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.

run-plan - Prompt - OpenSmartRoute

Name: run-plan
Author: agent-kit-startup

Prompt file imported from agent-kit-startup/agent-kit (.cursor/commands/run-plan.md). Copyright stays with the author.

Command: /run-plan

Goal

Run the active plan continuously until it is done or blocked. The agent picks the strategy (orchestrated when Task exists, in-session loop otherwise, headless agent-kit run-plan). Never /git-prod from this command.

HITL contract, exact Ask labels, numbered fallback (path 1): hitl-gates. Full tick contract: run-plan-tick-contract.md.

Hard stops (kit failure if skipped)

Never /git-prod. Suggest it only after Final HANDOFF when staging is ahead of main (separate HITL).
One to-do per tick. Mark in_progress before work. Never stack the next to-do.
Risk / API-limit stop. PII, secrets, or ambiguous scope: Ask the risk labels. Quota or Task abort: revert the to-do to pending, HANDOFF the stop, do not reschedule or silent-inline.
One Ask on the default path. Inbox, owed-close, and landing Asks are opt-in or post-default, never pre-Ask blockers. Empty inbox: silent skip. Skip the inbox Ask inside a /run-plan-all per-plan Task.
Exhaustion audits do not steal /git-prod. Exit 3 is timeout-only and does not retroactively convert, upgrade, or rewrite a later monitor into success.

Ask labels

Gate	Labels
Risk	`Continue with risk` / `Modify approach` / `Stop run`
Inbox (post-default)	`Analyze inbox now` / `Enqueue Fix now` / `Not now`
Exhaustion (post-default)	`Run review now` / `Always enable automatic` / `Not now`
Owed-close (post-default)	`Adopt existing monitor` / `Ack owed without review` / `Not now`
Pending ticket (preflight, id `ticket`)	`Read the ticket` / `Accept` / `Discard` / `Later`

Numbered-list fallback is path 1 when Ask questions is missing.

Procedure

Read HANDOFF + plan + config. Preflight API-limit stop, pending operator ticket (Ask ticket only while .cursor/context/gate-exit.json has a pending entry; inside a /run-plan-all Task or --no-hitl, list the stamps instead: pending-ticket.md), audits, unsatisfiable Claude reviewer, session-pile. Read a product-context extract when the plan points at one.
Next pending to-do. force_task: true or findings → Task. Lightweight docs-only → inline-first. Else Task or in-session.
Execute only that to-do. Findings-only for review-*. autoRemediate default false: no silent product fix.
Close: plan status, HANDOFF, cadence bump, /git-staging on a commitable diff. Staging ready: yes requires lint evidence (or none applicable). Dashboard HTML: none applicable (dashboard-CSS) covered by plugin-ux-validation. Contract string alone without that evidence is invalid.
Reschedule or stop (blocker, exhausted, user stop, API limit). Never /git-prod.

Persona chrome (agentPersona.modes.run-plan) after the command Ask, not instead of HITL. Default chat chrome: no cockpit emoji.

Install run-plan 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.

# Command: /run-plan ## Goal Run the **active plan** continuously until it is done or blocked. The agent picks the strategy (orchestrated when Task exists, in-session loop otherwise, headless `agent-kit run-plan`). Never `/git-prod` from this command. HITL contract, exact Ask labels, numbered fallback (path 1): [hitl-gates](../skills/core/hitl-gates/SKILL.md). Full tick contract: [run-plan-tick-contract.md](../skills/core/hitl-gates/run-plan-tick-contract.md). ## Hard stops (kit failure if skipped) 1. **Never `/git-prod`.** Suggest it only after Final HANDOFF when staging is ahead of `main` (separate HITL). 2. **One to-do per tick.** Mark `in_progress` before work. Never stack the next to-do. 3. **Risk / API-limit stop.** PII, secrets, or ambiguous scope: Ask the risk labels. Quota or Task abort: revert the to-do to `pending`, HANDOFF the stop, do not reschedule or silent-inline. 4. **One Ask on the default path.** Inbox, owed-close, and landing Asks are opt-in or post-default, never pre-Ask blockers. Empty inbox: silent skip. Skip the inbox Ask inside a `/run-plan-all` per-plan Task. 5. **Exhaustion audits do not steal `/git-prod`.** Exit `3` is timeout-only and does not retroactively convert, upgrade, or rewrite a later monitor into success. ## Ask labels | Gate | Labels | |------|--------| | Risk | `Continue with risk` / `Modify approach` / `Stop run` | | Inbox (post-default) | `Analyze inbox now` / `Enqueue Fix now` / `Not now` | | Exhaustion (post-default) | `Run review now` / `Always enable automatic` / `Not now` | | Owed-close (post-default) | `Adopt existing monitor` / `Ack owed without review` / `Not now` | | Pending ticket (preflight, id `ticket`) | `Read the ticket` / `Accept` / `Discard` / `Later` | Numbered-list fallback is **path 1** when Ask questions is missing. ## Procedure 1. Read HANDOFF + plan + config. Preflight API-limit stop, pending operator ticket (Ask `ticket` only while `.cursor/context/gate-exit.json` has a pending entry; inside a `/run-plan-all` Task or `--no-hitl`, list the stamps instead: [pending-ticket.md](../skills/core/hitl-gates/pending-ticket.md)), audits, unsatisfiable Claude reviewer, session-pile. Read a product-context extract when the plan points at one. 2. Next pending to-do. `force_task: true` or findings → Task. Lightweight docs-only → inline-first. Else Task or in-session. 3. Execute only that to-do. Findings-only for `review-*`. `autoRemediate` default false: no silent product fix. 4. Close: plan status, HANDOFF, cadence bump, `/git-staging` on a commitable diff. Staging ready: yes requires lint evidence (or `none applicable`). Dashboard HTML: `none applicable (dashboard-CSS)` covered by plugin-ux-validation. Contract string alone without that evidence is invalid. 5. Reschedule or stop (blocker, exhausted, user stop, API limit). Never `/git-prod`. Persona chrome (`agentPersona.modes.run-plan`) after the command Ask, not instead of HITL. Default chat chrome: no cockpit emoji.

{ "prompt": "# Command: /run-plan\n\n## Goal\n\nRun the **active plan** continuously until it is done or blocked. The agent picks the strategy (orchestrated when Task exists, in-session loop otherwise, headless `agent-kit run-plan`). Never `/git-prod` from this command.\n\nHITL contract, exact Ask labels, numbered fallback (path 1): [hitl-gates](../skills/core/hitl-gates/SKILL.md). Full tick contract: [run-plan-tick-contract.md](../skills/core/hitl-gates/run-plan-tick-contract.md).\n\n## Hard stops (kit failure if skipped)\n\n1. **Never `/git-prod`.** Suggest it only after Final HANDOFF when staging is ahead of `main` (separate HITL).\n2. **One to-do per tick.** Mark `in_progress` before work. Never stack the next to-do.\n3. **Risk / API-limit stop.** PII, secrets, or ambiguous scope: Ask the risk labels. Quota or Task abort: revert the to-do to `pending`, HANDOFF the stop, do not reschedule or silent-inline.\n4. **One Ask on the default path.** Inbox, owed-close, and landing Asks are opt-in or post-default, never pre-Ask blockers. Empty inbox: silent skip. Skip the inbox Ask inside a `/run-plan-all` per-plan Task.\n5. **Exhaustion audits do not steal `/git-prod`.** Exit `3` is timeout-only and does not retroactively convert, upgrade, or rewrite a later monitor into success.\n\n## Ask labels\n\n| Gate | Labels |\n|------|--------|\n| Risk | `Continue with risk` / `Modify approach` / `Stop run` |\n| Inbox (post-default) | `Analyze inbox now` / `Enqueue Fix now` / `Not now` |\n| Exhaustion (post-default) | `Run review now` / `Always enable automatic` / `Not now` |\n| Owed-close (post-default) | `Adopt existing monitor` / `Ack owed without review` / `Not now` |\n| Pending ticket (preflight, id `ticket`) | `Read the ticket` / `Accept` / `Discard` / `Later` |\n\nNumbered-list fallback is **path 1** when Ask questions is missing.\n\n## Procedure\n\n1. Read HANDOFF + plan + config. Preflight API-limit stop, pending operator ticket (Ask `ticket` only while `.cursor/context/gate-exit.json` has a pending entry; inside a `/run-plan-all` Task or `--no-hitl`, list the stamps instead: [pending-ticket.md](../skills/core/hitl-gates/pending-ticket.md)), audits, unsatisfiable Claude reviewer, session-pile. Read a product-context extract when the plan points at one.\n2. Next pending to-do. `force_task: true` or findings → Task. Lightweight docs-only → inline-first. Else Task or in-session.\n3. Execute only that to-do. Findings-only for `review-*`. `autoRemediate` default false: no silent product fix.\n4. Close: plan status, HANDOFF, cadence bump, `/git-staging` on a commitable diff. Staging ready: yes requires lint evidence (or `none applicable`). Dashboard HTML: `none applicable (dashboard-CSS)` covered by plugin-ux-validation. Contract string alone without that evidence is invalid.\n5. Reschedule or stop (blocker, exhausted, user stop, API limit). Never `/git-prod`.\n\nPersona chrome (`agentPersona.modes.run-plan`) after the command Ask, not instead of HITL. Default chat chrome: no cockpit emoji.", "variables": [], "notes": "Run the active plan continuously until it is done or blocked, picking the execution strategy automatically.", "metadata": { "source": { "provider": "github-cursor-commands", "repository": "https://github.com/agent-kit-startup/agent-kit", "path": ".cursor/commands/run-plan.md", "ref": "043e48ba345344396fe6c627d785ec516283dde7", "url": "https://github.com/agent-kit-startup/agent-kit/blob/043e48ba345344396fe6c627d785ec516283dde7/.cursor/commands/run-plan.md", "key": "agent-kit-startup/agent-kit/.cursor/commands/run-plan.md" } } }

run-plan

About

Command: /run-plan

Goal

Hard stops (kit failure if skipped)

Ask labels

Procedure

Install run-plan 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

Use it

Manifest

Reviews