devcxl/opencode-spec/openspec-verify-change

Verify that an implementation matches the change artifacts (specs, tasks, design).

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 node .opencode/skills/_shared/references/openspec-cli.js list to get available changes and use the question tool to let the user select

When prompting, show changes that have implementation tasks (tasks artifact exists). Include the schema used for each change if available. Mark changes with incomplete tasks as "(In Progress)".

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

1. Check status to understand the schema

``bash node .opencode/skills/_shared/references/openspec-cli.js status "<name>" `` Parse the JSON to understand:

• schemaName: The workflow being used (e.g., "spec-driven")
• planningHome, changeRoot, artifactPaths, and actionContext: path and scope context
• Which artifacts exist for this change

1. Get planning context and load artifacts

``bash node .opencode/skills/_shared/references/openspec-cli.js prepare-apply --change="<name>" ``

This returns the change directory and contextFiles (artifact ID -> array of concrete file paths). Read all available artifacts from contextFiles.

1. Initialize verification report structure

Create a report structure with three dimensions:

• Completeness: Track tasks and spec coverage
• Correctness: Track requirement implementation and scenario coverage
• Coherence: Track design adherence and pattern consistency

Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.

1. Verify Completeness

Task Completion:

• If contextFiles.tasks exists, read every file path in it
• Parse checkboxes: - [ ] (incomplete) vs - [x] (complete)
• Count complete vs total tasks
• If incomplete tasks exist:
• Add CRITICAL issue for each incomplete task

Spec Coverage:

• If delta specs exist in contextFiles.specs:
• Extract all requirements (marked with "### Requirement:")
• For each requirement, search codebase for keywords related to the requirement
• If requirements appear unimplemented:
• Add CRITICAL issue: "Requirement not found: <requirement name>"

1. Verify Correctness

Requirement Implementation Mapping:

• For each requirement from delta specs:
• Search codebase for implementation evidence
• If divergence detected:
• Add WARNING: "Implementation may diverge from spec: <details>"

Scenario Coverage:

• For each scenario in delta specs (marked with "#### Scenario:"):
• Check if conditions are handled in code
• If scenario appears uncovered:
• Add WARNING: "Scenario not covered: <scenario name>"

1. Verify Coherence

Design Adherence:

• If contextFiles.design exists:
• Extract key decisions
• Verify implementation follows those decisions
• If contradiction detected:
• Add WARNING: "Design decision not followed: <decision>"

Code Pattern Consistency:

• Review new code for consistency with project patterns
• If significant deviations found:
• Add SUGGESTION: "Code pattern deviation: <details>"

1. Generate Verification Report

Summary Scorecard: ```markdown ## Verification Report: <change-name>

### Summary

```

Issues by Priority:

1. CRITICAL (Must fix before archive):

• Incomplete tasks, missing requirement implementations

1. WARNING (Should fix):

• Spec/design divergences, missing scenario coverage

1. SUGGESTION (Nice to fix):

• Pattern inconsistencies, minor improvements

Final Assessment:

• If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
• If only warnings: "No critical issues. Y warning(s) to consider."
• If all clear: "All checks passed. Ready for archive."

Verification Heuristics

• Completeness: Focus on objective checklist items (checkboxes, requirements list)
• Correctness: Use keyword search, file path analysis, reasonable inference
• Coherence: Look for glaring inconsistencies, don't nitpick style
• False Positives: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL
• Actionability: Every issue must have a specific recommendation with file/line references

Graceful Degradation

• If only tasks.md exists: verify task completion only, skip spec/design checks
• If tasks + specs exist: verify completeness and correctness, skip design
• If full artifacts: verify all three dimensions
• Always note which checks were skipped and why