qualiow-exploratory-testing 1.3.0 → 2.0.0

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 (93) hide show
  1. package/.claude-plugin/plugin.json +22 -0
  2. package/.env.example +27 -0
  3. package/CHANGELOG.md +194 -0
  4. package/README.md +362 -205
  5. package/agents/qa-gather-agent.md +24 -0
  6. package/{scripts → bin}/doctor-mobile.sh +57 -18
  7. package/bin/mcli +15 -9
  8. package/bin/mobile-cli.mjs +574 -286
  9. package/{scripts → bin}/setup-mobile.sh +56 -19
  10. package/bin/wadb +10 -4
  11. package/bin/wk-ios +29 -17
  12. package/bin/wkeval.mjs +7 -1
  13. package/data/domains/_default.yml +1 -1
  14. package/data/knowledge/changelog.yml +30 -12
  15. package/data/knowledge/manifest.yml +333 -127
  16. package/data/knowledge/releases/v0.1.0/entries/technique-business-logic-race-conditions.yml +1 -1
  17. package/data/knowledge/releases/v0.1.0/release.yml +8 -1
  18. package/data/knowledge/releases/v0.6.0/entries/technique-async-callback-contracts.yml +98 -0
  19. package/data/knowledge/releases/v0.6.0/entries/technique-exactly-once-verification.yml +116 -0
  20. package/data/knowledge/releases/v0.6.0/release.yml +30 -0
  21. package/data/security/SECURITY-POLICY.md +273 -0
  22. package/data/targets/_default.yml +1 -1
  23. package/data/targets/_example-api-only.yml +80 -0
  24. package/data/targets/_example-mobile-emulation.yml +2 -2
  25. package/data/targets/_example-native-mobile.yml +2 -2
  26. package/data/targets/_example-sim-android-chrome.yml +1 -1
  27. package/data/targets/_example-sim-ios-safari.yml +1 -1
  28. package/data/templates/api-probe-matrix.md +3 -3
  29. package/data/templates/bug-report.md +29 -151
  30. package/data/templates/coverage-map.md +9 -6
  31. package/data/templates/expected-behaviour.md +3 -2
  32. package/data/templates/session-charter.md +3 -0
  33. package/data/templates/session-report.md +57 -80
  34. package/dist/cli/index.js +1452 -700
  35. package/dist/index.d.ts +589 -81
  36. package/dist/index.js +1612 -227
  37. package/docs/BACKEND-VERIFICATION.md +39 -9
  38. package/docs/GETTING-STARTED.md +188 -128
  39. package/docs/MOBILE-SETUP.md +149 -18
  40. package/package.json +32 -18
  41. package/skills/qa-explore/SKILL.md +31 -25
  42. package/skills/qa-explore/phases/00-setup.md +67 -41
  43. package/skills/qa-explore/phases/01-auth.md +32 -15
  44. package/skills/qa-explore/phases/02-charter.md +16 -5
  45. package/skills/qa-explore/phases/03-discovery.md +50 -26
  46. package/skills/qa-explore/phases/04-journeys.md +2 -2
  47. package/skills/qa-explore/phases/05-features.md +39 -24
  48. package/skills/qa-explore/phases/06-edge-cases.md +24 -13
  49. package/skills/qa-explore/phases/07-reporting.md +79 -140
  50. package/skills/qa-explore/references/context-integration.md +1 -1
  51. package/skills/qa-explore/references/output-contract.md +187 -0
  52. package/skills/qa-explore/references/paths.md +84 -0
  53. package/skills/qa-explore/references/playwright-agents-integration.md +61 -84
  54. package/skills/qa-explore/references/security-rules.md +66 -25
  55. package/skills/qa-explore/references/severity-guide.md +31 -4
  56. package/skills/qa-explore-cleanup/SKILL.md +17 -6
  57. package/skills/qa-explore-feedback/SKILL.md +18 -5
  58. package/skills/qa-explore-mobile/SKILL.md +86 -64
  59. package/skills/qa-explore-mobile/phases/00-setup.md +71 -62
  60. package/skills/qa-explore-mobile/phases/01-auth.md +28 -31
  61. package/skills/qa-explore-mobile/phases/02-charter.md +8 -4
  62. package/skills/qa-explore-mobile/phases/03-discovery.md +17 -11
  63. package/skills/qa-explore-mobile/phases/04-journeys.md +6 -6
  64. package/skills/qa-explore-mobile/phases/05-features.md +9 -9
  65. package/skills/qa-explore-mobile/phases/06-edge-cases.md +35 -40
  66. package/skills/qa-explore-mobile/phases/07-reporting.md +82 -56
  67. package/skills/qa-explore-mobile/references/mobile-edges.md +26 -26
  68. package/skills/qa-explore-quick/SKILL.md +60 -25
  69. package/skills/qa-explore-report/SKILL.md +40 -34
  70. package/skills/qa-gather/SKILL.md +17 -2
  71. package/skills/qa-knowledge-add/SKILL.md +20 -9
  72. package/skills/qa-knowledge-list/SKILL.md +12 -3
  73. package/skills/qa-target-setup/SKILL.md +63 -41
  74. package/skills/qa-verify-backend/SKILL.md +26 -17
  75. package/skills/qa-verify-backend/phases/00-setup.md +57 -12
  76. package/skills/qa-verify-backend/phases/01-ac-decomposition.md +2 -2
  77. package/skills/qa-verify-backend/phases/03-live-verification.md +3 -3
  78. package/skills/qa-verify-backend/phases/03b-api-verification.md +22 -9
  79. package/skills/qa-verify-backend/phases/04-e2e-trigger.md +18 -2
  80. package/skills/qa-verify-backend/phases/05-reporting.md +38 -10
  81. package/skills/qa-verify-backend/references/api-probes.md +28 -1
  82. package/skills/qa-verify-backend/references/payload-verification.md +1 -1
  83. package/skills/qa-verify-backend/references/release-readiness.md +1 -1
  84. package/skills/qa-verify-backend/references/safety-rules.md +13 -8
  85. package/data/domains/_default.md +0 -181
  86. package/data/domains/ecommerce.md +0 -192
  87. package/data/domains/fintech.md +0 -200
  88. package/data/domains/identity.md +0 -88
  89. package/data/domains/marketing.md +0 -194
  90. package/data/domains/saas.md +0 -197
  91. package/dist/cli/index.d.ts +0 -1
  92. package/dist/cli/index.js.map +0 -1
  93. package/dist/index.js.map +0 -1
@@ -1,6 +1,6 @@
1
- # Phase 1: Authentication
1
+ # Phase 1: Authentication (2 min)
2
2
 
3
- Skip if `auth.strategy: none`. Otherwise:
3
+ Skip if `auth.strategy: none`. Every command below carries the session id `-s=<sid>` (omitted here).
4
4
 
5
5
  ## Storage State (fastest)
6
6
 
@@ -9,30 +9,47 @@ playwright-cli state-load .auth/<target>.json
9
9
  playwright-cli goto <base_url>
10
10
  ```
11
11
 
12
- ## Credentials (adaptive -- uses snapshot to find form fields)
12
+ If the state file is older than 24 hours, expect it to have expired and fall through to
13
+ credentials when the login page appears.
13
14
 
14
- Before filling credentials, resolve their values:
15
- 1. If `qa/.env` exists in CWD, read it — use the values for the env var names specified in `auth.credentials.username` / `auth.credentials.password` in the target config
16
- 2. Otherwise read from the skill root `.env`
15
+ ## Credentials (adaptive: uses snapshot to find form fields)
16
+
17
+ Resolve the values named by `auth.credentials.username` / `auth.credentials.password` in the
18
+ order from `${CLAUDE_SKILL_DIR}/references/paths.md` (`qa/.env`, then `.env`). Read the value,
19
+ pass it to the command, and never echo it into the log or the report.
17
20
 
18
21
  ```bash
19
22
  playwright-cli open <login_url>
20
23
  playwright-cli snapshot
21
- playwright-cli fill <email_ref> "$QA_USER"
22
- playwright-cli fill <pass_ref> "$QA_PASS"
24
+ playwright-cli fill <email_ref> "<username value>"
25
+ playwright-cli fill <pass_ref> "<password value>"
23
26
  playwright-cli click <submit_ref>
24
27
  playwright-cli state-save .auth/<target>.json
25
28
  ```
26
29
 
30
+ ## Token (`auth.strategy: token`)
31
+
32
+ Inject the token named by `auth.token` where the app expects it, then reload:
33
+
34
+ ```bash
35
+ playwright-cli open <base_url>
36
+ playwright-cli cookie-set <cookie-name> "<token value>" --domain=<host> --httpOnly --secure # cookie-based
37
+ playwright-cli localstorage-set <key> "<token value>" # localStorage-based
38
+ playwright-cli reload
39
+ ```
40
+
27
41
  ## Verify Login
28
42
 
29
- After authentication, verify login via `playwright-cli snapshot` -- confirm user indicators are present (e.g., username display, avatar, dashboard access).
43
+ After authentication, `playwright-cli snapshot` and confirm user indicators are present
44
+ (username display, avatar, dashboard access).
30
45
 
31
46
  If login fails:
32
- 1. Check console for errors: `playwright-cli console error`
33
- 2. Verify credentials are correct
34
- 3. Check for MFA requirements
35
- 4. Log the failure and attempt alternative auth strategy if available
36
-
37
- **Update progress:** Set auth phase complete (or failed) in progress.json. Append to session-log.md:
47
+ 1. Check the console: `playwright-cli console error`
48
+ 2. Check the last requests: `playwright-cli requests --filter="login|auth|session"`
49
+ 3. Verify the credentials are the ones the target names
50
+ 4. Check for MFA. Never automate an MFA challenge; hand it to the user in a headed browser
51
+ (`playwright-cli open <login_url> --headed`) and continue once they confirm
52
+ 5. Log the failure and attempt an alternative strategy if the target defines one
53
+
54
+ **Update progress:** set the auth phase complete (or failed) in `progress.json`. Append to `session-log.md`:
38
55
  `[<timestamp>] [PHASE] Auth complete — strategy: <strategy>, result: <success/failed>, user: <redacted>`
@@ -1,10 +1,10 @@
1
- # Phase 2: Business Context & Charter (~5 min)
1
+ # Phase 2: Business Context & Charter (5 min)
2
2
 
3
3
  **This is the most important phase. Skip it and everything else is shallow.**
4
4
 
5
5
  ## Step 1: Use the App as a Real User
6
6
 
7
- Before any testing, spend 2-3 minutes USING the app the way a customer would. Not testing -- USING.
7
+ Before any testing, spend 2 minutes USING the app the way a customer would. Not testing -- USING.
8
8
 
9
9
  ```bash
10
10
  playwright-cli open <url>
@@ -62,9 +62,12 @@ Also select 2 Test Tours:
62
62
 
63
63
  ## Step 5: Write Charter
64
64
 
65
- Save to `output/sessions/<session-dir>/charter.md`:
65
+ Save to `output/sessions/<session-dir>/charter.md` (confidentiality header first, per `${CLAUDE_SKILL_DIR}/references/output-contract.md`):
66
66
 
67
67
  ```markdown
68
+ > CONFIDENTIAL: This report may contain internal URLs, security vulnerabilities,
69
+ > and application details. Do not share outside your organization without review.
70
+
68
71
  # Session Charter
69
72
 
70
73
  ## Context Source
@@ -101,12 +104,20 @@ Save to `output/sessions/<session-dir>/charter.md`:
101
104
  - FEW HICCUPPS oracles: Focus on [Users, Claims, Product]
102
105
 
103
106
  ## Session Parameters
104
- - Time box: [duration]
107
+ - Time box: 45 min
105
108
  - Domain: [domain]
106
109
  - Focus: [focus area or "full exploration"]
110
+ - Read-only: [true | false]
111
+ ```
112
+
113
+ Start evidence capture (both carry `-s=<sid>`):
114
+
115
+ ```bash
116
+ playwright-cli tracing-start
117
+ playwright-cli video-start output/sessions/<session-dir>/videos/session.webm
107
118
  ```
108
119
 
109
- Start trace: `playwright-cli tracing-start`
120
+ Add `playwright-cli video-chapter "<phase or feature>"` at each phase boundary so the recording is navigable.
110
121
 
111
122
  **Update progress:** Set charter phase complete in progress.json. Append to session-log.md:
112
123
  `[<timestamp>] [PHASE] Charter complete — risk ranking defined, <N> journeys planned, heuristics: <selected>`
@@ -1,6 +1,6 @@
1
- # Phase 3: Discovery & Mapping (~15% of time)
1
+ # Phase 3: Discovery & Mapping (6 min)
2
2
 
3
- **Goal:** Map the app structure and refine your risk ranking.
3
+ **Goal:** Map the app structure and refine your risk ranking. Every command carries `-s=<sid>` (omitted here).
4
4
 
5
5
  ## Site Mapping
6
6
 
@@ -8,56 +8,80 @@
8
8
  playwright-cli goto <start_url>
9
9
  playwright-cli snapshot
10
10
  playwright-cli console error
11
- playwright-cli network
11
+ playwright-cli requests
12
12
  ```
13
13
 
14
14
  For each page:
15
- 1. `playwright-cli snapshot` -- note structure, forms, interactive elements
16
- 2. Click through navigation to discover all sections
15
+ 1. `playwright-cli snapshot` — note structure, forms, interactive elements. Use `snapshot --depth=3` on very large pages, then `snapshot <ref>` for the region you care about.
16
+ 2. Click through navigation to discover all sections.
17
17
  3. Log: `[DISCOVERED] <url> -- <description> -- Risk: <P0/P1/P2/P3>`
18
- 4. Check `playwright-cli console error` on each page
18
+ 4. Check `playwright-cli console error` and `playwright-cli requests` on each page.
19
+
20
+ Useful helpers:
21
+ - `playwright-cli find "<text>"` (or `find --regex "<re>"`) — locate a label or message in the snapshot without reading the whole tree.
22
+ - `playwright-cli --raw snapshot > before.yml`, act, `playwright-cli --raw snapshot > after.yml`, then `diff before.yml after.yml` — see exactly what an action changed.
23
+ - `playwright-cli requests --filter="/api/"` — only the calls that matter; `playwright-cli request <n>` for headers and body of one of them.
19
24
 
20
25
  ## Scope Enforcement
21
26
 
22
- Stay within the target domain. Do not follow links to external sites unless they are part of the application's workflow (e.g., OAuth redirects, payment gateways).
27
+ Stay within the target domain. Do not follow links to external sites unless they are part of
28
+ the application's workflow (OAuth redirects, payment gateways).
23
29
 
24
30
  ## What's MISSING Check
25
31
 
26
- **Critical during discovery -- look for what's MISSING:**
27
- - Read the domain completeness checklist from `data/domains/<domain>.md` (or the corresponding `.yml`)
28
- - Compare what the app HAS vs what it SHOULD have
29
- - E-commerce missing payment method? Log it now.
32
+ **Critical during discovery — look for what's MISSING:**
33
+ - Read the domain completeness checklist from `<data>/domains/<domain>.yml` (`completeness_checklist`)
34
+ - Compare what the app HAS against what it SHOULD have
35
+ - E-commerce missing a payment method? Log it now.
30
36
  - Banking app missing transaction history? Flag it immediately.
31
37
  - No error messages on empty states? Note it.
32
38
 
33
39
  ## Console & Network Checks
34
40
 
35
41
  On every page during discovery:
36
- - `playwright-cli console error` -- log any JavaScript errors
37
- - `playwright-cli network` -- note any failed requests (4xx, 5xx)
38
- - Watch for mixed content warnings (HTTP resources on HTTPS pages)
42
+ - `playwright-cli console error` — JavaScript errors
43
+ - `playwright-cli requests` — failed requests (4xx, 5xx); `requests --static` to include assets
44
+ - Watch for mixed-content warnings (HTTP resources on HTTPS pages)
45
+
46
+ ### Cross-navigation observation via `run-code` (Playwright 1.59+)
39
47
 
40
- ### API-level observation helpers (optional, Playwright 1.56+)
48
+ The CLI's `console` and `requests` show only the tail since the last navigation. To reach
49
+ messages from *before* it, run Playwright's retrieval methods inside the session with
50
+ `run-code` (the callback receives the live `page`) and pass `filter: 'all'` — **without it
51
+ they default to `since-navigation` and return exactly the same window as the CLI**. The
52
+ buffers are capped: 200 console messages, 200 page errors, 100 requests.
41
53
 
42
- If the session has access to the `@playwright/test` peer dep AND is running inside a Playwright test context (rare for qa-explore, common for bug-reproduction follow-ups), the following 1.56 retrieval methods can be used alongside the CLI commands above:
54
+ ```bash
55
+ # every console message still buffered, across navigations
56
+ playwright-cli run-code "async page => (await page.consoleMessages({ filter: 'all' })).map(m => m.type() + ': ' + m.text()).join('\n')"
43
57
 
44
- - `await page.consoleMessages()` — returns all console messages captured so far on the page. Useful when you need the full history rather than the most-recent tail.
45
- - `await page.pageErrors()` — returns runtime page errors (uncaught exceptions). More reliable than filtering `console error` output.
46
- - `await page.requests()` — returns all network requests issued by the page, with status, resource type, and timing. Use this for a single network snapshot instead of parsing `playwright-cli network` output twice.
58
+ # uncaught exceptions only — more reliable than filtering console output
59
+ playwright-cli run-code "async page => (await page.pageErrors({ filter: 'all' })).map(e => e.message).join('\n')"
60
+
61
+ # failures and error statuses among the last 100 requests (page.requests() takes no filter)
62
+ playwright-cli run-code "async page => { const out = []; for (const r of await page.requests()) { const res = await r.response(); const f = r.failure(); if (f) out.push('FAILED ' + f.errorText + ' ' + r.url()); else if (res && res.status() >= 400) out.push(res.status() + ' ' + r.url()); } return out.join('\n'); }"
63
+ ```
47
64
 
48
- These are OPTIONAL and only apply when exploratory testing is done from a Playwright test harness. The bash `playwright-cli` commands above remain the primary path for the skill.
65
+ These are optional; the bash commands above remain the primary path.
49
66
 
50
- ### Service Workers (Playwright 1.56+)
67
+ ### Service Workers (Playwright 1.61+)
51
68
 
52
- Playwright 1.56 added Service Worker network routing. If `playwright-cli network` shows requests you cannot account for on the main document, assume a Service Worker is intercepting them and flag this as a high-risk area worth re-testing with the route filter.
69
+ Service-worker requests are reported and routable at the **BrowserContext** level from 1.61.
70
+ `playwright-cli route` maps to `page.route()`, which per the API docs still does **not**
71
+ intercept service-worker traffic. So if `playwright-cli requests` shows calls you cannot
72
+ account for on the main document, assume a service worker is serving them: flag the area as
73
+ high-risk, and note in the report that mocking it needs service workers blocked
74
+ (`serviceWorkers: 'block'`), not `route`.
53
75
 
54
76
  ## After Discovery
55
77
 
56
- 1. Write findings to `phase-1-discovery.md`
78
+ 1. Write findings to `phase-3-discovery.md` (confidentiality header first)
57
79
  2. **Update your risk ranking** if discovery changed your understanding
58
- 3. Carry forward: site map summary, risk ranking, list of what's missing
80
+ 3. Carry forward: site-map summary, risk ranking, list of what's missing
59
81
 
60
- **Log your reasoning:** "I expected a payment method selector in checkout because this is e-commerce, but it's missing. I'll flag this as a medium bug."
82
+ **Log your reasoning:** "I expected a payment-method selector in checkout because this is
83
+ e-commerce, but it's missing. I'll flag this as a medium bug."
61
84
 
62
- **Update progress:** Set discovery phase complete in progress.json with pages_explored count. Append to session-log.md:
85
+ **Update progress:** set the discovery phase complete in `progress.json` with the
86
+ `pages_explored` count. Append to `session-log.md`:
63
87
  `[<timestamp>] [PHASE] Discovery complete — <N> pages mapped, <N> console errors, <N> missing checklist items, <N> bugs so far`
@@ -1,4 +1,4 @@
1
- # Phase 4: End-to-End User Journeys (~25% of time)
1
+ # Phase 4: End-to-End User Journeys (10 min)
2
2
 
3
3
  **Goal:** Test the critical user journeys you defined in the charter -- end to end, crossing multiple features.
4
4
 
@@ -43,7 +43,7 @@ Do things change? Are order IDs unique? Are timestamps correct?
43
43
 
44
44
  ## After Journeys
45
45
 
46
- 1. Write findings to `phase-2-user-journeys.md`
46
+ 1. Write findings to `phase-4-journeys.md` (confidentiality header first)
47
47
  2. Include data integrity results
48
48
  3. Note any cross-feature inconsistencies
49
49
 
@@ -1,8 +1,9 @@
1
- # Phase 5: Deep Feature Testing (~25% of time)
1
+ # Phase 5: Deep Feature Testing (10 min)
2
2
 
3
- **Goal:** Go deep on P0 and P1 features. Spend time proportional to risk.
3
+ **Goal:** Go deep on P0 and P1 features. Spend time proportional to risk. Every command carries `-s=<sid>` (omitted here).
4
4
 
5
- Focus on the features your risk ranking identified as P0/P1. Apply SFDIPOT, but only the dimensions you selected in the charter.
5
+ Focus on the features your risk ranking identified as P0/P1. Apply SFDIPOT, but only the
6
+ dimensions you selected in the charter.
6
7
 
7
8
  ## For Each P0/P1 Feature
8
9
 
@@ -21,55 +22,69 @@ playwright-cli fill <ref> "a" # Minimum
21
22
  playwright-cli fill <ref> "<1000+ chars>" # Maximum
22
23
  ```
23
24
 
24
- ### Business Logic Stress (from knowledge base)
25
+ ### Business Logic Stress (from the knowledge base)
25
26
 
26
- - **Wrong state order:** Skip a step in a multi-step flow -- navigate directly to confirmation
27
- - **Parameter tampering:** Change values that should be server-controlled
27
+ - **Wrong state order:** skip a step in a multi-step flow; navigate directly to confirmation
28
+ - **Parameter tampering:** change values that should be server-controlled
28
29
  ```bash
30
+ playwright-cli fill <ref> "-100" # preferred: types, so framework handlers fire
29
31
  playwright-cli eval "document.querySelector('input[name=amount]').value = '-100'"
30
32
  ```
31
- - **Replay:** Complete an action, then try to complete it again immediately
32
- - **Self-referential:** Transfer from account A to account A. Apply discount code twice.
33
+ The `eval` form assigns `.value` without dispatching `input`/`change`, so a
34
+ React/Vue-controlled field reverts on the next render — prefer `fill`, and tamper at the
35
+ network layer (`route`) when the value is genuinely server-controlled.
36
+ - **Replay:** complete an action, then try to complete it again immediately
37
+ - **Self-referential:** transfer from account A to account A; apply a discount code twice
33
38
 
34
39
  ### Negative Space Check
35
40
 
36
41
  - For EACH form, ask: "What fields should be here that aren't?"
37
42
  - For EACH flow, ask: "What steps are missing?"
38
- - Compare against domain checklist
43
+ - Compare against the domain checklist (`<data>/domains/<domain>.yml`)
39
44
 
40
45
  ### Consistency Oracles (FEW HICCUPPS)
41
46
 
42
47
  After testing each feature, explicitly ask:
43
- - **Users:** "Would a real user expect this behavior?"
48
+ - **Users:** "Would a real user expect this behaviour?"
44
49
  - **Claims:** "Does this match what the app promises?"
45
50
  - **Product:** "Is this consistent with how other features in the app work?"
46
51
  - **Standards:** "Does this meet industry standards for this domain?"
47
52
 
48
- If you notice an inconsistency (e.g., "Bill Pay validates but Transfer doesn't"), **follow that thread** -- don't move on. The inconsistency is a signal.
53
+ If you notice an inconsistency ("Bill Pay validates but Transfer doesn't"), **follow that
54
+ thread**; don't move on. The inconsistency is a signal.
49
55
 
50
- ### Locator Stabilization Helpers (Playwright 1.59+, optional)
56
+ ### Stable locators for the bug report
51
57
 
52
- When testing a feature produces flaky snapshots because a locator isn't uniquely addressable, the following 1.59 helpers can harden the repro before you file a bug. They require the `@playwright/test` peer dep.
58
+ A reproduction step must name the element unambiguously. When a ref is ambiguous:
53
59
 
54
- - `page.pickLocator()` — interactive locator picker. Use this when your current locator matches multiple elements and you need to find the one the user actually sees.
55
- - `locator.normalize()` — returns a cleaned-up, canonical form of a locator. Use before copying a locator into a bug report so the reproduction is portable across runs.
60
+ ```bash
61
+ playwright-cli generate-locator <ref> # a Playwright locator for the element behind the ref
62
+ playwright-cli highlight <ref> # confirm visually which element you mean, then
63
+ playwright-cli highlight --hide
64
+ ```
56
65
 
57
- These are diagnostic aids, not required steps. The bash `playwright-cli` flow above is the primary path.
66
+ Paste the generated locator into the bug's steps. `page.pickLocator()` (Playwright 1.59)
67
+ exists for the same purpose but is **human-only**: it opens an interactive picker in a headed
68
+ browser and waits for a click, so it is not usable from an agent session.
58
69
 
59
70
  ### Test Agents Handoff (optional, Playwright 1.56+)
60
71
 
61
- When feature testing produces a **reproducible** bug (you can trigger it twice in a row, same steps, same result), you may hand off to the Playwright Test Agents **generator** to convert the reproduction into a regression test case:
72
+ When feature testing produces a **reproducible** bug (you can trigger it twice in a row,
73
+ same steps, same result), you may hand it off after the session to the Playwright Test
74
+ Agents **generator** to convert the reproduction into a regression test:
62
75
 
63
- 1. Finish writing the bug report with exact steps (see phase 07).
64
- 2. If the session's Step 6 bootstrapped Test Agents, pass the repro steps to the generator agent.
65
- 3. The generator produces a `tests/repro-<bug-id>.spec.ts` you can commit alongside the bug report.
66
- 4. The **healer** agent can later be used by the team if the test becomes flaky.
76
+ 1. Finish the bug report with exact steps (phase 7).
77
+ 2. If Step 6 of setup bootstrapped Test Agents, pass the bug report to the generator agent.
78
+ 3. The generator produces a `tests/repro-BUG-NNN.spec.ts` you can commit alongside the bug report.
79
+ 4. The **healer** agent later repairs the test if it breaks for non-bug reasons.
67
80
 
68
- Full workflow in `../references/playwright-agents-integration.md`. This handoff is **opt-in** — it does not replace the bug report and is skipped entirely when `@playwright/test` is not installed.
81
+ Full workflow in `${CLAUDE_SKILL_DIR}/references/playwright-agents-integration.md`. This
82
+ handoff is **opt-in**; it does not replace the bug report and is skipped entirely when
83
+ `@playwright/test` is not installed.
69
84
 
70
85
  ## After Feature Testing
71
86
 
72
- Write to `phase-3-feature-testing.md`. Include reasoning for each test.
87
+ Write `phase-5-features.md` (confidentiality header first). Include the reasoning for each test.
73
88
 
74
- **Update progress:** Set features phase complete in progress.json. Append to session-log.md:
89
+ **Update progress:** set the features phase complete in `progress.json`. Append to `session-log.md`:
75
90
  `[<timestamp>] [PHASE] Features complete — <N> P0 features tested, <N> P1 features tested, <N> inconsistencies found, <N> bugs so far`
@@ -1,6 +1,6 @@
1
- # Phase 6: Edge Cases, Security & Negative Testing (~20% of time)
1
+ # Phase 6: Edge Cases, Security & Negative Testing (6 min)
2
2
 
3
- **Goal:** Saboteur tour -- actively try to break things.
3
+ **Goal:** Saboteur tour: actively try to break things. Every command carries `-s=<sid>` (omitted here). In read-only mode, fill but never submit.
4
4
 
5
5
  ## Input Attacks (from error-guessing knowledge)
6
6
 
@@ -17,15 +17,21 @@ playwright-cli fill <ref> " "
17
17
  playwright-cli fill <ref> "A repeated 5000 times..."
18
18
  ```
19
19
 
20
+ After an XSS payload, check whether it executed: `playwright-cli console error` plus
21
+ `playwright-cli run-code "async page => (await page.pageErrors()).length"`, and look for a
22
+ dialog (`dialog-dismiss` if one opened).
23
+
20
24
  ## Race Conditions (if applicable)
21
25
 
22
26
  ```bash
23
- # Open a second session
24
- playwright-cli -s=race open <url>
25
- playwright-cli -s=race state-load .auth/<target>.json
26
- # Set up identical action in both sessions
27
+ # Open a second, separately isolated session alongside the main one
28
+ playwright-cli -s=<sid>-race open <url>
29
+ playwright-cli -s=<sid>-race state-load .auth/<target>.json
30
+ # Set up the identical action in both sessions
27
31
  # Submit both as close to simultaneously as possible
28
- # Check for double-processing
32
+ # Check for double-processing, then close the second session:
33
+ playwright-cli -s=<sid>-race close
34
+ playwright-cli -s=<sid>-race delete-data
29
35
  ```
30
36
 
31
37
  ## State Manipulation
@@ -33,14 +39,15 @@ playwright-cli -s=race state-load .auth/<target>.json
33
39
  - Navigate directly to pages that require prior steps
34
40
  - Use browser back/forward mid-flow
35
41
  - Double-click submit buttons
36
- - Simulate network errors: `playwright-cli route "**/*" --status=500`
42
+ - Simulate network errors: `playwright-cli route "**/*" --status=500` (then `playwright-cli unroute` to restore)
43
+ - Simulate offline: `playwright-cli network-state-set offline` / `online`
37
44
 
38
45
  ## Security
39
46
 
40
47
  - Check for session tokens in URLs
41
48
  - Try accessing admin/internal pages directly
42
- - Check if authenticated endpoints work without auth
43
- - Test brute force: 5+ failed login attempts -- check for lockout
49
+ - Check whether authenticated endpoints work without auth (`playwright-cli -s=<sid>-anon open <api-url>` in a fresh session, then close and `delete-data` it)
50
+ - Test brute force: 5+ failed login attempts; check for lockout
44
51
 
45
52
  ## Accessibility (quick check)
46
53
 
@@ -54,7 +61,11 @@ playwright-cli snapshot
54
61
  playwright-cli resize 1280 720 # restore
55
62
  ```
56
63
 
57
- > **Note on `page.accessibility` (Playwright 1.57 deprecation):** Upstream Playwright deprecated the `page.accessibility` snapshot API in 1.57. The replacement, available as of Playwright 1.59, is `page.ariaSnapshot()` — an aria-tree-based accessibility snapshot that is both more accurate and directly usable as a locator base. If a session upgrades to deeper a11y checks than the quick-pass above, prefer `page.ariaSnapshot()` over `page.accessibility`. The CLI checks above are unaffected and remain the primary path. See `../references/playwright-agents-integration.md` for a feature cross-reference.
64
+ The CLI `snapshot` **is** an aria snapshot: roles, names and states as assistive technology
65
+ sees them, so missing names and duplicate landmarks show up directly. For the raw YAML aria
66
+ tree of a region, `playwright-cli run-code "async page => page.locator('main').ariaSnapshot()"`.
67
+ Note: Playwright **removed** `page.accessibility` in 1.57; anything still calling it will
68
+ throw.
58
69
 
59
70
  ## Empty States
60
71
 
@@ -65,7 +76,7 @@ playwright-cli resize 1280 720 # restore
65
76
 
66
77
  ## After Edge Cases
67
78
 
68
- Write to `phase-4-edge-cases.md`.
79
+ Write `phase-6-edge-cases.md` (confidentiality header first).
69
80
 
70
- **Update progress:** Set edge_cases phase complete in progress.json. Append to session-log.md:
81
+ **Update progress:** set the edge_cases phase complete in `progress.json`. Append to `session-log.md`:
71
82
  `[<timestamp>] [PHASE] Edge cases complete — <N> input attacks, <N> security checks, <N> a11y checks, <N> bugs so far`