qualiow-exploratory-testing 2.2.1 → 2.3.1

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 (44) hide show
  1. package/.claude-plugin/marketplace.json +1 -1
  2. package/.claude-plugin/plugin.json +1 -1
  3. package/.env.example +6 -0
  4. package/CHANGELOG.md +183 -0
  5. package/README.md +110 -27
  6. package/agents/qa-bug-judge.md +115 -0
  7. package/agents/qa-diff-indexer-agent.md +1 -1
  8. package/agents/qa-gather-agent.md +1 -1
  9. package/agents/qa-reporting-agent.md +15 -4
  10. package/bin/mobile-cli.mjs +74 -26
  11. package/bin/qualiow +7 -2
  12. package/bin/wk-ios +60 -6
  13. package/bin/wkeval.mjs +7 -2
  14. package/data/security/SECURITY-POLICY.md +17 -1
  15. package/data/templates/bug-report.md +11 -0
  16. package/data/templates/session-report.md +12 -4
  17. package/dist/cli/index.js +1660 -85
  18. package/dist/index.d.ts +623 -2
  19. package/dist/index.js +1626 -47
  20. package/docs/GETTING-STARTED.md +44 -12
  21. package/docs/MOBILE-SETUP.md +31 -0
  22. package/hooks/hooks.json +12 -2
  23. package/hooks/scripts/bash-guard.mjs +242 -0
  24. package/hooks/scripts/secret-patterns.d.mts +4 -1
  25. package/hooks/scripts/secret-patterns.mjs +126 -34
  26. package/hooks/scripts/write-guard.mjs +70 -15
  27. package/package.json +2 -2
  28. package/skills/qa-explore/SKILL.md +9 -5
  29. package/skills/qa-explore/phases/00-setup.md +9 -1
  30. package/skills/qa-explore/phases/07-reporting.md +186 -11
  31. package/skills/qa-explore/references/delegation-rules.md +21 -2
  32. package/skills/qa-explore/references/evidence-triage.md +213 -0
  33. package/skills/qa-explore/references/output-contract.md +41 -8
  34. package/skills/qa-explore/references/security-rules.md +31 -2
  35. package/skills/qa-explore-cleanup/SKILL.md +1 -1
  36. package/skills/qa-explore-mobile/SKILL.md +13 -3
  37. package/skills/qa-explore-mobile/references/mobile-edges.md +3 -1
  38. package/skills/qa-explore-quick/SKILL.md +1 -1
  39. package/skills/qa-explore-report/SKILL.md +4 -2
  40. package/skills/qa-gather/SKILL.md +1 -1
  41. package/skills/qa-knowledge-add/SKILL.md +1 -1
  42. package/skills/qa-knowledge-list/SKILL.md +1 -1
  43. package/skills/qa-verify-backend/SKILL.md +1 -1
  44. package/skills/qa-verify-backend/phases/05-reporting.md +2 -1
@@ -1,18 +1,46 @@
1
1
  /**
2
2
  * Secret detection for the write-guard hook.
3
3
  *
4
- * Mirrors the categories and patterns in `src/utils/redact.ts` as closely as
5
- * possible, so a hook denial matches what `qualiow session finalize --redact`
6
- * would flag on the same text. Kept as a standalone, dependency-free ES
7
- * module (Node built-ins only, no TS import) because a git-sourced plugin
8
- * install has neither `dist/` nor `node_modules` to pull the real util from.
4
+ * Carries the same rules as `src/utils/redact.ts`, regex for regex and in the
5
+ * same order (`tests/unit/redact-hardening.test.ts` compares the sources), so a
6
+ * hook denial matches what `qualiow session finalize --redact` would flag on
7
+ * the same text. Kept as a standalone, dependency-free ES module (Node
8
+ * built-ins only, no TS import) because a git-sourced plugin install has
9
+ * neither `dist/` nor `node_modules` to pull the real util from.
10
+ *
11
+ * Every pattern must stay linear on adversarial input: the hook has a timeout,
12
+ * and a hook that times out fails open.
9
13
  *
10
14
  * `findSecretCategories` never returns the matched text itself — only
11
15
  * category names — so the hook that calls it can safely put the result in a
12
16
  * denial reason without leaking the secret it found.
13
17
  */
14
18
 
15
- const EMAIL_ALLOW = /(?:@|\.)(?:example\.(?:com|org|net)|localhost)$/i;
19
+ // Documentation domains only, matched exactly: `x@corp.example.com` is flagged.
20
+ const EMAIL_ALLOW = /@(?:example\.(?:com|org|net)|localhost)$/i;
21
+
22
+ // A value that is nothing but a redaction placeholder (optionally quoted, optionally
23
+ // after an auth scheme) is already clean; anything more than that is not.
24
+ const REDACTED_VALUE =
25
+ /^\s*\\?["']?(?:(?:bearer|basic|token|digest)\s+)?\[[A-Z0-9_]*REDACTED\]\\?["']?\s*$/i;
26
+ const JSON_LITERAL = /^(?:null|true|false)$/i;
27
+
28
+ const QUOTED = String.raw`\\"[^"\\\n]{1,4096}\\"|"(?:[^"\\\n]|\\.){1,4096}"|'(?:[^'\\\n]|\\.){1,4096}'`;
29
+ const LOOSE = String.raw`["']?[^\s,}"']+`;
30
+ const TOKENISH = String.raw`["']?[^\s,;}"'|]{8,}`;
31
+ const LINE_REST = String.raw`[^\s|](?:[^\r\n|]*[^\s|])?`;
32
+
33
+ function kv(keys, value, sepOps = ':=') {
34
+ return new RegExp(
35
+ String.raw`(${keys})((?:\\?["']|\*\*)?[ \t]*[${sepOps}][ \t]*(?:\*\*[ \t]*)?)(${QUOTED}|${value})`,
36
+ 'gi',
37
+ );
38
+ }
39
+
40
+ const PEM_HEAD = String.raw`-----BEGIN (?:[A-Z0-9]{1,20} ){0,3}PRIVATE KEY(?: BLOCK)?-----`;
41
+ const PEM_TAIL = String.raw`-----END (?:[A-Z0-9]{1,20} ){0,3}PRIVATE KEY(?: BLOCK)?-----`;
42
+ const NL = String.raw`(?:\r?\n|\\n)`;
43
+ const PEM_BODY = String.raw`(?:${NL}[ \t]*(?:(?:Proc-Type|DEK-Info|Version|Comment|Hash|Charset): [^\r\n]{0,256}|[A-Za-z0-9+/=]+(?:\.{2,}|…)?[ \t]*(?=${NL}|$|["'])|(?=${NL}|$)))*`;
16
44
 
17
45
  function luhnValid(digits) {
18
46
  let sum = 0;
@@ -31,29 +59,46 @@ function luhnValid(digits) {
31
59
  return sum % 10 === 0;
32
60
  }
33
61
 
62
+ // Key/value rules: the third group is the value; one that is already a placeholder is clean.
63
+ const keyValueFilter = (_match, _key, _sep, value) =>
64
+ !REDACTED_VALUE.test(value) && !JSON_LITERAL.test(value);
65
+
34
66
  /**
35
67
  * category: name surfaced in denial reasons (never the matched text).
36
- * re: detection pattern (mirrors redact.ts; capture groups dropped since
37
- * only presence, not replacement, is needed here).
38
- * filter(match): optional extra check a raw regex match can't express
39
- * (Luhn validity, the example.com/localhost allow-list).
68
+ * re: detection pattern (identical to the redact.ts rule of the same name).
69
+ * filter(match, ...groups): optional extra check a raw regex match can't
70
+ * express (Luhn validity, the example.com allow-list, a value that is
71
+ * already a redaction placeholder).
40
72
  */
41
73
  export const SECRET_PATTERNS = [
42
74
  {
43
75
  category: 'Private key',
44
- re: /-----BEGIN (?:[A-Z0-9 ]+ )?PRIVATE KEY-----[\s\S]*?-----END (?:[A-Z0-9 ]+ )?PRIVATE KEY-----/g,
76
+ re: new RegExp(
77
+ String.raw`${PEM_HEAD}(?:(?:(?!-----BEGIN )[\s\S]){0,16384}?${PEM_TAIL}|${PEM_BODY})`,
78
+ 'g',
79
+ ),
45
80
  },
46
81
  {
47
82
  category: 'JWT',
48
- re: /\beyJ[A-Za-z0-9_-]{8,}\.[A-Za-z0-9_-]{6,}\.[A-Za-z0-9_-]{6,}\b/g,
83
+ re: /(?<![A-Za-z0-9_-])eyJ[A-Za-z0-9_-]{8,}\.(?:[A-Za-z0-9_-]{6,}\.[A-Za-z0-9_-]{6,}|eyJ[A-Za-z0-9_-]{6,}(?:\.[A-Za-z0-9_-]*)?)/g,
49
84
  },
50
85
  {
51
86
  category: 'Authorization header',
52
- re: /authorization\s*[:=]\s*\S[^\n\r]*/gi,
87
+ re: kv('authorization', LINE_REST),
88
+ filter: keyValueFilter,
53
89
  },
54
90
  {
55
91
  category: 'Cookie header',
56
- re: /^(?:set-cookie|cookie)\s*:\s*.+$/gim,
92
+ re: kv('set-cookie|cookie', String.raw`[^\s|=]{1,256}=(?:[^\r\n|]*[^\s|])?`, ':=|'),
93
+ filter: keyValueFilter,
94
+ },
95
+ {
96
+ category: 'Bearer token',
97
+ re: /\b(bearer|basic)([ \t]+)(?:(?=[A-Za-z._~+/-]*[0-9=])[A-Za-z0-9._~+/=-]{8,}|[A-Za-z0-9._~+/=-]{24,})/gi,
98
+ },
99
+ {
100
+ category: 'AWS secret access key',
101
+ re: /(\b(?:AKIA|ASIA)[0-9A-Z]{16}\b|\[AWS_KEY_REDACTED\])([\s,;:|"'=]{1,8})[A-Za-z0-9/+]{40}(?![A-Za-z0-9/+=])/g,
57
102
  },
58
103
  {
59
104
  category: 'AWS access key id',
@@ -61,45 +106,77 @@ export const SECRET_PATTERNS = [
61
106
  },
62
107
  {
63
108
  category: 'AWS secret access key',
64
- re: /aws_secret_access_key\s*[:=]\s*\S+/gi,
109
+ re: kv(String.raw`aws_secret_access_key|secret_?access_?key`, String.raw`["']?[^\s,;}"']+`),
110
+ filter: keyValueFilter,
111
+ },
112
+ {
113
+ category: 'AWS session token',
114
+ re: kv(
115
+ String.raw`aws_session_token|session_?token|x-amz-security-token|security_?token`,
116
+ String.raw`["']?[^\s,;}"']+`,
117
+ ),
118
+ filter: keyValueFilter,
65
119
  },
66
120
  {
67
121
  category: 'OpenAI-style key',
68
- re: /\bsk-(?:proj-)?[A-Za-z0-9_-]{20,}\b/g,
122
+ re: /(?<![A-Za-z0-9_-])sk-(?:proj-)?[A-Za-z0-9_-]{20,}/g,
123
+ },
124
+ {
125
+ category: 'Stripe key',
126
+ re: /(?<![A-Za-z0-9_])(?:(?:sk|rk)_(?:live|test)_[A-Za-z0-9]{10,}|whsec_[A-Za-z0-9+/=]{16,})/g,
69
127
  },
70
128
  {
71
129
  category: 'GitHub token',
72
130
  re: /\b(?:gh[pousr]_[A-Za-z0-9]{20,}|github_pat_[A-Za-z0-9_]{20,})\b/g,
73
131
  },
132
+ {
133
+ category: 'GitLab token',
134
+ re: /(?<![A-Za-z0-9_-])glpat-[A-Za-z0-9_-]{20,}/g,
135
+ },
136
+ {
137
+ category: 'npm token',
138
+ re: /\bnpm_[A-Za-z0-9]{36}\b/g,
139
+ },
140
+ {
141
+ category: 'Google API key',
142
+ re: /\bAIza[0-9A-Za-z_-]{35}/g,
143
+ },
144
+ {
145
+ category: 'Google OAuth token',
146
+ re: /\bya29\.[0-9A-Za-z_-]{20,}/g,
147
+ },
74
148
  {
75
149
  category: 'Slack token',
76
- re: /\bxox[abposr]-[A-Za-z0-9-]{10,}\b/g,
150
+ re: /(?<![A-Za-z0-9-])xox[abposre](?:\.xox[a-z])?-[A-Za-z0-9-]{10,}/g,
151
+ },
152
+ {
153
+ category: 'Slack webhook',
154
+ re: /(?:(?:https?:\/\/)?hooks\.slack\.com)?\/services\/T[A-Z0-9]{6,}\/B[A-Z0-9]{6,}\/[A-Za-z0-9]{16,}/g,
77
155
  },
78
156
  {
79
157
  category: 'API key',
80
- re: /(?:x-api-key|api[_-]?key)\s*[:=]\s*["']?[A-Za-z0-9._-]{8,}["']?/gi,
158
+ re: kv(String.raw`x-api-key|api[_-]?key`, TOKENISH),
159
+ filter: keyValueFilter,
81
160
  },
82
161
  {
83
162
  category: 'Password',
84
- re: /(?:password|passwd|pwd)\s*[:=]\s*["']?[^\s,}"']+["']?/gi,
163
+ re: kv('password|passwd|pwd', LOOSE),
164
+ filter: keyValueFilter,
85
165
  },
86
166
  {
87
167
  category: 'Token',
88
- re: /(?:access[_-]?token|refresh[_-]?token|token)\s*[:=]\s*["']?[A-Za-z0-9._-]{8,}["']?/gi,
168
+ re: kv(String.raw`access[_-]?token|refresh[_-]?token|token`, TOKENISH),
169
+ filter: keyValueFilter,
89
170
  },
90
171
  {
91
172
  category: 'Secret',
92
- re: /[a-z_]*secret\s*[:=]\s*["']?[^\s,}"']+["']?/gi,
173
+ re: kv(String.raw`secret(?:[_-]?(?:key|token|value))?`, LOOSE),
174
+ filter: keyValueFilter,
93
175
  },
94
176
  {
95
177
  category: 'SSN',
96
178
  re: /\b\d{3}-\d{2}-\d{4}\b/g,
97
179
  },
98
- {
99
- category: 'Email',
100
- re: /\b[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\.[A-Za-z]{2,}\b/g,
101
- filter: (match) => !EMAIL_ALLOW.test(match),
102
- },
103
180
  {
104
181
  category: 'Credit card number',
105
182
  re: /\b\d(?:[ -]?\d){12,18}\b/g,
@@ -110,26 +187,41 @@ export const SECRET_PATTERNS = [
110
187
  return luhnValid(digits);
111
188
  },
112
189
  },
190
+ {
191
+ category: 'Email',
192
+ re: /(?<![A-Za-z0-9._%+-])[A-Za-z0-9._%+-]{1,64}@(?:[A-Za-z0-9-]{1,63}\.){1,8}[A-Za-z]{2,24}\b/g,
193
+ filter: (match) => !EMAIL_ALLOW.test(match),
194
+ },
113
195
  ];
114
196
 
197
+ /** Number of secret-shaped matches per category in `text`; never the matched text. */
198
+ export function countSecrets(text) {
199
+ const counts = new Map();
200
+ for (const { category, re, filter } of SECRET_PATTERNS) {
201
+ re.lastIndex = 0;
202
+ let match;
203
+ while ((match = re.exec(text)) !== null) {
204
+ if (match[0].length === 0) re.lastIndex += 1;
205
+ if (filter && !filter(...match)) continue;
206
+ counts.set(category, (counts.get(category) || 0) + 1);
207
+ }
208
+ }
209
+ return counts;
210
+ }
211
+
115
212
  /** Returns the category names of every secret-shaped pattern found in `text`. */
116
213
  export function findSecretCategories(text) {
117
214
  const found = new Set();
118
215
  for (const { category, re, filter } of SECRET_PATTERNS) {
216
+ if (found.has(category)) continue;
119
217
  re.lastIndex = 0;
120
218
  let match;
121
219
  while ((match = re.exec(text)) !== null) {
122
- // A value that is already a redaction placeholder is clean: redact.ts leaves it
123
- // untouched, so containsSecrets() is false for it and this must agree.
124
- if (/REDACTED\]/.test(match[0])) {
125
- if (match[0].length === 0) re.lastIndex += 1;
126
- continue;
127
- }
128
- if (!filter || filter(match[0])) {
220
+ if (match[0].length === 0) re.lastIndex += 1;
221
+ if (!filter || filter(...match)) {
129
222
  found.add(category);
130
223
  break;
131
224
  }
132
- if (match[0].length === 0) re.lastIndex += 1;
133
225
  }
134
226
  }
135
227
  return [...found];
@@ -1,6 +1,6 @@
1
1
  #!/usr/bin/env node
2
2
  /**
3
- * PreToolUse hook (matcher: Write|Edit|MultiEdit).
3
+ * PreToolUse hook (matcher: Write|Edit|MultiEdit|NotebookEdit).
4
4
  *
5
5
  * Denies writing a secret-shaped string into anything under `output/`
6
6
  * (excluding `output/**\/snapshots/`, which never ships a report and is
@@ -8,15 +8,25 @@
8
8
  * excludes it). Mechanises security rule 3 (redact before disk) instead of
9
9
  * relying on the model remembering it.
10
10
  *
11
+ * The path is resolved against the hook's `cwd` first, so `snapshots/../bugs/`
12
+ * cannot borrow the snapshots exemption, and `output/` matches in any case
13
+ * (macOS file systems are case-insensitive). An Edit or MultiEdit is judged on
14
+ * the file as it would read afterwards, so a secret assembled across the edit
15
+ * boundary is caught; edits that only remove or keep secrets already there
16
+ * pass, so a file can be cleaned up one value at a time.
17
+ *
11
18
  * Node built-ins only, plus the sibling `secret-patterns.mjs` — a
12
19
  * git-sourced plugin install has neither `dist/` nor `node_modules`. Never
13
20
  * throws and never echoes the matched text back: the denial reason names
14
21
  * categories only.
15
22
  */
16
- import { readFileSync } from 'node:fs';
17
- import { findSecretCategories } from './secret-patterns.mjs';
23
+ import { readFileSync, statSync } from 'node:fs';
24
+ import { resolve } from 'node:path';
25
+ import { countSecrets, findSecretCategories } from './secret-patterns.mjs';
18
26
 
19
- const WRITE_TOOLS = new Set(['Write', 'Edit', 'MultiEdit']);
27
+ const WRITE_TOOLS = new Set(['Write', 'Edit', 'MultiEdit', 'NotebookEdit']);
28
+ // Larger files are judged on the inserted text alone.
29
+ const MAX_POST_EDIT_BYTES = 5 * 1024 * 1024;
20
30
 
21
31
  function deny(reason) {
22
32
  process.stdout.write(
@@ -30,8 +40,8 @@ function deny(reason) {
30
40
  );
31
41
  }
32
42
 
33
- function collectText(toolName, toolInput) {
34
- if (!toolInput) return '';
43
+ /** The text the tool inserts, on its own. */
44
+ function insertedText(toolName, toolInput) {
35
45
  if (toolName === 'Write') {
36
46
  return typeof toolInput.content === 'string' ? toolInput.content : '';
37
47
  }
@@ -44,9 +54,51 @@ function collectText(toolName, toolInput) {
44
54
  .map((e) => (e && typeof e.new_string === 'string' ? e.new_string : ''))
45
55
  .join('\n');
46
56
  }
57
+ if (toolName === 'NotebookEdit') {
58
+ return typeof toolInput.new_source === 'string' ? toolInput.new_source : '';
59
+ }
47
60
  return '';
48
61
  }
49
62
 
63
+ function applyEdit(content, edit) {
64
+ if (!edit || typeof edit.old_string !== 'string' || typeof edit.new_string !== 'string') {
65
+ return null;
66
+ }
67
+ if (!edit.old_string || !content.includes(edit.old_string)) return null;
68
+ return edit.replace_all
69
+ ? content.split(edit.old_string).join(edit.new_string)
70
+ : content.replace(edit.old_string, () => edit.new_string);
71
+ }
72
+
73
+ /** [before, after] for an Edit/MultiEdit, or null when the file can't be read or an edit won't apply. */
74
+ function postEditContent(toolName, toolInput, absPath) {
75
+ if (toolName !== 'Edit' && toolName !== 'MultiEdit') return null;
76
+ let before;
77
+ try {
78
+ if (statSync(absPath).size > MAX_POST_EDIT_BYTES) return null;
79
+ before = readFileSync(absPath, 'utf-8');
80
+ } catch {
81
+ return null;
82
+ }
83
+ const edits = toolName === 'Edit' ? [toolInput] : Array.isArray(toolInput.edits) ? toolInput.edits : [];
84
+ let after = before;
85
+ for (const edit of edits) {
86
+ after = applyEdit(after, edit);
87
+ if (after === null) return null;
88
+ }
89
+ return [before, after];
90
+ }
91
+
92
+ /** Categories whose match count the edit raises. */
93
+ function introducedCategories(before, after) {
94
+ const was = countSecrets(before);
95
+ const out = [];
96
+ for (const [category, n] of countSecrets(after)) {
97
+ if (n > (was.get(category) || 0)) out.push(category);
98
+ }
99
+ return out;
100
+ }
101
+
50
102
  try {
51
103
  if (process.env.QUALIOW_HOOKS === 'off') process.exit(0);
52
104
 
@@ -62,20 +114,23 @@ try {
62
114
  if (!WRITE_TOOLS.has(input.tool_name)) process.exit(0);
63
115
 
64
116
  const toolInput = input.tool_input || {};
65
- const filePath = toolInput.file_path;
117
+ const filePath = input.tool_name === 'NotebookEdit' ? toolInput.notebook_path : toolInput.file_path;
66
118
  if (!filePath || typeof filePath !== 'string') process.exit(0);
67
119
 
68
- const normalized = filePath.split('\\').join('/');
69
- if (!/(^|\/)output\//.test(normalized)) process.exit(0);
70
- if (normalized.includes('/snapshots/')) process.exit(0);
120
+ const cwd = typeof input.cwd === 'string' && input.cwd ? input.cwd : process.cwd();
121
+ const absPath = resolve(cwd, filePath);
122
+ const normalized = absPath.split('\\').join('/');
123
+ const outputAt = normalized.search(/(^|\/)output\//i);
124
+ if (outputAt === -1) process.exit(0);
125
+ if (normalized.slice(outputAt).includes('/snapshots/')) process.exit(0);
71
126
 
72
- const text = collectText(input.tool_name, toolInput);
73
- if (!text) process.exit(0);
127
+ const found = new Set(findSecretCategories(insertedText(input.tool_name, toolInput)));
128
+ const edited = postEditContent(input.tool_name, toolInput, absPath);
129
+ if (edited) introducedCategories(edited[0], edited[1]).forEach((c) => found.add(c));
74
130
 
75
- const categories = findSecretCategories(text);
76
- if (categories.length > 0) {
131
+ if (found.size > 0) {
77
132
  deny(
78
- `Refusing to write ${filePath}: it contains ${categories.join(', ')}. ` +
133
+ `Refusing to write ${filePath}: it contains ${[...found].join(', ')}. ` +
79
134
  'Redact per security-rules.md ([REDACTED]) before writing; ' +
80
135
  'qualiow session finalize --redact rewrites an existing file. ' +
81
136
  'Set QUALIOW_HOOKS=off to disable.',
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "qualiow-exploratory-testing",
3
- "version": "2.2.1",
3
+ "version": "2.3.1",
4
4
  "description": "qualiow — AI-powered exploratory testing skills for Claude Code: web via playwright-cli, iOS/Android simulators via Maestro/mobile-cli, and backend/API acceptance-criteria verification",
5
5
  "type": "module",
6
6
  "main": "dist/index.js",
@@ -104,6 +104,6 @@
104
104
  "@types/node": "^26.1.1",
105
105
  "tsup": "^8.4.0",
106
106
  "typescript": "^5.9.3",
107
- "vitest": "^4.1.10"
107
+ "vitest": "^5.0.0"
108
108
  }
109
109
  }
@@ -7,8 +7,8 @@ description: >
7
7
  and writes bug reports that executives act on.
8
8
  Use when user says: "explore", "test this site", "find bugs", "QA check", "exploratory session",
9
9
  or provides a URL to test.
10
- argument-hint: "<url> [--target <id>] [--context <file>] [--focus <area>] [--session <dir>]"
11
- allowed-tools: Bash(playwright-cli:*), Bash(npx playwright-cli:*), Bash(npx playwright:*), Bash(qualiow:*), Bash(npx:*), Bash(wc:*), Bash(diff:*), Read, Write, Glob, Grep
10
+ argument-hint: "<url> [--target <id>] [--context <file>] [--focus <area>] [--session <dir>] [--no-judge]"
11
+ allowed-tools: Bash(playwright-cli:*), Bash(npx playwright-cli:*), Bash(npx playwright:*), Bash(qualiow:*), Bash(npx -y -p qualiow-exploratory-testing qualiow:*), Bash(wc:*), Bash(diff:*), Read, Write, Glob, Grep
12
12
  ---
13
13
 
14
14
  # Exploratory Testing Session
@@ -41,6 +41,9 @@ You are a **Principal QA Engineer** with 20+ years of experience. You don't just
41
41
  # With a saved target config, or reusing a `qualiow explore` pre-flight directory
42
42
  /qa-explore --target company-staging --context output/context/SI-2305-context.md
43
43
  /qa-explore https://example.com --session output/sessions/2026-09-08-1420-explore-example-com
44
+
45
+ # Skip the phase-7 bug judge for this run (a target can set verification.mode: off instead)
46
+ /qa-explore https://example.com --no-judge
44
47
  ```
45
48
 
46
49
  ## Before You Start
@@ -51,7 +54,7 @@ You are a **Principal QA Engineer** with 20+ years of experience. You don't just
51
54
 
52
55
  ## Session Phases
53
56
 
54
- Execute each phase in order. Read and follow the linked file. The budget sums to 45 minutes; write to disk after each phase and carry only summaries in context.
57
+ Execute each phase in order. Read and follow the linked file. The budget sums to 45 minutes, plus up to 15 minutes of bug verification in phase 7; write to disk after each phase and carry only summaries in context.
55
58
 
56
59
  | Phase | File | Budget | Summary |
57
60
  |-------|------|--------|---------|
@@ -62,7 +65,7 @@ Execute each phase in order. Read and follow the linked file. The budget sums to
62
65
  | **Journeys** | `${CLAUDE_SKILL_DIR}/phases/04-journeys.md` | 10 min | End-to-end user journeys, data-integrity verification, cross-page consistency |
63
66
  | **Features** | `${CLAUDE_SKILL_DIR}/phases/05-features.md` | 10 min | Deep feature testing with SFDIPOT, business-logic stress, negative space, FEW HICCUPPS |
64
67
  | **Edge Cases** | `${CLAUDE_SKILL_DIR}/phases/06-edge-cases.md` | 6 min | Input attacks, race conditions, state manipulation, security, accessibility, empty states |
65
- | **Reporting** | `${CLAUDE_SKILL_DIR}/phases/07-reporting.md` | 4 min | Stop recording, reflect, write bug reports with business impact, session report, stats, close the browser session |
68
+ | **Reporting** | `${CLAUDE_SKILL_DIR}/phases/07-reporting.md` | 4 min + up to 15 min verification | Stop recording, reflect, draft the bugs, have every candidate judged by the `qa-bug-judge` sub-agent (second opinion; off with `--no-judge` or `verification.mode: off`), ship the verified bugs with business impact, session report with a refuted appendix, stats, close the browser session |
66
69
 
67
70
  ## References
68
71
 
@@ -73,6 +76,7 @@ Consult these as needed throughout the session:
73
76
  - **`${CLAUDE_SKILL_DIR}/references/security-rules.md`** — prompt-injection resistance, production rule, redaction list, session isolation, output classification
74
77
  - **`${CLAUDE_SKILL_DIR}/references/severity-guide.md`** — severity definitions, the "when in doubt go LOWER" rule, risk matrix, priority table
75
78
  - **`${CLAUDE_SKILL_DIR}/references/session-rules.md`** — 20 testing-discipline rules: 45-min cap, one bug one report, evidence, risk-proportional time, adapt mid-session, log WHY, AI-bias avoidance
76
- - **`${CLAUDE_SKILL_DIR}/references/delegation-rules.md`** — what the `qualiow` CLI does instead of you, the never-delegate list (severity, impact, bug reports, verdicts, reflection) and the read thresholds
79
+ - **`${CLAUDE_SKILL_DIR}/references/delegation-rules.md`** — what the `qualiow` CLI does instead of you, the never-delegate list (severity, impact, bug reports, AC verdicts, reflection), the one bounded exception (`qa-bug-judge` rules on whether a claim reproduces) and the read thresholds
80
+ - **`${CLAUDE_SKILL_DIR}/references/evidence-triage.md`** — opt-in, advisory decision-model triage recorded beside the judge's verdict (`verification.mode: triage-shadow`): the `qualiow judge triage` command, providers, what is sent, the `JEV-NNN` / `LAYA-NNN` files, stats
77
81
  - **`${CLAUDE_SKILL_DIR}/references/context-integration.md`** — how `--context` changes the session (context file, inline context, blind mode)
78
82
  - **`${CLAUDE_SKILL_DIR}/references/playwright-agents-integration.md`** — opt-in handoff to Playwright Test Agents (planner / generator / healer, Playwright 1.56+) when a reproducible bug should become a regression test; requires the optional `@playwright/test` peer dependency
@@ -8,6 +8,7 @@ Extract from the user message:
8
8
  - **--context <file>** or inline context text (optional)
9
9
  - **--focus <area>**: a specific area or feature (optional)
10
10
  - **--session <dir>**: an existing pre-flight directory created by `qualiow explore` (optional)
11
+ - **--no-judge**: skip the adversarial bug judge in phase 7 for this run (optional)
11
12
  - **domain**: domain type (optional; auto-detect from the app if not given)
12
13
  - **time_box**: 45 min (default and maximum)
13
14
 
@@ -22,6 +23,13 @@ Apply the **production rule** from `${CLAUDE_SKILL_DIR}/references/security-rule
22
23
  resolved hostname now. If it fires, log `[SAFETY] Production detected -- running in read-only mode`
23
24
  and carry read-only mode through every later phase.
24
25
 
26
+ Resolve the **verification mode** for phase 7 the same way: `off` when the run carries
27
+ `--no-judge` or the target sets `verification.mode: off`, otherwise `judge` (a target without
28
+ a `verification` block means `judge`). Either source turns the judge off; nothing on the
29
+ command line turns it back on for a target that set `off`. A target with
30
+ `verification.mode: triage-shadow` resolves to `judge` plus the advisory triage in phase 7
31
+ (`${CLAUDE_SKILL_DIR}/references/evidence-triage.md`); `--no-judge` turns both off.
32
+
25
33
  ## Step 2: Load Context (if provided)
26
34
 
27
35
  **If `--context <file>` provided:** read the file. It may be a `/qa-gather` context file
@@ -116,7 +124,7 @@ Write `output/sessions/<session-dir>/progress.json`:
116
124
 
117
125
  Append to `session-log.md`:
118
126
  ```
119
- [<timestamp>] [PHASE] Setup complete — session <session-dir>, sid <sid>, read_only: <true|false>
127
+ [<timestamp>] [PHASE] Setup complete — session <session-dir>, sid <sid>, read_only: <true|false>, verification: <judge|off|triage-shadow>
120
128
  ```
121
129
 
122
130
  ## Step 6: Optional — Bootstrap Playwright Test Agents (opt-in)