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:verify-work - Prompt - OpenSmartRoute

Name: gsd:verify-work
Author: tumma72

Prompt file imported from tumma72/mlx-manager (.claude/commands/gsd/verify-work.md). Fill in {{arguments}} before use. Copyright stays with the author.

Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.

Output: {phase}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase

<execution_context> @.claude/get-shit-done/workflows/verify-work.md @.claude/get-shit-done/templates/UAT.md </execution_context>

@.planning/STATE.md @.planning/ROADMAP.md

<anti_patterns>

Don't use AskUserQuestion for test responses — plain text conversation
Don't ask severity — infer from description
Don't present full checklist upfront — one test at a time
Don't run automated tests — this is manual user validation
Don't fix issues during testing — log as gaps, diagnose after all tests complete </anti_patterns>

<offer_next> Output this markdown directly (not as a code block). Route based on UAT results:

Status	Route
All tests pass + more phases	Route A (next phase)
All tests pass + last phase	Route B (milestone complete)
Issues found + fix plans ready	Route C (execute fixes)
Issues found + planning blocked	Route D (manual intervention)

Route A: All tests pass, more phases remain

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} VERIFIED ✓ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Phase {Z}: {Name}

{N}/{N} tests passed UAT complete ✓

───────────────────────────────────────────────────────────────

▶ Next Up

Phase {Z+1}: {Name} — {Goal from ROADMAP.md}

/gsd:discuss-phase {Z+1} — gather context and clarify approach

/clear first → fresh context window

───────────────────────────────────────────────────────────────

Also available:

/gsd:plan-phase {Z+1} — skip discussion, plan directly
/gsd:execute-phase {Z+1} — skip to execution (if already planned)

───────────────────────────────────────────────────────────────

Route B: All tests pass, milestone complete

Phase {Z}: {Name}

{N}/{N} tests passed Final phase verified ✓

───────────────────────────────────────────────────────────────

▶ Next Up

Audit milestone — verify requirements, cross-phase integration, E2E flows

/gsd:audit-milestone

/clear first → fresh context window

───────────────────────────────────────────────────────────────

Also available:

/gsd:complete-milestone — skip audit, archive directly

───────────────────────────────────────────────────────────────

Route C: Issues found, fix plans ready

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} ISSUES FOUND ⚠ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Phase {Z}: {Name}

{N}/{M} tests passed {X} issues diagnosed Fix plans verified ✓

Issues Found

{List issues with severity from UAT.md}

───────────────────────────────────────────────────────────────

▶ Next Up

Execute fix plans — run diagnosed fixes

/gsd:execute-phase {Z} --gaps-only

/clear first → fresh context window

───────────────────────────────────────────────────────────────

Also available:

cat .planning/phases/{phase_dir}/*-PLAN.md — review fix plans
/gsd:plan-phase {Z} --gaps — regenerate fix plans

───────────────────────────────────────────────────────────────

Route D: Issues found, planning blocked

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} BLOCKED ✗ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Phase {Z}: {Name}

{N}/{M} tests passed Fix planning blocked after {X} iterations

Unresolved Issues

{List blocking issues from planner/checker output}

───────────────────────────────────────────────────────────────

▶ Next Up

Manual intervention required

Review the issues above and either:

Provide guidance for fix planning
Manually address blockers
Accept current state and continue

───────────────────────────────────────────────────────────────

Options:

/gsd:plan-phase {Z} --gaps — retry fix planning with guidance
/gsd:discuss-phase {Z} — gather more context before replanning

─────────────────────────────────────────────────────────────── </offer_next>

<success_criteria>

<objective> Validate built features through conversational testing with persistent state. Purpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution. Output: {phase}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase </objective> <execution_context> @.claude/get-shit-done/workflows/verify-work.md @.claude/get-shit-done/templates/UAT.md </execution_context> <context> Phase: {{arguments}} (optional) - If provided: Test specific phase (e.g., "4") - If not provided: Check for active sessions or prompt for phase @.planning/STATE.md @.planning/ROADMAP.md </context> <process> 1. Check for active UAT sessions (resume or start new) 2. Find SUMMARY.md files for the phase 3. Extract testable deliverables (user-observable outcomes) 4. Create {phase}-UAT.md with test list 5. Present tests one at a time: - Show expected behavior - Wait for plain text response - "yes/y/next" = pass, anything else = issue (severity inferred) 6. Update UAT.md after each response 7. On completion: commit, present summary 8. If issues found: - Spawn parallel debug agents to diagnose root causes - Spawn gsd-planner in --gaps mode to create fix plans - Spawn gsd-plan-checker to verify fix plans - Iterate planner ↔ checker until plans pass (max 3) - Present ready status with `/clear` then `/gsd:execute-phase` </process> <anti_patterns> - Don't use AskUserQuestion for test responses — plain text conversation - Don't ask severity — infer from description - Don't present full checklist upfront — one test at a time - Don't run automated tests — this is manual user validation - Don't fix issues during testing — log as gaps, diagnose after all tests complete </anti_patterns> <offer_next> Output this markdown directly (not as a code block). Route based on UAT results: | Status | Route | |--------|-------| | All tests pass + more phases | Route A (next phase) | | All tests pass + last phase | Route B (milestone complete) | | Issues found + fix plans ready | Route C (execute fixes) | | Issues found + planning blocked | Route D (manual intervention) | --- **Route A: All tests pass, more phases remain** ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} VERIFIED ✓ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ **Phase {Z}: {Name}** {N}/{N} tests passed UAT complete ✓ ─────────────────────────────────────────────────────────────── ## ▶ Next Up **Phase {Z+1}: {Name}** — {Goal from ROADMAP.md} /gsd:discuss-phase {Z+1} — gather context and clarify approach /clear first → fresh context window ─────────────────────────────────────────────────────────────── **Also available:** - /gsd:plan-phase {Z+1} — skip discussion, plan directly - /gsd:execute-phase {Z+1} — skip to execution (if already planned) ─────────────────────────────────────────────────────────────── --- **Route B: All tests pass, milestone complete** ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} VERIFIED ✓ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ **Phase {Z}: {Name}** {N}/{N} tests passed Final phase verified ✓ ─────────────────────────────────────────────────────────────── ## ▶ Next Up **Audit milestone** — verify requirements, cross-phase integration, E2E flows /gsd:audit-milestone /clear first → fresh context window ─────────────────────────────────────────────────────────────── **Also available:** - /gsd:complete-milestone — skip audit, archive directly ─────────────────────────────────────────────────────────────── --- **Route C: Issues found, fix plans ready** ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} ISSUES FOUND ⚠ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ **Phase {Z}: {Name}** {N}/{M} tests passed {X} issues diagnosed Fix plans verified ✓ ### Issues Found {List issues with severity from UAT.md} ─────────────────────────────────────────────────────────────── ## ▶ Next Up **Execute fix plans** — run diagnosed fixes /gsd:execute-phase {Z} --gaps-only /clear first → fresh context window ─────────────────────────────────────────────────────────────── **Also available:** - cat .planning/phases/{phase_dir}/*-PLAN.md — review fix plans - /gsd:plan-phase {Z} --gaps — regenerate fix plans ─────────────────────────────────────────────────────────────── --- **Route D: Issues found, planning blocked** ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ GSD ► PHASE {Z} BLOCKED ✗ ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ **Phase {Z}: {Name}** {N}/{M} tests passed Fix planning blocked after {X} iterations ### Unresolved Issues {List blocking issues from planner/checker output} ─────────────────────────────────────────────────────────────── ## ▶ Next Up **Manual intervention required** Review the issues above and either: 1. Provide guidance for fix planning 2. Manually address blockers 3. Accept current state and continue ─────────────────────────────────────────────────────────────── **Options:** - /gsd:plan-phase {Z} --gaps — retry fix planning with guidance - /gsd:discuss-phase {Z} — gather more context before replanning ─────────────────────────────────────────────────────────────── </offer_next> <success_criteria> - [ ] UAT.md created with tests from SUMMARY.md - [ ] Tests presented one at a time with expected behavior - [ ] Plain text responses (no structured forms) - [ ] Severity inferred, never asked - [ ] Batched writes: on issue, every 5 passes, or completion - [ ] Committed on completion - [ ] If issues: parallel debug agents diagnose root causes - [ ] If issues: gsd-planner creates fix plans from diagnosed gaps - [ ] If issues: gsd-plan-checker verifies fix plans (max 3 iterations) - [ ] Ready for `/gsd:execute-phase` when complete </success_criteria>

{ "prompt": "<objective>\nValidate built features through conversational testing with persistent state.\n\nPurpose: Confirm what Claude built actually works from user's perspective. One test at a time, plain text responses, no interrogation. When issues are found, automatically diagnose, plan fixes, and prepare for execution.\n\nOutput: {phase}-UAT.md tracking all test results. If issues found: diagnosed gaps, verified fix plans ready for /gsd:execute-phase\n</objective>\n\n<execution_context>\n@.claude/get-shit-done/workflows/verify-work.md\n@.claude/get-shit-done/templates/UAT.md\n</execution_context>\n\n<context>\nPhase: {{arguments}} (optional)\n- If provided: Test specific phase (e.g., \"4\")\n- If not provided: Check for active sessions or prompt for phase\n\n@.planning/STATE.md\n@.planning/ROADMAP.md\n</context>\n\n<process>\n1. Check for active UAT sessions (resume or start new)\n2. Find SUMMARY.md files for the phase\n3. Extract testable deliverables (user-observable outcomes)\n4. Create {phase}-UAT.md with test list\n5. Present tests one at a time:\n - Show expected behavior\n - Wait for plain text response\n - \"yes/y/next\" = pass, anything else = issue (severity inferred)\n6. Update UAT.md after each response\n7. On completion: commit, present summary\n8. If issues found:\n - Spawn parallel debug agents to diagnose root causes\n - Spawn gsd-planner in --gaps mode to create fix plans\n - Spawn gsd-plan-checker to verify fix plans\n - Iterate planner ↔ checker until plans pass (max 3)\n - Present ready status with `/clear` then `/gsd:execute-phase`\n</process>\n\n<anti_patterns>\n- Don't use AskUserQuestion for test responses — plain text conversation\n- Don't ask severity — infer from description\n- Don't present full checklist upfront — one test at a time\n- Don't run automated tests — this is manual user validation\n- Don't fix issues during testing — log as gaps, diagnose after all tests complete\n</anti_patterns>\n\n<offer_next>\nOutput this markdown directly (not as a code block). Route based on UAT results:\n\n| Status | Route |\n|--------|-------|\n| All tests pass + more phases | Route A (next phase) |\n| All tests pass + last phase | Route B (milestone complete) |\n| Issues found + fix plans ready | Route C (execute fixes) |\n| Issues found + planning blocked | Route D (manual intervention) |\n\n---\n\n**Route A: All tests pass, more phases remain**\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n GSD ► PHASE {Z} VERIFIED ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n**Phase {Z}: {Name}**\n\n{N}/{N} tests passed\nUAT complete ✓\n\n───────────────────────────────────────────────────────────────\n\n## ▶ Next Up\n\n**Phase {Z+1}: {Name}** — {Goal from ROADMAP.md}\n\n/gsd:discuss-phase {Z+1} — gather context and clarify approach\n\n/clear first → fresh context window\n\n───────────────────────────────────────────────────────────────\n\n**Also available:**\n- /gsd:plan-phase {Z+1} — skip discussion, plan directly\n- /gsd:execute-phase {Z+1} — skip to execution (if already planned)\n\n───────────────────────────────────────────────────────────────\n\n---\n\n**Route B: All tests pass, milestone complete**\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n GSD ► PHASE {Z} VERIFIED ✓\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n**Phase {Z}: {Name}**\n\n{N}/{N} tests passed\nFinal phase verified ✓\n\n───────────────────────────────────────────────────────────────\n\n## ▶ Next Up\n\n**Audit milestone** — verify requirements, cross-phase integration, E2E flows\n\n/gsd:audit-milestone\n\n/clear first → fresh context window\n\n───────────────────────────────────────────────────────────────\n\n**Also available:**\n- /gsd:complete-milestone — skip audit, archive directly\n\n───────────────────────────────────────────────────────────────\n\n---\n\n**Route C: Issues found, fix plans ready**\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n GSD ► PHASE {Z} ISSUES FOUND ⚠\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n**Phase {Z}: {Name}**\n\n{N}/{M} tests passed\n{X} issues diagnosed\nFix plans verified ✓\n\n### Issues Found\n\n{List issues with severity from UAT.md}\n\n───────────────────────────────────────────────────────────────\n\n## ▶ Next Up\n\n**Execute fix plans** — run diagnosed fixes\n\n/gsd:execute-phase {Z} --gaps-only\n\n/clear first → fresh context window\n\n───────────────────────────────────────────────────────────────\n\n**Also available:**\n- cat .planning/phases/{phase_dir}/*-PLAN.md — review fix plans\n- /gsd:plan-phase {Z} --gaps — regenerate fix plans\n\n───────────────────────────────────────────────────────────────\n\n---\n\n**Route D: Issues found, planning blocked**\n\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n GSD ► PHASE {Z} BLOCKED ✗\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\n**Phase {Z}: {Name}**\n\n{N}/{M} tests passed\nFix planning blocked after {X} iterations\n\n### Unresolved Issues\n\n{List blocking issues from planner/checker output}\n\n───────────────────────────────────────────────────────────────\n\n## ▶ Next Up\n\n**Manual intervention required**\n\nReview the issues above and either:\n1. Provide guidance for fix planning\n2. Manually address blockers\n3. Accept current state and continue\n\n───────────────────────────────────────────────────────────────\n\n**Options:**\n- /gsd:plan-phase {Z} --gaps — retry fix planning with guidance\n- /gsd:discuss-phase {Z} — gather more context before replanning\n\n───────────────────────────────────────────────────────────────\n</offer_next>\n\n<success_criteria>\n- [ ] UAT.md created with tests from SUMMARY.md\n- [ ] Tests presented one at a time with expected behavior\n- [ ] Plain text responses (no structured forms)\n- [ ] Severity inferred, never asked\n- [ ] Batched writes: on issue, every 5 passes, or completion\n- [ ] Committed on completion\n- [ ] If issues: parallel debug agents diagnose root causes\n- [ ] If issues: gsd-planner creates fix plans from diagnosed gaps\n- [ ] If issues: gsd-plan-checker verifies fix plans (max 3 iterations)\n- [ ] Ready for `/gsd:execute-phase` when complete\n</success_criteria>", "variables": [ "arguments" ], "notes": "Validate built features through conversational UAT Tools: Read, Bash, Glob, Grep, Edit, Write, Task. Arguments: [phase number, e.g., '4'].", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/tumma72/mlx-manager", "path": ".claude/commands/gsd/verify-work.md", "ref": "cffa5f2d2302e6cf04c0aad8dd37f40f8fdf17f8", "url": "https://github.com/tumma72/mlx-manager/blob/cffa5f2d2302e6cf04c0aad8dd37f40f8fdf17f8/.claude/commands/gsd/verify-work.md", "key": "tumma72/mlx-manager/.claude/commands/gsd/verify-work.md" } } }

gsd:verify-work

About

▶ Next Up

▶ Next Up

Issues Found

▶ Next Up

Unresolved Issues

▶ Next Up

Install gsd:verify-work 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