qaa-agent 1.3.0 → 1.5.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (23) hide show
  1. package/.claude/commands/create-test.md +42 -4
  2. package/.claude/commands/qa-analyze.md +8 -10
  3. package/.claude/commands/qa-map.md +18 -7
  4. package/.claude/commands/qa-pr.md +23 -0
  5. package/.claude/commands/qa-validate.md +25 -3
  6. package/.claude/skills/qa-learner/SKILL.md +8 -0
  7. package/CLAUDE.md +23 -13
  8. package/README.md +20 -7
  9. package/agents/qa-pipeline-orchestrator.md +171 -10
  10. package/agents/qaa-analyzer.md +16 -0
  11. package/agents/qaa-bug-detective.md +2 -0
  12. package/agents/qaa-e2e-runner.md +415 -0
  13. package/agents/qaa-executor.md +14 -0
  14. package/agents/qaa-planner.md +17 -1
  15. package/agents/qaa-scanner.md +2 -0
  16. package/agents/qaa-testid-injector.md +2 -0
  17. package/agents/qaa-validator.md +2 -0
  18. package/bin/install.cjs +12 -4
  19. package/docs/COMMANDS.md +341 -0
  20. package/docs/DEMO.md +182 -0
  21. package/docs/TESTING.md +156 -0
  22. package/package.json +2 -1
  23. package/workflows/qa-pr.md +389 -0
package/.claude/commands/create-test.md CHANGED
@@ -1,19 +1,22 @@
1
1
  # Create Automated Tests
2
2
 
3
- Generate production-ready test files with POM pattern for a specific feature or module. Reads existing QA_ANALYSIS.md and TEST_INVENTORY.md if available.
3
+ Generate production-ready test files with POM pattern for a specific feature or module. Reads codebase map, existing analysis artifacts, and CLAUDE.md standards to produce tests that match the project's actual code patterns. If E2E tests are generated and an app URL is available, runs them against the live app and fixes locators until they pass.
4
4
 
5
5
  ## Usage
6
6
 
7
- /create-test <feature-name> [--dev-repo <path>]
7
+ /create-test <feature-name> [--dev-repo <path>] [--app-url <url>] [--skip-run]
8
8
 
9
9
  - feature-name: which feature to test (e.g., "login", "checkout", "user API")
10
10
  - --dev-repo: path to developer repository (default: current directory)
11
+ - --app-url: URL of running application for E2E test execution (auto-detects if not provided)
12
+ - --skip-run: skip E2E execution, only generate and statically validate
11
13
 
12
14
  ## What It Produces
13
15
 
14
16
  - Test spec files (unit, API, E2E as appropriate for the feature)
15
17
  - Page Object Model files (for E2E tests)
16
18
  - Fixture files (test data)
19
+ - E2E_RUN_REPORT.md (if E2E tests were run against live app)
17
20
 
18
21
  ## Instructions
19
22
 
@@ -21,20 +24,55 @@ Generate production-ready test files with POM pattern for a specific feature or
21
24
  2. Read existing analysis artifacts if available:
22
25
  - `.qa-output/QA_ANALYSIS.md` -- architecture context
23
26
  - `.qa-output/TEST_INVENTORY.md` -- pre-defined test cases for this feature
24
- 3. Invoke executor agent:
27
+ 3. Read codebase map if available (check `.qa-output/codebase/`):
28
+ - `CODE_PATTERNS.md` -- naming conventions, import style, code patterns to match
29
+ - `API_CONTRACTS.md` -- request/response shapes for API tests
30
+ - `TEST_SURFACE.md` -- function signatures and testable entry points
31
+ - `TESTABILITY.md` -- pure functions vs stateful code, mock boundaries
32
+ If codebase map does not exist, run `/qa-map` first for best results, or proceed without it.
33
+
34
+ 4. Invoke executor agent to generate test files:
25
35
 
26
36
  Task(
27
37
  prompt="
28
- <objective>Generate test files for the specified feature following CLAUDE.md standards</objective>
38
+ <objective>Generate test files for the specified feature following CLAUDE.md standards, using codebase map for context</objective>
29
39
  <execution_context>@agents/qaa-executor.md</execution_context>
30
40
  <files_to_read>
31
41
  - CLAUDE.md
42
+ - .qa-output/codebase/CODE_PATTERNS.md (if exists)
43
+ - .qa-output/codebase/API_CONTRACTS.md (if exists)
44
+ - .qa-output/codebase/TEST_SURFACE.md (if exists)
45
+ - .qa-output/codebase/TESTABILITY.md (if exists)
32
46
  </files_to_read>
33
47
  <parameters>
34
48
  user_input: $ARGUMENTS
35
49
  mode: feature-test
50
+ codebase_map_dir: .qa-output/codebase
36
51
  </parameters>
37
52
  "
38
53
  )
39
54
 
55
+ 5. If E2E test files were generated AND `--skip-run` was NOT passed, invoke the E2E runner to execute tests against the live app:
56
+
57
+ Task(
58
+ prompt="
59
+ <objective>Run generated E2E tests against live application, capture real locators, fix mismatches, loop until pass</objective>
60
+ <execution_context>@agents/qaa-e2e-runner.md</execution_context>
61
+ <files_to_read>
62
+ - CLAUDE.md
63
+ - {generated E2E test files from executor return}
64
+ - {generated POM files from executor return}
65
+ </files_to_read>
66
+ <parameters>
67
+ app_url: {from --app-url flag or auto-detect}
68
+ output_dir: .qa-output
69
+ </parameters>
70
+ "
71
+ )
72
+
73
+ 6. Present results:
74
+ - List generated files with type counts (unit, API, E2E, POM, fixture)
75
+ - If E2E runner executed: show pass/fail counts, locator fixes applied, app bugs found
76
+ - Suggest `/qa-pr` to package as a pull request
77
+
40
78
  $ARGUMENTS
package/.claude/commands/qa-analyze.md CHANGED
@@ -1,21 +1,19 @@
1
- # QA Repository Analysis
1
+ # QA Repository Analysis (Deprecated)
2
2
 
3
- Analysis-only mode. Scans a repository, detects framework and stack, and produces QA assessment documents. No test generation. No PR creation.
3
+ This command has been merged into `/qa-map`, which runs codebase mapping + analysis in one step.
4
4
 
5
5
  ## Usage
6
6
 
7
- /qa-analyze [--dev-repo <path>] [--qa-repo <path>]
7
+ Use `/qa-map` instead:
8
8
 
9
- - No arguments: analyzes current directory
10
- - --dev-repo: explicit path to developer repository
11
- - --qa-repo: path to existing QA repository (produces gap analysis instead of blueprint)
9
+ ```
10
+ /qa-map [--dev-repo <path>] [--qa-repo <path>]
11
+ ```
12
12
 
13
13
  ## Instructions
14
14
 
15
- 1. Read `CLAUDE.md` -- all QA standards.
16
- 2. Execute the workflow:
15
+ Tell the user: "/qa-analyze is now part of /qa-map. Running /qa-map for you."
17
16
 
18
- Follow the workflow defined in `@workflows/qa-analyze.md` end-to-end.
19
- Preserve all workflow gates (scan verification, artifact checks).
17
+ Then execute `/qa-map` with the same arguments the user provided.
20
18
 
21
19
  $ARGUMENTS
package/.claude/commands/qa-map.md CHANGED
@@ -1,21 +1,30 @@
1
- # QA Codebase Map
1
+ # QA Codebase Map & Analysis
2
2
 
3
- Deep-scan a codebase for QA-relevant information. Spawns 4 parallel mapper agents that analyze testability, risk areas, code patterns, and existing tests. Produces structured documents consumed by the QA pipeline.
3
+ Deep-scan a codebase for QA-relevant information and produce a complete analysis. Runs codebase mapping (4 parallel agents) followed by repository analysis. One command to fully understand a codebase before writing tests.
4
4
 
5
5
  ## Usage
6
6
 
7
- /qa-map [--focus <area>]
7
+ /qa-map [--focus <area>] [--dev-repo <path>] [--qa-repo <path>]
8
8
 
9
- - No arguments: runs all 4 focus areas in parallel
10
- - --focus: run a single area (testability, risk, patterns, existing-tests)
9
+ - No arguments: runs full map + analysis on current directory
10
+ - --focus: run a single map area only, skip analysis (testability, risk, patterns, existing-tests)
11
+ - --dev-repo: explicit path to developer repository
12
+ - --qa-repo: path to existing QA repository (produces gap analysis instead of blueprint)
11
13
 
12
14
  ## What It Produces
13
15
 
16
+ ### Stage 1: Codebase Map (4 parallel agents)
14
17
  - TESTABILITY.md + TEST_SURFACE.md — what's testable, entry points, mocking needs
15
18
  - RISK_MAP.md + CRITICAL_PATHS.md — business-critical paths, error handling gaps
16
19
  - CODE_PATTERNS.md + API_CONTRACTS.md — naming conventions, API shapes, auth patterns
17
20
  - TEST_ASSESSMENT.md + COVERAGE_GAPS.md — existing test quality, what's missing
18
21
 
22
+ ### Stage 2: Repository Analysis
23
+ - SCAN_MANIFEST.md — file tree, framework detection, testable surfaces
24
+ - QA_ANALYSIS.md — architecture overview, risk assessment, top 10 unit targets, testing pyramid
25
+ - TEST_INVENTORY.md — every test case with ID, target, inputs, expected outcome, priority
26
+ - QA_REPO_BLUEPRINT.md (no QA repo) or GAP_ANALYSIS.md (QA repo provided)
27
+
19
28
  ## Instructions
20
29
 
21
30
  1. Read `CLAUDE.md` — QA standards.
@@ -30,7 +39,9 @@ Agent(
30
39
  execution_context="@agents/qaa-codebase-mapper.md"
31
40
  )
32
41
 
33
- 4. If --focus flag, spawn only that one area.
34
- 5. When all complete, print summary of documents produced.
42
+ 4. If --focus flag, spawn only that one area and stop (skip analysis stage).
43
+ 5. When all map agents complete, print summary of codebase documents produced.
44
+ 6. Run the analysis stage — execute the workflow defined in `@workflows/qa-analyze.md` end-to-end. Pass --dev-repo and --qa-repo arguments if provided. Preserve all workflow gates (scan verification, artifact checks).
45
+ 7. Print final summary: all documents produced across both stages.
35
46
 
36
47
  $ARGUMENTS
package/.claude/commands/qa-pr.md ADDED
@@ -0,0 +1,23 @@
1
+ # Create QA Pull Request
2
+
3
+ Create a draft PR from QA artifacts already on disk. Auto-detects git platform (GitHub, Azure DevOps, GitLab), applies your team's branch naming convention, and creates a draft PR with a summary. Asks for your branch pattern the first time and remembers it.
4
+
5
+ ## Usage
6
+
7
+ /qa-pr [--ticket <id>] [--title <description>] [--scope <type>] [--files <glob>] [--base <branch>]
8
+
9
+ - --ticket: ticket/issue ID for branch name (e.g., PROJ-123)
10
+ - --title: short description for branch and PR title (e.g., "login tests")
11
+ - --scope: limit to file type: unit, api, e2e, all (default: all)
12
+ - --files: explicit file glob to include (e.g., "tests/unit/auth*")
13
+ - --base: target branch for PR (default: auto-detect)
14
+
15
+ ## Instructions
16
+
17
+ 1. Read `CLAUDE.md` -- git workflow, commit conventions.
18
+ 2. Execute the workflow:
19
+
20
+ Follow the workflow defined in `@workflows/qa-pr.md` end-to-end.
21
+ Preserve all workflow gates (platform detection, user confirmation before push, branch convention save).
22
+
23
+ $ARGUMENTS
package/.claude/commands/qa-validate.md CHANGED
@@ -1,20 +1,42 @@
1
1
  # QA Test Validation
2
2
 
3
- Validate existing test files against CLAUDE.md standards. Runs 4-layer validation (syntax, structure, dependencies, logic) and classifies any failures found.
3
+ Validate existing test files against CLAUDE.md standards. Runs 4-layer static validation (syntax, structure, dependencies, logic) and optionally executes E2E tests against a live app to verify locators and assertions with real page data.
4
4
 
5
5
  ## Usage
6
6
 
7
- /qa-validate [<test-directory>] [--classify]
7
+ /qa-validate [<test-directory>] [--classify] [--run --app-url <url>]
8
8
 
9
9
  - test-directory: path to test files (auto-detects if omitted)
10
10
  - --classify: also run bug-detective to classify failures
11
+ - --run: execute E2E tests against a live application after static validation
12
+ - --app-url: URL of running application (auto-detects if not provided)
11
13
 
12
14
  ## Instructions
13
15
 
14
16
  1. Read `CLAUDE.md` -- quality gates, locator tiers, assertion rules.
15
- 2. Execute the workflow:
17
+ 2. Execute the static validation workflow:
16
18
 
17
19
  Follow the workflow defined in `@workflows/qa-validate.md` end-to-end.
18
20
  Preserve all workflow gates (fix loops, classification).
19
21
 
22
+ 3. If `--run` flag is present and E2E test files exist in the validated directory, invoke the E2E runner:
23
+
24
+ Task(
25
+ prompt="
26
+ <objective>Run E2E tests against live application, capture real locators, fix mismatches, loop until pass</objective>
27
+ <execution_context>@agents/qaa-e2e-runner.md</execution_context>
28
+ <files_to_read>
29
+ - CLAUDE.md
30
+ - {E2E test files from validated directory}
31
+ - {POM files from validated directory}
32
+ </files_to_read>
33
+ <parameters>
34
+ app_url: {from --app-url flag or auto-detect}
35
+ output_dir: .qa-output
36
+ </parameters>
37
+ "
38
+ )
39
+
40
+ 4. Present combined results: static validation + E2E execution (if ran).
41
+
20
42
  $ARGUMENTS
package/.claude/skills/qa-learner/SKILL.md CHANGED
@@ -132,6 +132,14 @@ The preference file is the user's personal override layer on top of the project'
132
132
  **Extract:** Naming rule — test ID at start of name
133
133
  **Save:** `## Naming\n- Test ID must appear at the beginning of the test name (e.g., "UT-AUTH-001: should validate email format") — (added 2026-03-24, context: "user wants ID at start of test name")`
134
134
 
135
+ **User says:** "Las branches tienen que ser feature/{ticket}-{description}"
136
+ **Extract:** Workflow rule — branch naming convention
137
+ **Save:** `## Workflow\n- Branch naming convention: feature/{ticket}-{description} — (added 2026-03-24, context: "user configured branch pattern for /qa-pr")`
138
+
139
+ **User says:** "Nuestras ramas siempre empiezan con test/ y el ticket de Jira"
140
+ **Extract:** Workflow rule — branch naming convention
141
+ **Save:** `## Workflow\n- Branch naming convention: test/{ticket}-{description} — (added 2026-03-24, context: "user specified branch pattern with Jira ticket prefix")`
142
+
135
143
  ## Important Rules
136
144
 
137
145
  1. **NEVER push MY_PREFERENCES.md to any repo** — it's personal
package/CLAUDE.md CHANGED
@@ -197,7 +197,7 @@ The QA automation system runs agents in a defined pipeline. Each stage produces
197
197
  ### Pipeline Stages
198
198
 
199
199
  ```
200
- scan -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> deliver
200
+ scan -> codebase-map -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> [e2e-runner if E2E tests] -> [bug-detective if failures] -> deliver
201
201
  ```
202
202
 
203
203
  ### Workflow Options
@@ -205,9 +205,9 @@ scan -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -
205
205
  **Option 1: Dev-Only Repo (no existing QA repo)**
206
206
  Full pipeline from scratch:
207
207
  ```
208
- scan -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> deliver
208
+ scan -> codebase-map -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> [e2e-runner if E2E tests] -> [bug-detective if failures] -> deliver
209
209
  ```
210
- Produces: SCAN_MANIFEST.md -> QA_ANALYSIS.md + TEST_INVENTORY.md + QA_REPO_BLUEPRINT.md -> [TESTID_AUDIT_REPORT.md] -> generation plan -> test files + POMs + fixtures + configs -> VALIDATION_REPORT.md -> branch + PR
210
+ Produces: SCAN_MANIFEST.md -> 8 codebase map documents -> QA_ANALYSIS.md + TEST_INVENTORY.md + QA_REPO_BLUEPRINT.md -> [TESTID_AUDIT_REPORT.md] -> generation plan -> test files + POMs + fixtures + configs -> VALIDATION_REPORT.md -> [E2E_RUN_REPORT.md] -> branch + PR
211
211
 
212
212
  **Option 2: Dev + Immature QA Repo (existing QA repo with low coverage or quality)**
213
213
  Gap-fill and standardize:
@@ -227,13 +227,18 @@ Produces: SCAN_MANIFEST.md (both repos) -> GAP_ANALYSIS.md (thin areas only) ->
227
227
 
228
228
  | From | To | Condition |
229
229
  |------|----|-----------|
230
- | scan | analyze | SCAN_MANIFEST.md exists with > 0 testable surfaces |
230
+ | scan | codebase-map | SCAN_MANIFEST.md exists with > 0 testable surfaces |
231
+ | codebase-map | analyze | At least 4 of 8 codebase map documents exist |
231
232
  | analyze | testid-inject | QA_ANALYSIS.md exists AND frontend components detected |
232
233
  | analyze | plan | QA_ANALYSIS.md + TEST_INVENTORY.md exist (skip testid-inject if no frontend) |
233
234
  | testid-inject | plan | TESTID_AUDIT_REPORT.md exists with coverage score calculated |
234
235
  | plan | generate | Generation plan approved (or auto-approved in auto-advance mode) |
235
236
  | generate | validate | All planned test files exist on disk |
236
- | validate | deliver | VALIDATION_REPORT.md shows PASS or max fix loops (3) exhausted |
237
+ | validate | e2e-runner | VALIDATION_REPORT.md shows PASS AND E2E test files were generated AND live app available |
238
+ | validate | deliver | VALIDATION_REPORT.md shows PASS and no E2E files or --skip-run |
239
+ | e2e-runner | bug-detective | E2E_RUN_REPORT.md exists AND failures need classification |
240
+ | e2e-runner | deliver | E2E_RUN_REPORT.md exists AND all tests pass or failures classified |
241
+ | bug-detective | deliver | FAILURE_CLASSIFICATION_REPORT.md exists |
237
242
 
238
243
  ---
239
244
 
@@ -244,12 +249,15 @@ Each agent owns specific artifacts. No agent may produce artifacts assigned to a
244
249
  | Agent | Reads | Produces | Template |
245
250
  |-------|-------|----------|----------|
246
251
  | qa-scanner | repo source files, package.json, file tree | SCAN_MANIFEST.md | templates/scan-manifest.md |
247
- | qa-analyzer | SCAN_MANIFEST.md, CLAUDE.md | QA_ANALYSIS.md, TEST_INVENTORY.md, QA_REPO_BLUEPRINT.md (Option 1) or GAP_ANALYSIS.md (Option 2/3) | templates/qa-analysis.md, templates/test-inventory.md, templates/qa-repo-blueprint.md, templates/gap-analysis.md |
248
- | qa-planner | TEST_INVENTORY.md, QA_ANALYSIS.md | Generation plan (internal) | -- |
249
- | qa-executor | TEST_INVENTORY.md, CLAUDE.md | test files, POMs, fixtures, configs | qa-template-engine patterns |
252
+ | qa-codebase-mapper | SCAN_MANIFEST.md, repo source files, CLAUDE.md | TESTABILITY.md, TEST_SURFACE.md, RISK_MAP.md, CRITICAL_PATHS.md, CODE_PATTERNS.md, API_CONTRACTS.md, TEST_ASSESSMENT.md, COVERAGE_GAPS.md | -- |
253
+ | qa-analyzer | SCAN_MANIFEST.md, codebase map documents, CLAUDE.md | QA_ANALYSIS.md, TEST_INVENTORY.md, QA_REPO_BLUEPRINT.md (Option 1) or GAP_ANALYSIS.md (Option 2/3) | templates/qa-analysis.md, templates/test-inventory.md, templates/qa-repo-blueprint.md, templates/gap-analysis.md |
254
+ | qa-planner | TEST_INVENTORY.md, QA_ANALYSIS.md, codebase map documents | Generation plan (internal) | -- |
255
+ | qa-executor | TEST_INVENTORY.md, codebase map documents, CLAUDE.md | test files, POMs, fixtures, configs | qa-template-engine patterns |
250
256
  | qa-validator | generated test files, CLAUDE.md | VALIDATION_REPORT.md (validation mode) or QA_AUDIT_REPORT.md (audit mode) | templates/validation-report.md, templates/qa-audit-report.md |
257
+ | qa-e2e-runner | generated E2E test files, POM files, CLAUDE.md, live application | E2E_RUN_REPORT.md, fixed test/POM files with real locators | -- |
251
258
  | qa-testid-injector | repo source files, SCAN_MANIFEST.md, CLAUDE.md | TESTID_AUDIT_REPORT.md, modified source files with data-testid attributes | templates/scan-manifest.md, templates/testid-audit-report.md |
252
259
  | qa-bug-detective | test execution results, test source files, CLAUDE.md | FAILURE_CLASSIFICATION_REPORT.md | templates/failure-classification.md |
260
+ | qa-project-researcher | SCAN_MANIFEST.md, repo source files | TESTING_STACK.md, FRAMEWORK_CAPABILITIES.md, API_TESTING_STRATEGY.md, E2E_STRATEGY.md | -- |
253
261
 
254
262
  **Rule:** An agent MUST NOT produce artifacts assigned to another agent.
255
263
 
@@ -390,11 +398,13 @@ Each agent operates on the same branch. No worktree splits are needed for this s
390
398
 
391
399
  Respect stage transitions from the Agent Pipeline section:
392
400
  1. qa-scanner runs first (no dependencies)
393
- 2. qa-analyzer and qa-testid-injector run after scanner (both depend on SCAN_MANIFEST.md)
394
- 3. qa-planner runs after analyzer (depends on QA_ANALYSIS.md + TEST_INVENTORY.md)
395
- 4. qa-executor runs after planner (depends on generation plan)
396
- 5. qa-validator runs after executor (depends on generated test files)
397
- 6. qa-bug-detective runs after test execution (depends on test results)
401
+ 2. qa-codebase-mapper runs after scanner (depends on SCAN_MANIFEST.md, spawns 4 parallel focus agents)
402
+ 3. qa-analyzer and qa-testid-injector run after codebase-map (both depend on SCAN_MANIFEST.md + codebase map documents)
403
+ 4. qa-planner runs after analyzer (depends on QA_ANALYSIS.md + TEST_INVENTORY.md + codebase map documents)
404
+ 5. qa-executor runs after planner (depends on generation plan + codebase map documents)
405
+ 6. qa-validator runs after executor (depends on generated test files)
406
+ 7. qa-e2e-runner runs after validator (depends on E2E test files + live application)
407
+ 8. qa-bug-detective runs after e2e-runner or validator if failures (depends on test results)
398
408
 
399
409
  ### Auto-Advance Mode
400
410
 
package/README.md CHANGED
@@ -67,7 +67,7 @@ If any command fails, install the missing tool before proceeding.
67
67
  node bin/qaa-tools.cjs validate health
68
68
  ```
69
69
 
70
- 3. Open Claude Code in this directory. The `.claude/commands/` directory provides all 13 slash commands automatically -- no additional setup needed.
70
+ 3. Open Claude Code in this directory. The `.claude/commands/` directory provides all slash commands automatically -- no additional setup needed.
71
71
 
72
72
  ## Configuration
73
73
 
@@ -166,8 +166,12 @@ Produces: TESTID_AUDIT_REPORT.md and modified source files with `data-testid` at
166
166
  | `/qa-blueprint` | Generate QA repository structure blueprint | `/qa-blueprint [--dev-repo <path>]` |
167
167
  | `/qa-report` | Generate QA status report (team/management/client) | `/qa-report <path-to-tests> [--audience <level>]` |
168
168
  | `/qa-pyramid` | Analyze test distribution vs. ideal pyramid | `/qa-pyramid <path-to-tests> [--dev-repo <path>]` |
169
- | `/create-test` | Generate tests for a specific feature | `/create-test <feature-name> [--dev-repo <path>]` |
169
+ | `/create-test` | Generate tests for a specific feature | `/create-test <feature-name> [--dev-repo <path>] [--app-url <url>]` |
170
170
  | `/update-test` | Improve existing tests without rewriting them | `/update-test <path-to-tests> [--scope <type>]` |
171
+ | `/qa-map` | Deep-scan codebase for testability, risk, patterns | `/qa-map [--focus <area>]` |
172
+ | `/qa-research` | Research best testing stack and practices | `/qa-research [--focus <area>]` |
173
+ | `/qa-from-ticket` | Generate tests from a Jira/Linear/GitHub ticket | `/qa-from-ticket <source>` |
174
+ | `/qa-pr` | Create draft PR from QA artifacts | `/qa-pr [--ticket <id>] [--title <desc>]` |
171
175
 
172
176
  ## Workflow Options
173
177
 
@@ -336,12 +340,15 @@ qa-agent-gsd/
336
340
  agents/ -- Agent workflow definitions
337
341
  qa-pipeline-orchestrator.md -- Main pipeline controller (3 options)
338
342
  qaa-scanner.md -- Repository scanner agent
343
+ qaa-codebase-mapper.md -- Codebase deep-scan agent (4 parallel focus areas)
339
344
  qaa-analyzer.md -- Architecture analyzer agent
340
345
  qaa-planner.md -- Test generation planner agent
341
346
  qaa-executor.md -- Test file generator agent
342
347
  qaa-validator.md -- Test validation agent
348
+ qaa-e2e-runner.md -- E2E test execution agent (Playwright browser)
343
349
  qaa-testid-injector.md -- Test ID injection agent
344
350
  qaa-bug-detective.md -- Failure classification agent
351
+ qaa-project-researcher.md -- Testing stack research agent
345
352
  bin/ -- CLI tooling
346
353
  qaa-tools.cjs -- Main CLI entry point
347
354
  lib/ -- CLI module library
@@ -356,7 +363,7 @@ qa-agent-gsd/
356
363
  testid-audit-report.md -- Test ID audit template
357
364
  qa-audit-report.md -- Quality audit template
358
365
  pr-template.md -- Pull request body template
359
- .claude/commands/ -- Slash commands (13 commands, auto-detected by Claude Code)
366
+ .claude/commands/ -- Slash commands (17 commands, auto-detected by Claude Code)
360
367
  qa-start.md -- Tier 1: full pipeline
361
368
  qa-analyze.md -- Tier 2: analysis only
362
369
  qa-validate.md -- Tier 2: test validation
@@ -370,6 +377,10 @@ qa-agent-gsd/
370
377
  qa-pyramid.md -- Tier 3: pyramid analysis
371
378
  create-test.md -- Tier 3: create tests for a feature
372
379
  update-test.md -- Tier 3: improve existing tests
380
+ qa-map.md -- Tier 3: deep-scan codebase
381
+ qa-research.md -- Tier 3: research testing stack
382
+ qa-from-ticket.md -- Tier 3: tests from ticket
383
+ qa-pr.md -- Tier 3: create draft PR
373
384
  CLAUDE.md -- QA standards, agent coordination, quality gates
374
385
  .planning/ -- Planning artifacts and project state
375
386
  config.json -- Pipeline configuration
@@ -381,17 +392,19 @@ qa-agent-gsd/
381
392
  The full pipeline follows this sequence:
382
393
 
383
394
  ```
384
- scan -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> [bug-detective if failures] -> deliver
395
+ scan -> codebase-map -> analyze -> [testid-inject if frontend] -> plan -> generate -> validate -> [e2e-runner if E2E tests] -> [bug-detective if failures] -> deliver
385
396
  ```
386
397
 
387
398
  | Stage | Agent | Input | Output |
388
399
  |-------|-------|-------|--------|
389
400
  | Scan | qa-scanner | Repository source files | SCAN_MANIFEST.md |
390
- | Analyze | qa-analyzer | SCAN_MANIFEST.md | QA_ANALYSIS.md, TEST_INVENTORY.md, blueprint or gap analysis |
401
+ | Codebase Map | qa-codebase-mapper (x4 parallel) | SCAN_MANIFEST.md, source files | 8 codebase documents (testability, risk, patterns, existing tests) |
402
+ | Analyze | qa-analyzer | SCAN_MANIFEST.md, codebase map | QA_ANALYSIS.md, TEST_INVENTORY.md, blueprint or gap analysis |
391
403
  | Test ID Inject | qa-testid-injector | Frontend source files | TESTID_AUDIT_REPORT.md, modified source files |
392
- | Plan | qa-planner | TEST_INVENTORY.md, QA_ANALYSIS.md | Generation plan (internal) |
393
- | Generate | qa-executor | Generation plan, TEST_INVENTORY.md | Test files, POMs, fixtures, configs |
404
+ | Plan | qa-planner | TEST_INVENTORY.md, QA_ANALYSIS.md, codebase map | Generation plan (internal) |
405
+ | Generate | qa-executor | Generation plan, codebase map | Test files, POMs, fixtures, configs |
394
406
  | Validate | qa-validator | Generated test files | VALIDATION_REPORT.md |
407
+ | E2E Runner | qa-e2e-runner | E2E test files, live app | E2E_RUN_REPORT.md, fixed locators |
395
408
  | Bug Detective | qa-bug-detective | Test execution results | FAILURE_CLASSIFICATION_REPORT.md |
396
409
  | Deliver | orchestrator | All artifacts | Git branch + draft PR |
397
410