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.

fix - Prompt - OpenSmartRoute

Name: fix
Author: OthmanAdi

Prompt file imported from OthmanAdi/MDDesign (.cursor/commands/fix.md). Copyright stays with the author.

/mddesign:fix

Apply one finding's fix from DESIGN.md.critique.md.

Flow

Read the critique: open DESIGN.md.critique.md, find the finding by id. If not found, refuse. If already status: applied, refuse.
Show the proposed change: print the finding and the proposed edit to the user.
HITL gate: the PreToolUse hook intercepts the next Edit (named checkpoint: before_design_md_fix) and waits for approval.
Apply: make the single edit on DESIGN.md (or on the named source file when the fix touches code).
Re-lint: Bash: npx --yes @google/design.md lint DESIGN.md.
- If lint regresses, revert the edit and surface the error.
- If lint passes, proceed.
Update critique: mark the finding status: applied in DESIGN.md.critique.md.
Append to progress.md: "Applied F. DESIGN.md still passes lint."

Arguments

<finding-id> — required. Must match a finding in DESIGN.md.critique.md.

Boundaries

One finding at a time. Never batch-applies.
Always HITL gated.
Always re-lints. Never leaves DESIGN.md in a regressed state.

See skills/design-harvest/SKILL.md for the full logic.

# /mddesign:fix Apply one finding's fix from `DESIGN.md.critique.md`. ## Flow 1. **Read the critique**: open `DESIGN.md.critique.md`, find the finding by id. If not found, refuse. If already `status: applied`, refuse. 2. **Show the proposed change**: print the finding and the proposed edit to the user. 3. **HITL gate**: the PreToolUse hook intercepts the next `Edit` (named checkpoint: `before_design_md_fix`) and waits for approval. 4. **Apply**: make the single edit on `DESIGN.md` (or on the named source file when the fix touches code). 5. **Re-lint**: `Bash: npx --yes @google/design.md lint DESIGN.md`. - If lint regresses, revert the edit and surface the error. - If lint passes, proceed. 6. **Update critique**: mark the finding `status: applied` in `DESIGN.md.critique.md`. 7. **Append to progress.md**: "Applied F<id>. DESIGN.md still passes lint." ## Arguments - `<finding-id>` — required. Must match a finding in `DESIGN.md.critique.md`. ## Boundaries - One finding at a time. Never batch-applies. - Always HITL gated. - Always re-lints. Never leaves DESIGN.md in a regressed state. See skills/design-harvest/SKILL.md for the full logic.

Install fix 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": "# /mddesign:fix\n\nApply one finding's fix from `DESIGN.md.critique.md`.\n\n## Flow\n\n1. **Read the critique**: open `DESIGN.md.critique.md`, find the finding by id. If not found, refuse. If already `status: applied`, refuse.\n\n2. **Show the proposed change**: print the finding and the proposed edit to the user.\n\n3. **HITL gate**: the PreToolUse hook intercepts the next `Edit` (named checkpoint: `before_design_md_fix`) and waits for approval.\n\n4. **Apply**: make the single edit on `DESIGN.md` (or on the named source file when the fix touches code).\n\n5. **Re-lint**: `Bash: npx --yes @google/design.md lint DESIGN.md`.\n - If lint regresses, revert the edit and surface the error.\n - If lint passes, proceed.\n\n6. **Update critique**: mark the finding `status: applied` in `DESIGN.md.critique.md`.\n\n7. **Append to progress.md**: \"Applied F<id>. DESIGN.md still passes lint.\"\n\n## Arguments\n\n- `<finding-id>` — required. Must match a finding in `DESIGN.md.critique.md`.\n\n## Boundaries\n\n- One finding at a time. Never batch-applies.\n- Always HITL gated.\n- Always re-lints. Never leaves DESIGN.md in a regressed state.\n\nSee skills/design-harvest/SKILL.md for the full logic.", "variables": [], "notes": "Apply a single safe quick win from DESIGN.md.critique.md. HITL gated. Re-lints DESIGN.md after every edit; reverts if lint regresses. Tools: Read, Edit, Bash. Arguments: <finding-id>.", "metadata": { "source": { "provider": "github-cursor-commands", "repository": "https://github.com/OthmanAdi/MDDesign", "path": ".cursor/commands/fix.md", "ref": "fb6e6db0c83ed16ca133cc6ebfc8677cce084426", "url": "https://github.com/OthmanAdi/MDDesign/blob/fb6e6db0c83ed16ca133cc6ebfc8677cce084426/.cursor/commands/fix.md", "key": "OthmanAdi/MDDesign/.cursor/commands/fix.md" } } }

fix

About

/mddesign:fix

Flow

Arguments

Boundaries

Use it

Install fix 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