openspec-apply-change

Implement tasks from an OpenSpec change.

Input: Optionally specify a change name. If omitted, check if it can be inferred from conversation context. If vague or ambiguous you MUST prompt for available changes.

Steps

1. Select the change

   If a name is provided, use it. Otherwise:

   • Infer from conversation context if the user mentioned a change
   • Auto-select if only one active change exists
   • If ambiguous, run openspec list --json to get available changes and use the AskUserQuestion tool to let the user select

   Always announce: "Using change: <name>" and how to override (e.g., /opsx:apply <other>).

2. Check status to understand the schema

   openspec status --change "<name>" --json

   Parse the JSON to understand:
   • schemaName: The workflow being used (e.g., "spec-driven")
   • Which artifact contains the tasks (typically "tasks" for spec-driven, check status for others)

3. Get apply instructions

   openspec instructions apply --change "<name>" --json

   This returns:

   • Context file paths (varies by schema - could be proposal/specs/design/tasks or spec/tests/implementation/docs)
   • Progress (total, complete, remaining)
   • Task list with status
   • Dynamic instruction based on current state

   Handle states:

   • If state: "blocked" (missing artifacts): show message, suggest using openspec-continue-change
   • If state: "all_done": congratulate, suggest archive
   • Otherwise: proceed to implementation

4. Read context files

   Read the files listed in contextFiles from the apply instructions output. The files depend on the schema being used:

   • spec-driven: proposal, specs, design, tasks
   • Other schemas: follow the contextFiles from CLI output

5. Show current progress

   Display:

   • Schema being used
   • Progress: "N/M tasks complete"
   • Remaining tasks overview
   • Dynamic instruction from CLI

6. Implement tasks (loop until done or blocked)

   CRITICAL: Before implementing, read .claude/rules/openspec-tasks-mandatory-steps.mdc to understand mandatory testing requirements.

   For each pending task:

   • Show which task is being worked on
   • Make the code changes required
   • Keep changes minimal and focused

   For Manual Testing Tasks (MANDATORY - AGENT MUST EXECUTE):

   • Manual Endpoint Testing with curl: If the task involves testing endpoints:
     • Start backend server if needed
     • Execute all curl commands yourself (GET, POST, PUT/PATCH, DELETE)
     • Test error cases (validation errors, 404, etc.)
     • Verify all responses
     • Restore database state after CREATE/UPDATE/DELETE operations
     • Document all curl commands and responses
     • NEVER ask the user to run curl commands - you must execute them yourself
   • E2E Testing with Playwright MCP: If the task involves frontend/E2E testing:
     • Start frontend and backend servers if needed
     • Use Playwright MCP tools (browser_navigate, browser_click, browser_type, etc.)
     • Execute complete user workflows
     • Test error scenarios
     • Verify data persistence
     • Restore test environment and database state
     • NEVER ask the user to run E2E tests - you must execute them yourself
   • Mark task complete: Only mark task as complete (- [ ] → - [x]) AFTER:
     • All code changes are complete
     • All required manual tests have been executed by you (the agent)
     • All test results have been verified
     • Database state has been restored (if applicable)
     • All test outcomes have been documented
   • Continue to next task

   Pause if:

   • Task is unclear → ask for clarification
   • Implementation reveals a design issue → suggest updating artifacts
   • Error or blocker encountered → report and wait for guidance
   • User interrupts

7. On completion or pause, show status

   Display:

   • Tasks completed this session
   • Overall progress: "N/M tasks complete"
   • If all done: suggest archive
   • If paused: explain why and wait for guidance

Output During Implementation

## Implementing: <change-name> (schema: <schema-name>)

Working on task 3/7: <task description>
[...implementation happening...]
✓ Task complete

Working on task 4/7: <task description>
[...implementation happening...]
✓ Task complete

Output On Completion

## Implementation Complete

**Change:** <change-name>
**Schema:** <schema-name>
**Progress:** 7/7 tasks complete ✓

### Completed This Session
- [x] Task 1
- [x] Task 2
...

All tasks complete! Ready to archive this change.

Output On Pause (Issue Encountered)

## Implementation Paused

**Change:** <change-name>
**Schema:** <schema-name>
**Progress:** 4/7 tasks complete

### Issue Encountered
<description of the issue>

**Options:**
1. <option 1>
2. <option 2>
3. Other approach

What would you like to do?

Guardrails

• Keep going through tasks until done or blocked
• Always read context files before starting (from the apply instructions output)
• CRITICAL: Read .claude/rules/openspec-tasks-mandatory-steps.mdc before implementing to understand mandatory testing requirements
• If task is ambiguous, pause and ask before implementing
• If implementation reveals issues, pause and suggest artifact updates
• Keep code changes minimal and scoped to each task
• For manual testing tasks: Execute all tests yourself (curl for endpoints, Playwright MCP for E2E) - NEVER delegate to user
• Mark tasks complete: Only mark tasks as complete AFTER executing all required manual tests and verifying results
• Update task checkbox immediately after completing each task AND verifying all tests pass
• Pause on errors, blockers, or unclear requirements - don't guess
• Use contextFiles from CLI output, don't assume specific file names
• Never ask user to run tests - you must execute curl commands and E2E tests yourself

Fluid Workflow Integration

This skill supports the "actions on a change" model:

• Can be invoked anytime: Before all artifacts are done (if tasks exist), after partial implementation, interleaved with other actions
• Allows artifact updates: If implementation reveals design issues, suggest updating artifacts - not phase-locked, work fluidly