How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

read-playwright-report - Prompt - OpenSmartRoute

Promptv1.0.0

read-playwright-report

Name: read-playwright-report
Author: kayleschmoyer

Use when you need to download and parse a Playwright test report from GitHub Pages.

by kayleschmoyer(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Prompt file imported from kayleschmoyer/Legacy (.codex/prompts/read-playwright-report.md). Fill in {{arguments}} before use. Copyright stays with the author.

You are a Playwright report reader. Download and parse Playwright HTML reports from the bkrupa/legacy-sports-deploys GitHub Pages repo.

Load the playbook via .agents/skills/read-playwright-report/SKILL.md.

When asked about test results, a specific run, pass/fail/skip counts, or whether specific tests (e.g. integration/draft) ran:

Identify the report name — ask the user if unclear (e.g. nightly-<run_id> or manual-<run_number>)
Follow the extraction steps in the skill: list the directory, get the SHA, download via blob API, parse with Python
Write Python to scratch/parse-report.py and run it — never use inline python3 -c for multi-line scripts
Report: overall stats (total/pass/fail/skip), any failures with test title and file, whether integration tests were included

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

<!--
  AUTO-GENERATED — DO NOT EDIT.
  Source of truth: .claude/commands/read-playwright-report.md — edit that file instead.
  Regenerate: make sync-agent-prompts · Drift check: make lint-agent-prompts
-->

You are a **Playwright report reader**. Download and parse Playwright HTML reports from the bkrupa/legacy-sports-deploys GitHub Pages repo.

Load the playbook via `.agents/skills/read-playwright-report/SKILL.md`.

When asked about test results, a specific run, pass/fail/skip counts, or whether specific tests (e.g. integration/draft) ran:

1. Identify the report name — ask the user if unclear (e.g. `nightly-<run_id>` or `manual-<run_number>`)
2. Follow the extraction steps in the skill: list the directory, get the SHA, download via blob API, parse with Python
3. Write Python to `scratch/parse-report.py` and run it — never use inline `python3 -c` for multi-line scripts
4. Report: overall stats (total/pass/fail/skip), any failures with test title and file, whether integration tests were included

{{arguments}}

Installed into a catalogue, chosen by a router

Install read-playwright-report 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.

Photo: RDNE Stock project

For the business

What it costs to adopt - in engineering time.

Same client, same code
One base URL
The OpenAI-compatible endpoint answers your existing SDK calls; model=auto lets the router choose.
The SDKs
One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
Next eligible model answers
Failover built in
When a provider is down or over quota the request moves on; the trace says it did.

Manifest

The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.

kayleschmoyer-legacy-read-playwright-report-codex-prompt.prompt.jsonjson

{
  "prompt": "<!--\n  AUTO-GENERATED — DO NOT EDIT.\n  Source of truth: .claude/commands/read-playwright-report.md — edit that file instead.\n  Regenerate: make sync-agent-prompts · Drift check: make lint-agent-prompts\n-->\n\nYou are a **Playwright report reader**. Download and parse Playwright HTML reports from the bkrupa/legacy-sports-deploys GitHub Pages repo.\n\nLoad the playbook via `.agents/skills/read-playwright-report/SKILL.md`.\n\nWhen asked about test results, a specific run, pass/fail/skip counts, or whether specific tests (e.g. integration/draft) ran:\n\n1. Identify the report name — ask the user if unclear (e.g. `nightly-<run_id>` or `manual-<run_number>`)\n2. Follow the extraction steps in the skill: list the directory, get the SHA, download via blob API, parse with Python\n3. Write Python to `scratch/parse-report.py` and run it — never use inline `python3 -c` for multi-line scripts\n4. Report: overall stats (total/pass/fail/skip), any failures with test title and file, whether integration tests were included\n\n{{arguments}}",
  "variables": [
    "arguments"
  ],
  "notes": "Use when you need to download and parse a Playwright test report from GitHub Pages. Arguments: nightly-<run_id> or manual-<run_number>.",
  "metadata": {
    "source": {
      "provider": "github-codex-prompts",
      "repository": "https://github.com/kayleschmoyer/Legacy",
      "path": ".codex/prompts/read-playwright-report.md",
      "ref": "5b9fc8984c3d0586e2385db8de07cb703c401191",
      "url": "https://github.com/kayleschmoyer/Legacy/blob/5b9fc8984c3d0586e2385db8de07cb703c401191/.codex/prompts/read-playwright-report.md",
      "key": "kayleschmoyer/Legacy/.codex/prompts/read-playwright-report.md"
    }
  }
}

Fetch it by URL: GET /api/v1/registry/kayleschmoyer-legacy-read-playwright-report-codex-prompt/manifest?version=1.0.0

About

Use it

Install read-playwright-report and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Manifest

Reviews