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.
Prompt file imported from drmrd/vernacular (.claude/commands/clean-code-review.md). Copyright stays with the author.
/clean-code-review
Dispatch the clean-code-reviewer subagent to audit the most recent commit (or the range you pass) against .claude/rules.md. The reviewer produces a structured report with must-fix, should-fix, and consider findings.
Use this in the BLUE phase of the red-green-blue cycle, immediately after /implement and before /refactor.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# /clean-code-review
Dispatch the `clean-code-reviewer` subagent to audit the most recent commit (or the range you pass) against `.claude/rules.md`. The reviewer produces a structured report with must-fix, should-fix, and consider findings.
Use this in the BLUE phase of the red-green-blue cycle, immediately after `/implement` and before `/refactor`.
Manifest
The prompt text and its fill-in variables. Copy it or fetch it by URL from your own code.
Installed into a catalogue, chosen by a router
Install clean-code-review 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.
{
"prompt": "# /clean-code-review\n\nDispatch the `clean-code-reviewer` subagent to audit the most recent commit (or the range you pass) against `.claude/rules.md`. The reviewer produces a structured report with must-fix, should-fix, and consider findings.\n\nUse this in the BLUE phase of the red-green-blue cycle, immediately after `/implement` and before `/refactor`.",
"variables": [],
"notes": "Dispatch the clean-code-reviewer agent Tools: Task. Arguments: [optional commit range, defaults to HEAD~1..HEAD].",
"metadata": {
"source": {
"provider": "github-claude-commands",
"repository": "https://github.com/drmrd/vernacular",
"path": ".claude/commands/clean-code-review.md",
"ref": "c788d0b25ced47a7ba049c92bc035db62e0ca0df",
"url": "https://github.com/drmrd/vernacular/blob/c788d0b25ced47a7ba049c92bc035db62e0ca0df/.claude/commands/clean-code-review.md",
"key": "drmrd/vernacular/.claude/commands/clean-code-review.md"
}
}
}
Fetch it by URL: GET /api/v1/registry/drmrd-vernacular-clean-code-review-command/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.