey runs a risk-tiered triage digest of what's safe to merge first.