claude-soul: Command for Claude Code

.claude/commands/qa-align.md

qa-align is a command for Claude Code from tomdwipo/claude-soul. It costs 0 tokens per session (1,600 once invoked), scanned A, original, MIT.

A command that compares product requirements with technical and quality-assurance documentation. QA means checking that software works as intended, while a TRD is a technical requirements document describing how it should work.

In plain words
What is it for?
Use it with a Jira ticket or project files to review screenshots and videos, inspect linked documents, and produce a QA alignment analysis.
Why use it?
It brings requirements, implementation details, test evidence, attachments, and existing compliance information together so missing or mismatched parts are easier to find.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

This is tomdwipo/claude-soul's own configuration. It tells Claude Code how to work on claude-soul itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-soul configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tomdwipo/claude-soul. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tomdwipo/claude-soul/main/.claude/commands/qa-align.md
Clone the repo
git clone --depth 1 https://github.com/tomdwipo/claude-soul

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for qa-align

README.md
[![agentmods](https://agentmods.dev/badge/commands/tomdwipo/claude-soul/qa-align.svg)](https://agentmods.dev/commands/tomdwipo/claude-soul/qa-align)
Your own site
<a href="https://agentmods.dev/commands/tomdwipo/claude-soul/qa-align"><img src="https://agentmods.dev/badge/commands/tomdwipo/claude-soul/qa-align.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01600
Opus 5 $0.00000 $0.00800
Sonnet 5 $0.00000 $0.00320
Haiku 4.5 $0.00000 $0.00160

Measured 7d ago against content hash 64b723aedf74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

qa-align scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/commands/qa-align.md · 180 lines

How it starts

The opening of the file, as written. The whole thing — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.

QA Alignment Command (Phase 3: QA Handoff)

Generate a standalone QA alignment analysis for: $ARGUMENTS

Instructions

Step 1: Gather QA & Dev Data

If $ARGUMENTS contains a Jira ticket ID (e.g., PROJ-1234):

  1. Use mcp__atlassian__getJiraIssue to fetch the ticket details
  2. Use mcp__jira-attachment__list_attachments to list all attachments
  3. Use mcp__jira-attachment__download_all_images to download screenshots/mockups
  4. Use mcp__jira-attachment__download_all_videos to download video attachments
  5. If videos found, use mcp__video-to-image__extract_frames_by_count (count: 5) to extract key frames
  6. Look for QA TRD Confluence link in ticket links/description — fetch with mcp__atlassian__getConfluencePage
  7. Look for BE TRD Confluence link — fetch with mcp__atlassian__getConfluencePage
  8. Look for PRD Confluence link — fetch with mcp__atlassian__getConfluencePage

Step 2: Read Existing Documentation

  1. Check if TRD exists at .docs/trd/TRD-{Feature-Name}.md — read it
  2. Check if feature report exists at .docs/feature-report/{feature-name}/ — read all files
  3. Check if COMPLIANCE_MATRIX.md already exists — use as input for gap analysis
  4. Read actual implemented code files to understand what was built

Step 3: Analyze QA TRD Against Implementation

  1. Map every QA test scenario to an implemented code path
  2. Identify gaps: scenarios in QA TRD not covered by implementation
  3. Identify gaps: implementation behaviors not covered by QA TRD
  4. Cross-reference with PRD requirements
  5. Assess automation feasibility for each gap

Step 4: Generate QA Alignment Document

If feature report exists, update: .docs/feature-report/{feature-name}/QA_ALIGNMENT.md Otherwise create standalone: .docs/qa-alignment/QA-{Feature-Name}.md

Max 10000 characters.

QA Alignment Template

# QA Alignment: {Feature Name}

## Reference Documents

| Document | Location | Status |
|----------|----------|--------|
| **PRD** | {Confluence link} | {Available|N/A} |
| **TRD (Dev)** | {TRD file path or Confluence link} | {Available|N/A} |
| **TRD (BE)** | {Confluence link} | {Available|N/A} |
| **TRD (QA)** | {Confluence link} | {Available|N/A} |
| **Feature Report** | {feature-report path} | {Available|N/A} |
| **Design** | {Figma link} | {Available|N/A} |
| **QA Engineer** | {name from QA TRD or TBD} |
| **Review Assessment** | {name or TBD} |
| **Analysis Date** | {current date YYYY-MM-DD} |

---

## 1. QA TRD Status

{Current status: Draft/In Review/Approved/Not Available}
{List sections marked "Will provide later" or incomplete}

---

## 2. QA Test Cases Mapping

### Automation Scenarios (New)

| # | Scenario | Type | Dev Coverage | Status |
|---|----------|------|-------------|--------|
| A1 | {scenario description} | {Happy path|Negative|Navigation|Validation|Edge case} | {Code path covered + file ref} | {Aligned|Gap|Partial} |

### Automation Scenarios (Updated Existing)

| # | File | Change | Impact |
|---|------|--------|--------|
| U1 | {test file name} | {what changed} | {affected scenarios} |

### New Step Definitions

| # | Step Definition | Mapped To |
|---|-----------------|-----------|
| S1 | {step definition text} | {Screen/Component it tests} |

### Manual Test Scenarios

| # | Scenario | Precondition | Expected Result | Automatable |
|---|----------|-------------|-----------------|-------------|
| M1 | {scenario} | {setup needed} | {what should happen} | {Yes|No|Partial} |

---

## 3. Gap Analysis

### Gaps: QA TRD Missing Coverage

| # | Gap | Severity | Implementation Reference | Suggested Test |
|---|-----|----------|------------------------|----------------|
| G1 | {what QA TRD doesn't cover but implementation has} | {Critical|High|Medium|Low} | {file:line or component} | {brief Gherkin scenario} |

### Gaps: Implementation Deviations from PRD

| # | PRD Requirement | Expected | Actual | Reason |
|---|----------------|----------|--------|--------|
| D1 | {requirement} | {what PRD says} | {what was implemented} | {why different — tech constraint, BE limitation, deferred} |

### Gaps: BE TRD vs Mobile Implementation

| # | Area | BE TRD Says | Mobile Does | Action Needed |
|---|------|------------|-------------|---------------|
| B1 | {area} | {BE contract} | {mobile implementation} | {Confirm with BE|Align|OK} |

---

## 4. Suggested Additional Test Scenarios

{Gherkin-style scenarios for each gap found. Number them matching gap IDs.}

### Scenario G1: {descriptive title}
```gherkin
Feature: {feature name}

Read the full file on GitHub · 180 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 7d ago First seen · 180 lines · 0 tokens per session scan A 64b723aedf74

Subscribe to this mod's changes

qa-align is a command published in the GitHub repository tomdwipo/claude-soul (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,600 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.