Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
ek-verify - Skill - OpenSmartRoute
Skillv1.0.0
ek-verify
Plan and record exact-head test and security evidence without bypassing native gates.
Imported from AlexandrShapkin/codex-smart (.engineering-kit/skills/ek-verify/SKILL.md). Install upstream with npx skills add AlexandrShapkin/codex-smart --skill ek-verify. Copyright stays with the author.
Verification evidence
Instruction-only; does not run tests or deploy. Preserve the project's own targeted, native, CI, security and platform gates. Smoke and contract checks alone are insufficient. Before running any tool confirm side effects, installation and target output path; RelayForge's legacy live Cargo path must not be overwritten. Record actual commands, outcomes and complete PR HEAD SHA. Separate PASS, FAIL, BLOCKED and UNVERIFIED. Do not treat source CI as live evidence, and recheck after a new commit.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - a plan picks it for its slotcurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'
Installed into a catalogue, chosen by a router
Install ek-verify and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
{
"ocm": "1",
"id": "alexandrshapkin-codex-smart-ek-verify",
"kind": "skill",
"name": "ek-verify",
"description": "Plan and record exact-head test and security evidence without bypassing native gates.",
"publisher": "AlexandrShapkin",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding",
"legal"
],
"tags": [
"skill-md",
"github"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Plan and record exact-head test and security evidence without bypassing native gates."
],
"primary": false,
"metadata": {
"source": {
"provider": "github",
"repository": "https://github.com/AlexandrShapkin/codex-smart",
"path": ".engineering-kit/skills/ek-verify/SKILL.md",
"ref": "6a6647dfbd723378e1351cf4af462475a16a67eb",
"url": "https://github.com/AlexandrShapkin/codex-smart/blob/6a6647dfbd723378e1351cf4af462475a16a67eb/.engineering-kit/skills/ek-verify/SKILL.md",
"key": "AlexandrShapkin/codex-smart/.engineering-kit/skills/ek-verify/SKILL.md"
}
},
"instructions": "# Verification evidence\n\nInstruction-only; does not run tests or deploy. Preserve the project's own targeted, native, CI, security and platform gates. Smoke and contract checks alone are insufficient. Before running any tool confirm side effects, installation and target output path; RelayForge's legacy live Cargo path must not be overwritten. Record actual commands, outcomes and complete PR HEAD SHA. Separate PASS, FAIL, BLOCKED and UNVERIFIED. Do not treat source CI as live evidence, and recheck after a new commit.",
"cost": {
"context_tokens": 130
}
}
Fetch it by URL: GET /api/v1/registry/alexandrshapkin-codex-smart-ek-verify/manifest?version=1.0.0
Reviews
Star ratings from people who tried it. One review per account; edit yours any time.
No reviews yet. Install it, try it, and be the first to rate it.
