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.

gsd/resume-task - Prompt - OpenSmartRoute

Name: gsd/resume-task
Author: heyaryansingh

Prompt file imported from heyaryansingh/get-shit-done-cursor (.cursor/commands/gsd/resume-task.md). Fill in {{arguments}} before use. Copyright stays with the author.

When a session ends mid-execution, subagents may be left in an incomplete state. This command allows users to continue that work without starting over.

Uses the agent ID tracking infrastructure from execute-plan to identify and resume agents.

<execution_context> @./.cursor/get-shit-done/workflows/resume-task.md </execution_context>

Load project state: @.planning/STATE.md

Load agent tracking: @.planning/current-agent-id.txt @.planning/agent-history.json

Resume specific agent by ID:

/gsd/resume-task agent_01HXYZ123

Find available agents to resume: Check .planning/agent-history.json for entries with status "spawned" or "interrupted".

<error_handling> No agent to resume:

current-agent-id.txt empty or missing
Solution: Run /gsd/progress to check project status

Agent already completed:

Agent finished successfully, nothing to resume
Solution: Continue with next plan

Agent not found:

Provided ID not in history
Solution: Check agent-history.json for valid IDs

Resume failed:

Agent context expired or invalidated
Solution: Start fresh with /gsd/execute-plan </error_handling>

<success_criteria>

Agent resumed via Task tool resume parameter
Agent-history.json updated with completion
current-agent-id.txt cleared
User informed of result </success_criteria>

Install gsd/resume-task 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.

<objective> Resume an interrupted subagent execution using the Task tool's resume parameter. When a session ends mid-execution, subagents may be left in an incomplete state. This command allows users to continue that work without starting over. Uses the agent ID tracking infrastructure from execute-plan to identify and resume agents. </objective> <execution_context> @./.cursor/get-shit-done/workflows/resume-task.md </execution_context> <context> Agent ID: {{arguments}} (optional - defaults to most recent) **Load project state:** @.planning/STATE.md **Load agent tracking:** @.planning/current-agent-id.txt @.planning/agent-history.json </context> <process> 1. Check .planning/ directory exists (error if not) 2. Parse agent ID from arguments or current-agent-id.txt 3. Validate agent exists in history and is resumable 4. Check for file conflicts since spawn 5. Follow resume-task.md workflow: - Update agent status to "interrupted" - Resume via Task tool resume parameter - Update history on completion - Clear current-agent-id.txt </process> <usage> **Resume most recent interrupted agent:** ``` /gsd/resume-task ``` **Resume specific agent by ID:** ``` /gsd/resume-task agent_01HXYZ123 ``` **Find available agents to resume:** Check `.planning/agent-history.json` for entries with status "spawned" or "interrupted". </usage> <error_handling> **No agent to resume:** - current-agent-id.txt empty or missing - Solution: Run /gsd/progress to check project status **Agent already completed:** - Agent finished successfully, nothing to resume - Solution: Continue with next plan **Agent not found:** - Provided ID not in history - Solution: Check agent-history.json for valid IDs **Resume failed:** - Agent context expired or invalidated - Solution: Start fresh with /gsd/execute-plan </error_handling> <success_criteria> - [ ] Agent resumed via Task tool resume parameter - [ ] Agent-history.json updated with completion - [ ] current-agent-id.txt cleared - [ ] User informed of result </success_criteria>

{ "prompt": "<objective>\nResume an interrupted subagent execution using the Task tool's resume parameter.\n\nWhen a session ends mid-execution, subagents may be left in an incomplete state. This command allows users to continue that work without starting over.\n\nUses the agent ID tracking infrastructure from execute-plan to identify and resume agents.\n</objective>\n\n<execution_context>\n@./.cursor/get-shit-done/workflows/resume-task.md\n</execution_context>\n\n<context>\nAgent ID: {{arguments}} (optional - defaults to most recent)\n\n**Load project state:**\n@.planning/STATE.md\n\n**Load agent tracking:**\n@.planning/current-agent-id.txt\n@.planning/agent-history.json\n</context>\n\n<process>\n1. Check .planning/ directory exists (error if not)\n2. Parse agent ID from arguments or current-agent-id.txt\n3. Validate agent exists in history and is resumable\n4. Check for file conflicts since spawn\n5. Follow resume-task.md workflow:\n - Update agent status to \"interrupted\"\n - Resume via Task tool resume parameter\n - Update history on completion\n - Clear current-agent-id.txt\n</process>\n\n<usage>\n**Resume most recent interrupted agent:**\n```\n/gsd/resume-task\n```\n\n**Resume specific agent by ID:**\n```\n/gsd/resume-task agent_01HXYZ123\n```\n\n**Find available agents to resume:**\nCheck `.planning/agent-history.json` for entries with status \"spawned\" or \"interrupted\".\n</usage>\n\n<error_handling>\n**No agent to resume:**\n- current-agent-id.txt empty or missing\n- Solution: Run /gsd/progress to check project status\n\n**Agent already completed:**\n- Agent finished successfully, nothing to resume\n- Solution: Continue with next plan\n\n**Agent not found:**\n- Provided ID not in history\n- Solution: Check agent-history.json for valid IDs\n\n**Resume failed:**\n- Agent context expired or invalidated\n- Solution: Start fresh with /gsd/execute-plan\n</error_handling>\n\n<success_criteria>\n- [ ] Agent resumed via Task tool resume parameter\n- [ ] Agent-history.json updated with completion\n- [ ] current-agent-id.txt cleared\n- [ ] User informed of result\n</success_criteria>", "variables": [ "arguments" ], "notes": "Resume an interrupted subagent execution Tools: Read, Write, Edit, Bash, Task, AskUserQuestion. Arguments: [agent-id].", "metadata": { "source": { "provider": "github-cursor-commands", "repository": "https://github.com/heyaryansingh/get-shit-done-cursor", "path": ".cursor/commands/gsd/resume-task.md", "ref": "2af88ef3a752a13420d25023b351561ecbd9f78f", "url": "https://github.com/heyaryansingh/get-shit-done-cursor/blob/2af88ef3a752a13420d25023b351561ecbd9f78f/.cursor/commands/gsd/resume-task.md", "key": "heyaryansingh/get-shit-done-cursor/.cursor/commands/gsd/resume-task.md" } } }

gsd/resume-task

About

Use it

Install gsd/resume-task 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