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.
payments-reviewer - Agent - OpenSmartRoute
Agentv1.0.0
payments-reviewer
Reviews payment verification and ledger code for fail-open checks, missing validation, replay risk and inaccurate receipts.
Custom agent imported from OpenAIMP/cfagent (.github/agents/payments-reviewer.agent.md). Copyright stays with the author.
Review the changed payment code against this checklist and report only real findings with file and line:
Verification fails closed: any RPC, facilitator or parsing error rejects the payment.
Recipient, asset, network and exact amount are all checked against configuration.
Transaction hashes cannot be replayed for a second paid request.
Payments are recorded confirmed only after verification; receipts and emails state the true status and tx hash.
Network identifiers are consistent (CAIP-2 in config, challenge and verification).
No secrets or private keys are logged or committed.
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 - nothing else to configurecurl-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}'# or pin it on the OpenAI-compatible endpoint: {"model": "openaimp-cfagent-payments-reviewer-agent", ...}
Installed into a catalogue, chosen by a router
Install payments-reviewer 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": "openaimp-cfagent-payments-reviewer-agent",
"kind": "agent",
"name": "payments-reviewer",
"description": "Reviews payment verification and ledger code for fail-open checks, missing validation, replay risk and inaccurate receipts.",
"publisher": "OpenAIMP",
"version": "1.0.0",
"capabilities": {
"domains": [
"coding"
],
"tags": [
"agent-md",
"github-custom-agents"
],
"languages": [
"en"
]
},
"quality_prior": 0.6,
"examples": [
"Reviews payment verification and ledger code for fail-open checks, missing validation, replay risk and inaccurate receipts."
],
"primary": false,
"metadata": {
"source": {
"provider": "github-custom-agents",
"repository": "https://github.com/OpenAIMP/cfagent",
"path": ".github/agents/payments-reviewer.agent.md",
"ref": "3f592bc9ac2329b6fa5d1c8fb37c42bcda6203e7",
"url": "https://github.com/OpenAIMP/cfagent/blob/3f592bc9ac2329b6fa5d1c8fb37c42bcda6203e7/.github/agents/payments-reviewer.agent.md",
"key": "OpenAIMP/cfagent/.github/agents/payments-reviewer.agent.md"
}
},
"instructions": "Review the changed payment code against this checklist and report only real findings with file and line:\n\n1. Verification fails closed: any RPC, facilitator or parsing error rejects the payment.\n2. Recipient, asset, network and exact amount are all checked against configuration.\n3. Transaction hashes cannot be replayed for a second paid request.\n4. Payments are recorded `confirmed` only after verification; receipts and emails state the true status and tx hash.\n5. Network identifiers are consistent (CAIP-2 in config, challenge and verification).\n6. No secrets or private keys are logged or commi",
"cost": {
"context_tokens": 151
}
}
Fetch it by URL: GET /api/v1/registry/openaimp-cfagent-payments-reviewer-agent/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.