Verify that an implementation matches the change artifacts (specs, tasks, design).
Store selection: If the user names a store (a store is a standalone OpenSpec repo registered on this machine) or the work lives in one, run openspec store list --json to discover registered store ids, then pass --store <id> on the commands that read or write specs and changes (new change, status, instructions, list, show, validate, archive, doctor, context, view). Once selected, treat --store <id> as sticky for the rest of the workflow. Every unscoped example of those commands below is shorthand: before running it, append the flag. For example, run openspec status --change "<name>" --json --store "<id>", not the unscoped form shown below. Other commands do not take the flag. Hints printed by commands already carry the flag; keep it on follow-ups. Without a store, commands act on the nearest local openspec/ root.
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
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 ask the user to select one
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: " and how to override (e.g., $openspec-verify-change (Codex) or /openspec-verify-change (other agents) <other>).
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")
planningHome, changeRoot, artifactPaths, and actionContext: path and scope context
- Which artifacts exist for this change
Get planning context and load artifacts
openspec instructions apply --change "<name>" --json
This returns the change directory and contextFiles (artifact ID -> array of concrete file paths). Read all available artifacts from contextFiles.
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.
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
- Recommendation: "Complete task: " or "Mark as done if already implemented"
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
- Assess if implementation likely exists
- If requirements appear unimplemented:
- Add CRITICAL issue: "Requirement not found: "
- Recommendation: "Implement requirement X: "
Verify Correctness
Requirement Implementation Mapping:
- For each requirement from delta specs:
- Search codebase for implementation evidence
- If found, note file paths and line ranges
- Assess if implementation matches requirement intent
- If divergence detected:
- Add WARNING: "Implementation may diverge from spec: "
- Recommendation: "Review : against requirement X"
Scenario Coverage:
- For each scenario in delta specs (marked with "#### Scenario:"):
- Check if conditions are handled in code
- Check if tests exist covering the scenario
- If scenario appears uncovered:
- Add WARNING: "Scenario not covered: "
- Recommendation: "Add test or implementation for scenario: "
Verify Coherence
Design Adherence:
- If
contextFiles.design exists:
- Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")
- Verify implementation follows those decisions
- If contradiction detected:
- Add WARNING: "Design decision not followed: "
- Recommendation: "Update implementation or revise design.md to match reality"
- If no design.md: Skip design adherence check, note "No design.md to verify against"
Code Pattern Consistency:
- Review new code for consistency with project patterns
- Check file naming, directory structure, coding style
- If significant deviations found:
- Add SUGGESTION: "Code pattern deviation: "
- Recommendation: "Consider following project pattern: "
Generate Verification Report
Summary Scorecard:
## Verification Report<change-name>
### Summary
| Dimension | Status |
| ------------ | ----------------- |
| Completeness | X/Y tasks, N reqs |
| Correctness | M/N reqs covered |
| Coherence | Followed/Issues |
Issues by Priority:
CRITICAL (Must fix before archive):
- Incomplete tasks
- Missing requirement implementations
- Each with specific, actionable recommendation
WARNING (Should fix):
- Spec/design divergences
- Missing scenario coverage
- Each with specific recommendation
SUGGESTION (Nice to fix):
- Pattern inconsistencies
- Minor improvements
- Each with specific recommendation
Final Assessment:
- If CRITICAL issues: "X critical issue(s) found. Fix before archiving."
- If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."
- 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 - don't require perfect certainty
- 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 where applicable
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
Output Format
Use clear markdown with:
- Table for summary scorecard
- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)
- Code references in format:
file.ts:123
- Specific, actionable recommendations
- No vague suggestions like "consider reviewing"
1---2name: openspec-verify-change3description: Verify implementation matches change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving.4license: MIT5---67Verify that an implementation matches the change artifacts (specs, tasks, design).89**Store selection:** If the user names a store (a store is a standalone OpenSpec repo registered on this machine) or the work lives in one, run `openspec store list --json` to discover registered store ids, then pass `--store <id>` on the commands that read or write specs and changes (`new change`, `status`, `instructions`, `list`, `show`, `validate`, `archive`, `doctor`, `context`, `view`). Once selected, treat `--store <id>` as sticky for the rest of the workflow. Every unscoped example of those commands below is shorthand: before running it, append the flag. For example, run `openspec status --change "<name>" --json --store "<id>"`, not the unscoped form shown below. Other commands do not take the flag. Hints printed by commands already carry the flag; keep it on follow-ups. Without a store, commands act on the nearest local `openspec/` root.1011**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.1213**Steps**14151. **Select the change**1617 If a name is provided, use it. Otherwise:18 - Infer from conversation context if the user mentioned a change19 - Auto-select if only one active change exists20 - If ambiguous, run `openspec list --json` to get available changes and ask the user to select one2122 When prompting, show changes that have implementation tasks (tasks artifact exists).23 Include the schema used for each change if available.24 Mark changes with incomplete tasks as "(In Progress)".2526 Always announce: "Using change: <name>" and how to override (e.g., `$openspec-verify-change (Codex) or /openspec-verify-change (other agents) <other>`).27282. **Check status to understand the schema**2930 ```bash31 openspec status --change "<name>" --json32 ```3334 Parse the JSON to understand:35 - `schemaName`: The workflow being used (e.g., "spec-driven")36 - `planningHome`, `changeRoot`, `artifactPaths`, and `actionContext`: path and scope context37 - Which artifacts exist for this change38393. **Get planning context and load artifacts**4041 ```bash42 openspec instructions apply --change "<name>" --json43 ```4445 This returns the change directory and `contextFiles` (artifact ID -> array of concrete file paths). Read all available artifacts from `contextFiles`.46474. **Initialize verification report structure**4849 Create a report structure with three dimensions:50 - **Completeness**: Track tasks and spec coverage51 - **Correctness**: Track requirement implementation and scenario coverage52 - **Coherence**: Track design adherence and pattern consistency5354 Each dimension can have CRITICAL, WARNING, or SUGGESTION issues.55565. **Verify Completeness**5758 **Task Completion**:59 - If `contextFiles.tasks` exists, read every file path in it60 - Parse checkboxes: `- [ ]` (incomplete) vs `- [x]` (complete)61 - Count complete vs total tasks62 - If incomplete tasks exist:63 - Add CRITICAL issue for each incomplete task64 - Recommendation: "Complete task: <description>" or "Mark as done if already implemented"6566 **Spec Coverage**:67 - If delta specs exist in `contextFiles.specs`:68 - Extract all requirements (marked with "### Requirement:")69 - For each requirement:70 - Search codebase for keywords related to the requirement71 - Assess if implementation likely exists72 - If requirements appear unimplemented:73 - Add CRITICAL issue: "Requirement not found: <requirement name>"74 - Recommendation: "Implement requirement X: <description>"75766. **Verify Correctness**7778 **Requirement Implementation Mapping**:79 - For each requirement from delta specs:80 - Search codebase for implementation evidence81 - If found, note file paths and line ranges82 - Assess if implementation matches requirement intent83 - If divergence detected:84 - Add WARNING: "Implementation may diverge from spec: <details>"85 - Recommendation: "Review <file>:<lines> against requirement X"8687 **Scenario Coverage**:88 - For each scenario in delta specs (marked with "#### Scenario:"):89 - Check if conditions are handled in code90 - Check if tests exist covering the scenario91 - If scenario appears uncovered:92 - Add WARNING: "Scenario not covered: <scenario name>"93 - Recommendation: "Add test or implementation for scenario: <description>"94957. **Verify Coherence**9697 **Design Adherence**:98 - If `contextFiles.design` exists:99 - Extract key decisions (look for sections like "Decision:", "Approach:", "Architecture:")100 - Verify implementation follows those decisions101 - If contradiction detected:102 - Add WARNING: "Design decision not followed: <decision>"103 - Recommendation: "Update implementation or revise design.md to match reality"104 - If no design.md: Skip design adherence check, note "No design.md to verify against"105106 **Code Pattern Consistency**:107 - Review new code for consistency with project patterns108 - Check file naming, directory structure, coding style109 - If significant deviations found:110 - Add SUGGESTION: "Code pattern deviation: <details>"111 - Recommendation: "Consider following project pattern: <example>"1121138. **Generate Verification Report**114115 **Summary Scorecard**:116117 ```markdown118 ## Verification Report<change-name>119120 ### Summary121122 | Dimension | Status |123 | ------------ | ----------------- |124 | Completeness | X/Y tasks, N reqs |125 | Correctness | M/N reqs covered |126 | Coherence | Followed/Issues |127 ```128129 **Issues by Priority**:130131 1. **CRITICAL** (Must fix before archive):132 - Incomplete tasks133 - Missing requirement implementations134 - Each with specific, actionable recommendation135136 2. **WARNING** (Should fix):137 - Spec/design divergences138 - Missing scenario coverage139 - Each with specific recommendation140141 3. **SUGGESTION** (Nice to fix):142 - Pattern inconsistencies143 - Minor improvements144 - Each with specific recommendation145146 **Final Assessment**:147 - If CRITICAL issues: "X critical issue(s) found. Fix before archiving."148 - If only warnings: "No critical issues. Y warning(s) to consider. Ready for archive (with noted improvements)."149 - If all clear: "All checks passed. Ready for archive."150151**Verification Heuristics**152153- **Completeness**: Focus on objective checklist items (checkboxes, requirements list)154- **Correctness**: Use keyword search, file path analysis, reasonable inference - don't require perfect certainty155- **Coherence**: Look for glaring inconsistencies, don't nitpick style156- **False Positives**: When uncertain, prefer SUGGESTION over WARNING, WARNING over CRITICAL157- **Actionability**: Every issue must have a specific recommendation with file/line references where applicable158159**Graceful Degradation**160161- If only tasks.md exists: verify task completion only, skip spec/design checks162- If tasks + specs exist: verify completeness and correctness, skip design163- If full artifacts: verify all three dimensions164- Always note which checks were skipped and why165166**Output Format**167168Use clear markdown with:169170- Table for summary scorecard171- Grouped lists for issues (CRITICAL/WARNING/SUGGESTION)172- Code references in format: `file.ts:123`173- Specific, actionable recommendations174- No vague suggestions like "consider reviewing"