heimdall-agent 1.0.0 → 1.1.0

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 (231) hide show
  1. package/README.md +57 -26
  2. package/README.pt-BR.md +429 -0
  3. package/agents/cloud-engineer.md +77 -0
  4. package/agents/code-sentinel.md +66 -35
  5. package/agents/database-architect.md +31 -25
  6. package/agents/frontend-designer.md +30 -28
  7. package/agents/mobile-designer.md +25 -24
  8. package/agents/modernizer.md +66 -0
  9. package/agents/orchestrator.md +94 -93
  10. package/agents/reviewer.md +100 -71
  11. package/agents/security-auditor.md +27 -27
  12. package/agents/tester.md +97 -90
  13. package/commands/grill-me.md +20 -4
  14. package/commands/orchestrate.md +16 -0
  15. package/commands/orchestrator.md +16 -0
  16. package/commands/plan.md +17 -1
  17. package/config/agents.json +21 -3
  18. package/config/mcp.json +72 -0
  19. package/config/models.json +26 -16
  20. package/config/profiles.json +2 -4
  21. package/config/skills.json +210 -100
  22. package/docs/SKILLS.md +341 -245
  23. package/docs/designs/old/2026-10-31 plan-lifecycle-backlog-and-clean-code-skill.md +87 -0
  24. package/docs/designs/old/2026-11-02 skill-upstream-audit-and-update.md +105 -0
  25. package/docs/designs/old/2026-11-05 communication-doctrine-bluf-ste.md +94 -0
  26. package/docs/designs/old/2026-11-06-cloud-engineer-and-resilience-synthesis.md +67 -0
  27. package/docs/designs/old/2026-11-06-herdr-native-agent-orchestration.md +45 -0
  28. package/docs/runs/skill-audit/add_progressive_disclosure.cjs +30 -0
  29. package/docs/runs/skill-audit/check_heimdall_skills.ps1 +9 -0
  30. package/docs/runs/skill-audit/compare_classics.ps1 +26 -0
  31. package/docs/runs/skill-audit/compare_taste.ps1 +12 -0
  32. package/docs/runs/skill-audit/customization-report.json +380 -0
  33. package/docs/runs/skill-audit/diff_pending_skills.cjs +94 -0
  34. package/docs/runs/skill-audit/fetch_and_apply_skill.cjs +58 -0
  35. package/docs/runs/skill-audit/fetch_and_apply_taste_v2.cjs +65 -0
  36. package/docs/runs/skill-audit/inspect_pending_skills.cjs +71 -0
  37. package/docs/runs/skill-audit/inventory.json +308 -0
  38. package/docs/runs/skill-audit/list_local_taste.ps1 +1 -0
  39. package/docs/runs/skill-audit/phase5-update-plan.json +595 -0
  40. package/docs/runs/skill-audit/phase5-update-plan.md +138 -0
  41. package/docs/runs/skill-audit/probe.ps1 +16 -0
  42. package/docs/runs/skill-audit/probe_classics_branches.ps1 +3 -0
  43. package/docs/runs/skill-audit/probe_commits.ps1 +15 -0
  44. package/docs/runs/skill-audit/probe_repos.ps1 +17 -0
  45. package/docs/runs/skill-audit/probe_sentry_sec.ps1 +3 -0
  46. package/docs/runs/skill-audit/probe_sentry_sweep.ps1 +5 -0
  47. package/docs/runs/skill-audit/probe_snyk.ps1 +3 -0
  48. package/docs/runs/skill-audit/probe_snyk_recipes.ps1 +5 -0
  49. package/docs/runs/skill-audit/probe_taste_branches.ps1 +8 -0
  50. package/docs/runs/skill-audit/probe_taste_v19.ps1 +3 -0
  51. package/docs/runs/skill-audit/probe_user_repos.ps1 +19 -0
  52. package/docs/runs/skill-audit/prune_taste_skills.cjs +22 -0
  53. package/docs/runs/skill-audit/run_phase1_2.cjs +142 -0
  54. package/docs/runs/skill-audit/run_phase6_verification.cjs +107 -0
  55. package/docs/runs/skill-audit/show_16_details.ps1 +25 -0
  56. package/docs/runs/skill-audit/show_20_skills.ps1 +28 -0
  57. package/docs/runs/skill-audit/show_classics_diff.cjs +37 -0
  58. package/docs/runs/skill-audit/sync_agent_markdowns.cjs +30 -0
  59. package/docs/runs/skill-audit/taste-skill-upstream.md +542 -0
  60. package/docs/runs/skill-audit/update-manifest.md +88 -0
  61. package/docs/runs/skill-audit/update_config_skills.cjs +52 -0
  62. package/docs/runs/skill-audit/update_registry_phase7.cjs +83 -0
  63. package/docs/runs/skill-audit/upstream-status.json +563 -0
  64. package/docs/runs/skill-audit/verification-results.json +252 -0
  65. package/doctrine/AGENTS.md +39 -77
  66. package/hooks/git/pre-commit +11 -0
  67. package/hooks/heimdall-hook.cjs +81 -2
  68. package/hooks/herdr-agent-state.ps1 +55 -0
  69. package/hooks/hooks.json +0 -11
  70. package/lib/catalog-sync.cjs +162 -0
  71. package/lib/hermes-context.cjs +57 -0
  72. package/lib/model-context.cjs +123 -0
  73. package/lib/path-discovery.cjs +94 -0
  74. package/package.json +7 -3
  75. package/playbooks/01-interactive-grilling-gate.md +14 -1
  76. package/playbooks/02-fast-code-deep-verification.md +3 -2
  77. package/playbooks/03-adversarial-code-review.md +3 -3
  78. package/playbooks/05-canonical-plan-template.md +32 -18
  79. package/playbooks/06-model-registry-matrix.md +24 -13
  80. package/playbooks/07-legacy-code-modernization.md +74 -0
  81. package/playbooks/08-backlog-and-change-request-flow.md +122 -0
  82. package/setup.mjs +592 -172
  83. package/skills/antislop/SKILL.md +76 -56
  84. package/skills/antislop/VERSION +1 -0
  85. package/skills/antislop-copywriting/SKILL.md +372 -372
  86. package/skills/antislop-human/LICENSE-web-quality-skills +21 -0
  87. package/skills/antislop-human/SKILL.md +204 -147
  88. package/skills/antislop-human/contrast-check.py +168 -165
  89. package/skills/antislop-human/contrast-mcp.py +6 -3
  90. package/skills/antislop-human/references/A11Y-PATTERNS.md +249 -0
  91. package/skills/antislop-human/references/WCAG.md +127 -0
  92. package/skills/antislop-ui/LICENSE-web-quality-skills +21 -0
  93. package/skills/antislop-ui/SKILL.md +344 -304
  94. package/skills/antislop-ui/references/CORE-WEB-VITALS.md +181 -0
  95. package/skills/antislop-ui/references/WEB-BASELINE.md +28 -0
  96. package/skills/brainstorming/SKILL.md +274 -265
  97. package/skills/brainstorming/builder-check-prompt.md +23 -0
  98. package/skills/brainstorming/scripts/frame-template.html +213 -213
  99. package/skills/brainstorming/scripts/server.cjs +723 -723
  100. package/skills/brandkit/SKILL.md +798 -798
  101. package/skills/brutalist-skill/SKILL.md +93 -92
  102. package/skills/caveman/README.md +68 -0
  103. package/skills/caveman/SKILL.md +73 -38
  104. package/skills/claude-collaborator/SKILL.md +24 -44
  105. package/skills/clean-code/SKILL.md +152 -0
  106. package/skills/cloudflare-security-audit/AI-AND-LLM.md +83 -83
  107. package/skills/cloudflare-security-audit/ATTACK-CLASSES.md +130 -130
  108. package/skills/cloudflare-security-audit/CLIENT-SIDE.md +83 -83
  109. package/skills/cloudflare-security-audit/CLOUD-AND-DEPLOYMENT.md +86 -86
  110. package/skills/cloudflare-security-audit/DATA-ISOLATION-AND-LIFECYCLE.md +84 -84
  111. package/skills/cloudflare-security-audit/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -89
  112. package/skills/cloudflare-security-audit/HUNTING.md +251 -251
  113. package/skills/cloudflare-security-audit/MEMORY-SAFETY-AND-BINARY.md +101 -101
  114. package/skills/cloudflare-security-audit/PROTOCOLS-RPC-AND-MESSAGING.md +81 -81
  115. package/skills/cloudflare-security-audit/RECONNAISSANCE.md +156 -156
  116. package/skills/cloudflare-security-audit/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -78
  117. package/skills/cloudflare-security-audit/SKILL.md +192 -192
  118. package/skills/cloudflare-security-audit/SUPPLY-CHAIN-AND-RELEASE.md +73 -73
  119. package/skills/cloudflare-security-audit/VALIDATION-AND-REPORTING.md +186 -186
  120. package/skills/cloudflare-security-audit/WEB-PROTOCOL-AND-AUTH.md +105 -105
  121. package/skills/cloudflare-security-audit/report-schema.json +461 -461
  122. package/skills/cloudflare-security-audit/validate-coverage-ledger.cjs +872 -872
  123. package/skills/cloudflare-security-audit/validate-coverage-ledger.test.cjs +740 -740
  124. package/skills/cloudflare-security-audit/validate-findings.cjs +773 -773
  125. package/skills/cloudflare-security-audit/validate-findings.test.cjs +652 -652
  126. package/skills/codex-collaborator/SKILL.md +24 -45
  127. package/skills/communication-doctrine/SKILL.md +89 -0
  128. package/skills/diagnosing-superpowers/SKILL.md +1 -1
  129. package/skills/diagnosing-superpowers/references/github-issues.md +3 -3
  130. package/skills/diagnosing-superpowers/templates/issue.md +23 -4
  131. package/skills/executing-plans/SKILL.md +0 -52
  132. package/skills/executing-plans/scripts/task-done +52 -52
  133. package/skills/executing-plans/scripts/task-start +28 -28
  134. package/skills/gemini-collaborator/SKILL.md +24 -56
  135. package/skills/herdr/SKILL.md +243 -0
  136. package/skills/image-to-code-skill/SKILL.md +1228 -1228
  137. package/skills/imagegen-frontend-mobile/SKILL.md +1465 -1465
  138. package/skills/imagegen-frontend-web/SKILL.md +987 -987
  139. package/skills/karpathy-guidelines/SKILL.md +67 -67
  140. package/skills/mcp-engineering/SKILL.md +74 -0
  141. package/skills/minimalist-skill/SKILL.md +87 -85
  142. package/skills/output-skill/SKILL.md +49 -49
  143. package/skills/ponytail/SKILL.md +36 -52
  144. package/skills/postgres-best-practices/SKILL.md +30 -52
  145. package/skills/postgres-best-practices/references/backup-restore.md +372 -0
  146. package/skills/postgres-best-practices/references/bulk-loading.md +315 -0
  147. package/skills/postgres-best-practices/references/connection-pooling.md +310 -0
  148. package/skills/postgres-best-practices/references/hot-standby.md +221 -0
  149. package/skills/postgres-best-practices/references/indexing.md +318 -0
  150. package/skills/postgres-best-practices/references/logical-replication.md +610 -0
  151. package/skills/postgres-best-practices/references/major-version-upgrades.md +334 -0
  152. package/skills/postgres-best-practices/references/performance-diagnostics.md +553 -0
  153. package/skills/postgres-best-practices/references/query-optimization.md +294 -0
  154. package/skills/postgres-best-practices/references/query-patterns.md +566 -0
  155. package/skills/postgres-best-practices/references/schema-design.md +362 -0
  156. package/skills/postgres-best-practices/references/security-roles.md +489 -0
  157. package/skills/postgres-best-practices/references/transaction-isolation.md +344 -0
  158. package/skills/progressive-disclosure/SKILL.md +68 -0
  159. package/skills/pstack-discipline/SKILL.md +40 -0
  160. package/skills/receiving-code-review/SKILL.md +2 -23
  161. package/skills/requesting-code-review/SKILL.md +7 -36
  162. package/skills/soft-skill/SKILL.md +99 -98
  163. package/skills/stitch-skill/DESIGN.md +121 -121
  164. package/skills/stitch-skill/SKILL.md +185 -184
  165. package/skills/strix-security/SKILL.md +54 -53
  166. package/skills/subagent-driven-development/SKILL.md +28 -260
  167. package/skills/subagent-driven-development/references/batching.md +11 -0
  168. package/skills/subagent-driven-development/references/cannot-verify.md +10 -0
  169. package/skills/subagent-driven-development/references/final-review.md +47 -0
  170. package/skills/subagent-driven-development/references/fix-loop.md +77 -0
  171. package/skills/subagent-driven-development/references/handling-reports.md +15 -0
  172. package/skills/subagent-driven-development/references/preflight.md +26 -0
  173. package/skills/subagent-driven-development/references/resuming.md +12 -0
  174. package/skills/subagent-driven-development/scripts/review-package +53 -53
  175. package/skills/subagent-driven-development/scripts/sdd-workspace +87 -82
  176. package/skills/subagent-driven-development/scripts/task-brief +43 -43
  177. package/skills/systematic-debugging/SKILL.md +283 -306
  178. package/skills/taste-skill/SKILL.md +542 -1206
  179. package/skills/taste-skill/references/app-screens.md +1199 -0
  180. package/skills/taste-skill/references/colour.md +141 -0
  181. package/skills/taste-skill/references/copy.md +177 -0
  182. package/skills/taste-skill/references/critique.md +182 -0
  183. package/skills/taste-skill/references/imagery.md +791 -0
  184. package/skills/taste-skill/references/layout.md +292 -0
  185. package/skills/taste-skill/references/motion.md +980 -0
  186. package/skills/taste-skill/references/research.md +356 -0
  187. package/skills/taste-skill/references/scenes.md +174 -0
  188. package/skills/taste-skill/references/tells.md +115 -0
  189. package/skills/taste-skill/references/type.md +170 -0
  190. package/skills/test-driven-development/SKILL.md +330 -337
  191. package/skills/thermo/SKILL.md +67 -0
  192. package/skills/threat-modeling/SKILL.md +55 -0
  193. package/skills/trailofbits-audit-context/SKILL.md +72 -72
  194. package/skills/trailofbits-insecure-defaults/commands/audit.md +35 -0
  195. package/skills/trailofbits-insecure-defaults/references/debug-features.json +13 -13
  196. package/skills/trailofbits-insecure-defaults/references/debug-features.md +75 -75
  197. package/skills/trailofbits-insecure-defaults/references/default-credentials.json +12 -12
  198. package/skills/trailofbits-insecure-defaults/references/default-credentials.md +76 -76
  199. package/skills/trailofbits-insecure-defaults/references/fail-open-security.json +11 -11
  200. package/skills/trailofbits-insecure-defaults/references/fail-open-security.md +70 -70
  201. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.json +11 -11
  202. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.md +70 -70
  203. package/skills/trailofbits-insecure-defaults/references/permissive-access.json +13 -13
  204. package/skills/trailofbits-insecure-defaults/references/permissive-access.md +62 -62
  205. package/skills/trailofbits-insecure-defaults/references/weak-crypto.json +13 -13
  206. package/skills/trailofbits-insecure-defaults/references/weak-crypto.md +71 -71
  207. package/skills/trailofbits-triage-brocards/SKILL.md +208 -208
  208. package/skills/verification-before-completion/SKILL.md +0 -14
  209. package/skills/writing-plans/SKILL.md +11 -15
  210. package/skills/writing-skills/SKILL.md +21 -303
  211. package/skills/writing-skills/references/CLAUDE_MD_TESTING.md +189 -0
  212. package/skills/writing-skills/references/anthropic-best-practices.md +1150 -0
  213. package/skills/writing-skills/references/bulletproofing.md +80 -0
  214. package/skills/writing-skills/references/discovery.md +201 -0
  215. package/skills/writing-skills/references/flowcharts.md +37 -0
  216. package/skills/writing-skills/references/graphviz-conventions.dot +172 -0
  217. package/skills/writing-skills/references/persuasion-principles.md +187 -0
  218. package/skills/writing-skills/references/testing-skills-with-subagents.md +384 -0
  219. package/tools/{claude-bridge.ps1 → archive/claude-bridge.ps1} +10 -7
  220. package/tools/{codex-bridge.ps1 → archive/codex-bridge.ps1} +1 -1
  221. package/tools/{gemini-bridge.ps1 → archive/gemini-bridge.ps1} +12 -19
  222. package/skills/gpt-tasteskill/SKILL.md +0 -74
  223. package/skills/taste-skill-v1/SKILL.md +0 -226
  224. /package/tools/{claude-bridge.cmd → archive/claude-bridge.cmd} +0 -0
  225. /package/tools/{claude-bridge.sh → archive/claude-bridge.sh} +0 -0
  226. /package/tools/{codex-bridge.cmd → archive/codex-bridge.cmd} +0 -0
  227. /package/tools/{codex-bridge.sh → archive/codex-bridge.sh} +0 -0
  228. /package/tools/{codexcli-bridge.cmd → archive/codexcli-bridge.cmd} +0 -0
  229. /package/tools/{codexcli-bridge.ps1 → archive/codexcli-bridge.ps1} +0 -0
  230. /package/tools/{gemini-bridge.cmd → archive/gemini-bridge.cmd} +0 -0
  231. /package/tools/{gemini-bridge.sh → archive/gemini-bridge.sh} +0 -0
@@ -1,13 +1,13 @@
1
- {
2
- "id": "weak-crypto",
3
- "title": "Weak cryptographic defaults",
4
- "seeds": [
5
- "(md5|sha1|MD5|SHA1)[[:space:]]*\\(",
6
- "(^|[^A-Za-z])(DESede|DES|RC2|RC4|Blowfish|ECB|PKCS1v15)([^A-Za-z]|$)",
7
- "(algorithm|alg|cipher|mode)[[:space:]]*[:=][[:space:]]*['\"](md5|sha1|none|HS256|DES|RC4|ECB)",
8
- "(createHmac|createHash|createCipher|createCipheriv|getInstance|MessageDigest|hmac\\.new|HMAC|Signature)[^)]{0,40}['\"](md5|sha1|MD5|SHA1|DES|RC4)",
9
- "['\"](md5|sha1|des|rc4|des-ede3-cbc|aes-[0-9]+-ecb)['\"]",
10
- "(token|secret|key|password|passwd|salt|nonce|otp|session|csrf)[A-Za-z_]*[[:space:]]*[:=][[:space:]]*[^=]{0,60}(random\\.|Math\\.random|mt_rand|rand\\()",
11
- "(random\\.|Math\\.random|mt_rand|rand\\()[^;]{0,80}(token|secret|key|password|salt|nonce|otp|session|csrf)"
12
- ]
13
- }
1
+ {
2
+ "id": "weak-crypto",
3
+ "title": "Weak cryptographic defaults",
4
+ "seeds": [
5
+ "(md5|sha1|MD5|SHA1)[[:space:]]*\\(",
6
+ "(^|[^A-Za-z])(DESede|DES|RC2|RC4|Blowfish|ECB|PKCS1v15)([^A-Za-z]|$)",
7
+ "(algorithm|alg|cipher|mode)[[:space:]]*[:=][[:space:]]*['\"](md5|sha1|none|HS256|DES|RC4|ECB)",
8
+ "(createHmac|createHash|createCipher|createCipheriv|getInstance|MessageDigest|hmac\\.new|HMAC|Signature)[^)]{0,40}['\"](md5|sha1|MD5|SHA1|DES|RC4)",
9
+ "['\"](md5|sha1|des|rc4|des-ede3-cbc|aes-[0-9]+-ecb)['\"]",
10
+ "(token|secret|key|password|passwd|salt|nonce|otp|session|csrf)[A-Za-z_]*[[:space:]]*[:=][[:space:]]*[^=]{0,60}(random\\.|Math\\.random|mt_rand|rand\\()",
11
+ "(random\\.|Math\\.random|mt_rand|rand\\()[^;]{0,80}(token|secret|key|password|salt|nonce|otp|session|csrf)"
12
+ ]
13
+ }
@@ -1,71 +1,71 @@
1
- # Weak Cryptographic Defaults
2
-
3
- **Report when:** A broken or non-cryptographic primitive standing in for a security-relevant one: password hashing, token generation, encryption, signature verification.
4
-
5
- **Skip when:** Checksums, ETags, cache keys, deduplication hashes, test vectors. Non-security shuffling or sampling.
6
-
7
- The algorithm alone is never the finding. `hashlib.md5` over a cache key is fine; the same call over a password is not. Trace to the use site before filing.
8
-
9
- ## VULNERABLE - Report These
10
-
11
- **MD5 for password hashing**
12
- ```python
13
- # File: src/auth/passwords.py
14
- import hashlib
15
-
16
- def hash_password(password):
17
- """Hash user password"""
18
- return hashlib.md5(password.encode()).hexdigest()
19
- ```
20
- **Why vulnerable:** MD5 is cryptographically broken. Rainbow tables exist. Use bcrypt/Argon2.
21
-
22
- **DES encryption for sensitive data**
23
- ```java
24
- // File: Encryption.java
25
- public static byte[] encrypt(String data, byte[] key) {
26
- Cipher cipher = Cipher.getInstance("DES/ECB/PKCS5Padding");
27
- SecretKeySpec secretKey = new SecretKeySpec(key, "DES");
28
- cipher.init(Cipher.ENCRYPT_MODE, secretKey);
29
- return cipher.doFinal(data.getBytes());
30
- }
31
- ```
32
- **Why vulnerable:** DES has 56-bit keys (brute-forceable). ECB mode leaks patterns.
33
-
34
- **SHA1 for signature verification**
35
- ```javascript
36
- // File: webhooks.js
37
- function verifySignature(payload, signature) {
38
- const hmac = crypto.createHmac('sha1', WEBHOOK_SECRET);
39
- const computed = hmac.update(payload).digest('hex');
40
- return computed === signature;
41
- }
42
- ```
43
- **Why vulnerable:** SHA1 collisions exist. Use SHA256 or better.
44
-
45
- ## SECURE - Skip These
46
-
47
- **Weak crypto for non-security checksums**
48
- ```python
49
- # File: src/utils/cache.py
50
- import hashlib
51
-
52
- def cache_key(data):
53
- """Generate cache key - not security-sensitive"""
54
- return hashlib.md5(data.encode()).hexdigest() # OK - just for cache lookup
55
- ```
56
-
57
- **Modern crypto for passwords**
58
- ```python
59
- # File: src/auth/passwords.py
60
- import bcrypt
61
-
62
- def hash_password(password):
63
- return bcrypt.hashpw(password.encode(), bcrypt.gensalt())
64
- ```
65
-
66
- **Strong encryption**
67
- ```java
68
- // File: Encryption.java
69
- Cipher cipher = Cipher.getInstance("AES/GCM/NoPadding");
70
- // 256-bit key, authenticated encryption
71
- ```
1
+ # Weak Cryptographic Defaults
2
+
3
+ **Report when:** A broken or non-cryptographic primitive standing in for a security-relevant one: password hashing, token generation, encryption, signature verification.
4
+
5
+ **Skip when:** Checksums, ETags, cache keys, deduplication hashes, test vectors. Non-security shuffling or sampling.
6
+
7
+ The algorithm alone is never the finding. `hashlib.md5` over a cache key is fine; the same call over a password is not. Trace to the use site before filing.
8
+
9
+ ## VULNERABLE - Report These
10
+
11
+ **MD5 for password hashing**
12
+ ```python
13
+ # File: src/auth/passwords.py
14
+ import hashlib
15
+
16
+ def hash_password(password):
17
+ """Hash user password"""
18
+ return hashlib.md5(password.encode()).hexdigest()
19
+ ```
20
+ **Why vulnerable:** MD5 is cryptographically broken. Rainbow tables exist. Use bcrypt/Argon2.
21
+
22
+ **DES encryption for sensitive data**
23
+ ```java
24
+ // File: Encryption.java
25
+ public static byte[] encrypt(String data, byte[] key) {
26
+ Cipher cipher = Cipher.getInstance("DES/ECB/PKCS5Padding");
27
+ SecretKeySpec secretKey = new SecretKeySpec(key, "DES");
28
+ cipher.init(Cipher.ENCRYPT_MODE, secretKey);
29
+ return cipher.doFinal(data.getBytes());
30
+ }
31
+ ```
32
+ **Why vulnerable:** DES has 56-bit keys (brute-forceable). ECB mode leaks patterns.
33
+
34
+ **SHA1 for signature verification**
35
+ ```javascript
36
+ // File: webhooks.js
37
+ function verifySignature(payload, signature) {
38
+ const hmac = crypto.createHmac('sha1', WEBHOOK_SECRET);
39
+ const computed = hmac.update(payload).digest('hex');
40
+ return computed === signature;
41
+ }
42
+ ```
43
+ **Why vulnerable:** SHA1 collisions exist. Use SHA256 or better.
44
+
45
+ ## SECURE - Skip These
46
+
47
+ **Weak crypto for non-security checksums**
48
+ ```python
49
+ # File: src/utils/cache.py
50
+ import hashlib
51
+
52
+ def cache_key(data):
53
+ """Generate cache key - not security-sensitive"""
54
+ return hashlib.md5(data.encode()).hexdigest() # OK - just for cache lookup
55
+ ```
56
+
57
+ **Modern crypto for passwords**
58
+ ```python
59
+ # File: src/auth/passwords.py
60
+ import bcrypt
61
+
62
+ def hash_password(password):
63
+ return bcrypt.hashpw(password.encode(), bcrypt.gensalt())
64
+ ```
65
+
66
+ **Strong encryption**
67
+ ```java
68
+ // File: Encryption.java
69
+ Cipher cipher = Cipher.getInstance("AES/GCM/NoPadding");
70
+ // 256-bit key, authenticated encryption
71
+ ```
@@ -1,208 +1,208 @@
1
- ---
2
- name: vulnerability-triage-brocards
3
- description: >-
4
- This skill should be used when the user asks to "triage a vulnerability
5
- report", "assess a CVE", "evaluate a bug bounty submission", "decide if a
6
- finding is valid", "review a security finding", "dismiss a vulnerability",
7
- "should we fix this CVE", "prioritize a vulnerability report", or needs
8
- to determine whether an incoming vulnerability report warrants
9
- investigation. Applies 7 brocards (rules of thumb) to systematically
10
- accept, dismiss, or request more information on vulnerability reports,
11
- or needs to filter raw findings from agentic vulnerability
12
- discovery pipelines before human review.
13
- ---
14
-
15
- # Vulnerability Triage Brocards
16
-
17
- Systematically evaluate incoming vulnerability reports against 7 principled
18
- criteria before committing resources to deeper analysis. Each brocard is a
19
- falsifiable test: if a report fails any brocard, document the reason and
20
- dismiss or request clarification. If a report survives all 7, escalate it.
21
-
22
- The 7 brocards are adapted from William Woodruff's
23
- ["Brocards for vulnerability triage"](https://vulnbrocards.com/)
24
- (2026).
25
-
26
- ## When to Use
27
-
28
- - Filtering findings from agentic vulnerability discovery pipelines
29
- before human review -- the primary use case; most automated runs
30
- produce findings that fail one or more brocards and can be dismissed
31
- without auditor time
32
- - Triaging findings during a ToB audit to decide which warrant
33
- escalation to PoC development
34
- - Evaluating third-party CVEs or advisories against a codebase under
35
- active audit to decide if they affect engagement scope
36
- - Reviewing bug bounty submissions or external vulnerability reports
37
- for ToB open-source projects
38
- - Providing structured, defensible justification when recommending a
39
- client dismiss or deprioritize a reported CVE
40
-
41
- ## When NOT to Use
42
-
43
- - **Hunting for new bugs during an audit** -- use other skills
44
- - **Proving exploitability of a confirmed finding** -- use a
45
- dedicated PoC/exploitability skill
46
- - **Triaging fuzzer crashes in C/C++** -- use a dedicated crash
47
- triage skill
48
-
49
- ## Pipeline Position
50
-
51
- This skill is the quality gate between automated discovery and human
52
- review. Findings that survive triage proceed to PoC development and
53
- formal writeup.
54
-
55
- ```mermaid
56
- flowchart TD
57
- A([agentic vulnerability discovery]) -->|raw findings| B[vulnerability-triage-brocards]
58
- B -->|DISMISS| C([Document brocard # and reasoning])
59
- B -->|NEEDS-MORE-INFO| D([Request specific evidence])
60
- B -->|ACCEPT| E[PoC / exploitability proof]
61
- E --> F[vulnerability report writeup]
62
- ```
63
-
64
- ## Triage Workflow
65
-
66
- For each incoming vulnerability report, evaluate it against all 7 brocards
67
- sequentially. By default, stop at the first DISMISS verdict and report it.
68
- If the user requests a full evaluation, continue through all 7 brocards
69
- regardless of intermediate failures. For each brocard, record one of three
70
- verdicts:
71
-
72
- - **PASS** -- the report survives this test
73
- - **DISMISS** -- the report fails this test; document the reason
74
- - **NEEDS-MORE-INFO** -- insufficient evidence to evaluate; specify what is
75
- missing
76
-
77
- ### Brocard 1: No Vulnerability Without a Threat Model
78
-
79
- Dismiss any report that lacks a coherent threat model. The report must
80
- articulate: (a) who the attacker is, (b) what capability the attacker has,
81
- (c) how the attacker exploits the behavior, and (d) what harm results.
82
-
83
- Reports that describe a code behavior without connecting it to attacker-
84
- reachable harm fail this brocard.
85
-
86
- **Quick test:** Can the report answer "an attacker with [capability] can
87
- [action] to achieve [impact]"? If not, dismiss or request clarification.
88
-
89
- ### Brocard 2: No Exploit from the Heavens
90
-
91
- Dismiss any report where the attacker capabilities required to trigger the
92
- vulnerability equal or exceed the impact of the vulnerability itself. If the
93
- attacker must already possess the power the exploit would grant, the
94
- vulnerability is redundant.
95
-
96
- **Quick test:** Does triggering the exploit require capabilities that already
97
- subsume its impact? If yes, dismiss.
98
-
99
- ### Brocard 3: No Vulnerability Outside of Usage
100
-
101
- Dismiss any report describing behavior that is theoretically possible but
102
- does not occur in actual software usage. Check whether the vulnerable code
103
- path is reachable in practice.
104
-
105
- **Quick test:** Is the vulnerable code path exercised by any real caller?
106
- If not, dismiss. If the report targets a library, ask if we should check
107
- downstream usage.
108
-
109
- ### Brocard 4: No Vulnerability from Standard Behavior
110
-
111
- Dismiss any report where the behavior results from correct implementation of
112
- a specification. The vulnerability, if any, exists in the standard -- not the
113
- implementation.
114
-
115
- **Nuance:** If an implementation voluntarily adopts a stricter posture than
116
- the standard requires, and that strictness fails, the implementation *is*
117
- vulnerable even though the standard permits the behavior.
118
-
119
- **Quick test:** Does the specification require or permit this behavior? If
120
- yes, the report targets the standard, not the code.
121
-
122
- ### Brocard 5: No Vulnerability from Documented Behavior
123
-
124
- Dismiss any report describing behavior that is explicitly documented,
125
- especially when the documentation includes security implications or usage
126
- caveats.
127
-
128
- **Nuance:** Downstream usage that violates documented guidelines may
129
- constitute a valid vulnerability in the *downstream* project, not the
130
- documented component.
131
-
132
- **Quick test:** Does the project's documentation describe this behavior and
133
- warn against misuse? If yes, dismiss the report against the project itself.
134
-
135
- ### Brocard 6: No Cure Worse Than the Disease
136
-
137
- Dismiss any report whose remediation would cause more harm than the
138
- vulnerability itself. Evaluate: (a) severity of the vulnerability in
139
- practice, (b) cost and disruption of the proposed fix, (c) blast radius of
140
- the remediation (dependency graph, ecosystem impact).
141
-
142
- **Quick test:** Would fixing this cause more disruption than the
143
- vulnerability itself? If yes, dismiss or downgrade severity.
144
-
145
- ### Brocard 7: The Report Is Neither Necessary nor Sufficient
146
-
147
- A CVE identifier or formal report does not prove a vulnerability exists.
148
- Conversely, absence of a report does not prove safety. Evaluate the
149
- technical merits independently of report metadata.
150
-
151
- **Quick test:** Strip the CVE number and CVSS score. Does the technical
152
- description alone justify action? Judge on evidence, not authority.
153
-
154
- ## Output Format
155
-
156
- After evaluating all 7 brocards, produce a structured triage summary:
157
-
158
- ```
159
- ## Triage Summary: [Report ID or Title]
160
-
161
- | # | Brocard | Verdict | Rationale |
162
- |---|---------|---------|-----------|
163
- | 1 | Threat Model | PASS/DISMISS/NEEDS-MORE-INFO | ... |
164
- | 2 | Exploit from the Heavens | PASS/DISMISS/NEEDS-MORE-INFO | ... |
165
- | 3 | Outside of Usage | PASS/DISMISS/NEEDS-MORE-INFO | ... |
166
- | 4 | Standard Behavior | PASS/DISMISS/NEEDS-MORE-INFO | ... |
167
- | 5 | Documented Behavior | PASS/DISMISS/NEEDS-MORE-INFO | ... |
168
- | 6 | Cure Worse Than Disease | PASS/DISMISS/NEEDS-MORE-INFO | ... |
169
- | 7 | Report Sufficiency | PASS/DISMISS/NEEDS-MORE-INFO | ... |
170
-
171
- **Overall Verdict:** ACCEPT / DISMISS / NEEDS-MORE-INFO
172
- **Reasoning:** [1-3 sentence justification]
173
- **Next Step:** [escalate to PoC development / request info / close]
174
- ```
175
-
176
- ## Rationalizations to Reject
177
-
178
- Guard against these reasoning failures in both directions:
179
-
180
- ### Wrongly Dismissing Valid Findings
181
-
182
- - "It's only reachable in debug mode" -- verify debug mode is truly
183
- never enabled in production; many clients ship with debug flags on
184
- - "The attacker would need local access" -- local access is a realistic
185
- threat model for many deployments, especially containerized services
186
- - "Nobody uses that API" -- confirm with actual usage data, not
187
- assumptions; check client's integration tests and deployment configs
188
- - "The spec allows it" -- check whether the implementation claims
189
- stricter behavior than the spec requires
190
-
191
- ### Wrongly Accepting Invalid Findings
192
-
193
- - "It has a CVE, so it must be real" -- Brocard 7 exists for this reason
194
- - "The CVSS score is high" -- CVSS is a formula, not a verdict
195
- - "Better safe than sorry" -- Brocard 6 requires evaluating fix cost
196
- - "We can't prove it's NOT exploitable" -- the burden of proof is on the
197
- reporter to demonstrate a threat model (Brocard 1)
198
- - "Other projects patched it" -- other projects may have different usage
199
- patterns (Brocard 3)
200
- - "We should include it to pad the report" -- ToB reports reflect
201
- technical reality, not finding count targets; a dismissed report with
202
- documented reasoning is more valuable than a false positive in a
203
- final deliverable
204
-
205
- ## Detailed References
206
-
207
- For expanded explanations, examples, and edge cases for each brocard, consult
208
- [`references/brocards-detail.md`](references/brocards-detail.md).
1
+ ---
2
+ name: vulnerability-triage-brocards
3
+ description: >-
4
+ This skill should be used when the user asks to "triage a vulnerability
5
+ report", "assess a CVE", "evaluate a bug bounty submission", "decide if a
6
+ finding is valid", "review a security finding", "dismiss a vulnerability",
7
+ "should we fix this CVE", "prioritize a vulnerability report", or needs
8
+ to determine whether an incoming vulnerability report warrants
9
+ investigation. Applies 7 brocards (rules of thumb) to systematically
10
+ accept, dismiss, or request more information on vulnerability reports,
11
+ or needs to filter raw findings from agentic vulnerability
12
+ discovery pipelines before human review.
13
+ ---
14
+
15
+ # Vulnerability Triage Brocards
16
+
17
+ Systematically evaluate incoming vulnerability reports against 7 principled
18
+ criteria before committing resources to deeper analysis. Each brocard is a
19
+ falsifiable test: if a report fails any brocard, document the reason and
20
+ dismiss or request clarification. If a report survives all 7, escalate it.
21
+
22
+ The 7 brocards are adapted from William Woodruff's
23
+ ["Brocards for vulnerability triage"](https://vulnbrocards.com/)
24
+ (2026).
25
+
26
+ ## When to Use
27
+
28
+ - Filtering findings from agentic vulnerability discovery pipelines
29
+ before human review -- the primary use case; most automated runs
30
+ produce findings that fail one or more brocards and can be dismissed
31
+ without auditor time
32
+ - Triaging findings during a ToB audit to decide which warrant
33
+ escalation to PoC development
34
+ - Evaluating third-party CVEs or advisories against a codebase under
35
+ active audit to decide if they affect engagement scope
36
+ - Reviewing bug bounty submissions or external vulnerability reports
37
+ for ToB open-source projects
38
+ - Providing structured, defensible justification when recommending a
39
+ client dismiss or deprioritize a reported CVE
40
+
41
+ ## When NOT to Use
42
+
43
+ - **Hunting for new bugs during an audit** -- use other skills
44
+ - **Proving exploitability of a confirmed finding** -- use a
45
+ dedicated PoC/exploitability skill
46
+ - **Triaging fuzzer crashes in C/C++** -- use a dedicated crash
47
+ triage skill
48
+
49
+ ## Pipeline Position
50
+
51
+ This skill is the quality gate between automated discovery and human
52
+ review. Findings that survive triage proceed to PoC development and
53
+ formal writeup.
54
+
55
+ ```mermaid
56
+ flowchart TD
57
+ A([agentic vulnerability discovery]) -->|raw findings| B[vulnerability-triage-brocards]
58
+ B -->|DISMISS| C([Document brocard # and reasoning])
59
+ B -->|NEEDS-MORE-INFO| D([Request specific evidence])
60
+ B -->|ACCEPT| E[PoC / exploitability proof]
61
+ E --> F[vulnerability report writeup]
62
+ ```
63
+
64
+ ## Triage Workflow
65
+
66
+ For each incoming vulnerability report, evaluate it against all 7 brocards
67
+ sequentially. By default, stop at the first DISMISS verdict and report it.
68
+ If the user requests a full evaluation, continue through all 7 brocards
69
+ regardless of intermediate failures. For each brocard, record one of three
70
+ verdicts:
71
+
72
+ - **PASS** -- the report survives this test
73
+ - **DISMISS** -- the report fails this test; document the reason
74
+ - **NEEDS-MORE-INFO** -- insufficient evidence to evaluate; specify what is
75
+ missing
76
+
77
+ ### Brocard 1: No Vulnerability Without a Threat Model
78
+
79
+ Dismiss any report that lacks a coherent threat model. The report must
80
+ articulate: (a) who the attacker is, (b) what capability the attacker has,
81
+ (c) how the attacker exploits the behavior, and (d) what harm results.
82
+
83
+ Reports that describe a code behavior without connecting it to attacker-
84
+ reachable harm fail this brocard.
85
+
86
+ **Quick test:** Can the report answer "an attacker with [capability] can
87
+ [action] to achieve [impact]"? If not, dismiss or request clarification.
88
+
89
+ ### Brocard 2: No Exploit from the Heavens
90
+
91
+ Dismiss any report where the attacker capabilities required to trigger the
92
+ vulnerability equal or exceed the impact of the vulnerability itself. If the
93
+ attacker must already possess the power the exploit would grant, the
94
+ vulnerability is redundant.
95
+
96
+ **Quick test:** Does triggering the exploit require capabilities that already
97
+ subsume its impact? If yes, dismiss.
98
+
99
+ ### Brocard 3: No Vulnerability Outside of Usage
100
+
101
+ Dismiss any report describing behavior that is theoretically possible but
102
+ does not occur in actual software usage. Check whether the vulnerable code
103
+ path is reachable in practice.
104
+
105
+ **Quick test:** Is the vulnerable code path exercised by any real caller?
106
+ If not, dismiss. If the report targets a library, ask if we should check
107
+ downstream usage.
108
+
109
+ ### Brocard 4: No Vulnerability from Standard Behavior
110
+
111
+ Dismiss any report where the behavior results from correct implementation of
112
+ a specification. The vulnerability, if any, exists in the standard -- not the
113
+ implementation.
114
+
115
+ **Nuance:** If an implementation voluntarily adopts a stricter posture than
116
+ the standard requires, and that strictness fails, the implementation *is*
117
+ vulnerable even though the standard permits the behavior.
118
+
119
+ **Quick test:** Does the specification require or permit this behavior? If
120
+ yes, the report targets the standard, not the code.
121
+
122
+ ### Brocard 5: No Vulnerability from Documented Behavior
123
+
124
+ Dismiss any report describing behavior that is explicitly documented,
125
+ especially when the documentation includes security implications or usage
126
+ caveats.
127
+
128
+ **Nuance:** Downstream usage that violates documented guidelines may
129
+ constitute a valid vulnerability in the *downstream* project, not the
130
+ documented component.
131
+
132
+ **Quick test:** Does the project's documentation describe this behavior and
133
+ warn against misuse? If yes, dismiss the report against the project itself.
134
+
135
+ ### Brocard 6: No Cure Worse Than the Disease
136
+
137
+ Dismiss any report whose remediation would cause more harm than the
138
+ vulnerability itself. Evaluate: (a) severity of the vulnerability in
139
+ practice, (b) cost and disruption of the proposed fix, (c) blast radius of
140
+ the remediation (dependency graph, ecosystem impact).
141
+
142
+ **Quick test:** Would fixing this cause more disruption than the
143
+ vulnerability itself? If yes, dismiss or downgrade severity.
144
+
145
+ ### Brocard 7: The Report Is Neither Necessary nor Sufficient
146
+
147
+ A CVE identifier or formal report does not prove a vulnerability exists.
148
+ Conversely, absence of a report does not prove safety. Evaluate the
149
+ technical merits independently of report metadata.
150
+
151
+ **Quick test:** Strip the CVE number and CVSS score. Does the technical
152
+ description alone justify action? Judge on evidence, not authority.
153
+
154
+ ## Output Format
155
+
156
+ After evaluating all 7 brocards, produce a structured triage summary:
157
+
158
+ ```
159
+ ## Triage Summary: [Report ID or Title]
160
+
161
+ | # | Brocard | Verdict | Rationale |
162
+ |---|---------|---------|-----------|
163
+ | 1 | Threat Model | PASS/DISMISS/NEEDS-MORE-INFO | ... |
164
+ | 2 | Exploit from the Heavens | PASS/DISMISS/NEEDS-MORE-INFO | ... |
165
+ | 3 | Outside of Usage | PASS/DISMISS/NEEDS-MORE-INFO | ... |
166
+ | 4 | Standard Behavior | PASS/DISMISS/NEEDS-MORE-INFO | ... |
167
+ | 5 | Documented Behavior | PASS/DISMISS/NEEDS-MORE-INFO | ... |
168
+ | 6 | Cure Worse Than Disease | PASS/DISMISS/NEEDS-MORE-INFO | ... |
169
+ | 7 | Report Sufficiency | PASS/DISMISS/NEEDS-MORE-INFO | ... |
170
+
171
+ **Overall Verdict:** ACCEPT / DISMISS / NEEDS-MORE-INFO
172
+ **Reasoning:** [1-3 sentence justification]
173
+ **Next Step:** [escalate to PoC development / request info / close]
174
+ ```
175
+
176
+ ## Rationalizations to Reject
177
+
178
+ Guard against these reasoning failures in both directions:
179
+
180
+ ### Wrongly Dismissing Valid Findings
181
+
182
+ - "It's only reachable in debug mode" -- verify debug mode is truly
183
+ never enabled in production; many clients ship with debug flags on
184
+ - "The attacker would need local access" -- local access is a realistic
185
+ threat model for many deployments, especially containerized services
186
+ - "Nobody uses that API" -- confirm with actual usage data, not
187
+ assumptions; check client's integration tests and deployment configs
188
+ - "The spec allows it" -- check whether the implementation claims
189
+ stricter behavior than the spec requires
190
+
191
+ ### Wrongly Accepting Invalid Findings
192
+
193
+ - "It has a CVE, so it must be real" -- Brocard 7 exists for this reason
194
+ - "The CVSS score is high" -- CVSS is a formula, not a verdict
195
+ - "Better safe than sorry" -- Brocard 6 requires evaluating fix cost
196
+ - "We can't prove it's NOT exploitable" -- the burden of proof is on the
197
+ reporter to demonstrate a threat model (Brocard 1)
198
+ - "Other projects patched it" -- other projects may have different usage
199
+ patterns (Brocard 3)
200
+ - "We should include it to pad the report" -- ToB reports reflect
201
+ technical reality, not finding count targets; a dismissed report with
202
+ documented reasoning is more valuable than a false positive in a
203
+ final deliverable
204
+
205
+ ## Detailed References
206
+
207
+ For expanded explanations, examples, and edge cases for each brocard, consult
208
+ [`references/brocards-detail.md`](references/brocards-detail.md).
@@ -46,20 +46,6 @@ Skip any step = lying, not verifying
46
46
  | Regression test works | Red-green cycle verified | Test passes once |
47
47
  | Agent completed | VCS diff shows changes | Agent reports "success" |
48
48
  | Requirements met | Line-by-line checklist | Tests passing |
49
- | UI works | Playwright browser E2E DOM & visual assertions pass | `curl` 200/302 (server responding ≠ UI works) |
50
- | Feature bundled | Browser runtime executes & renders component | `grep -c` on compiled JS (string in bundle ≠ runtime behavior) |
51
- | App ready | Runtime deployment & behavior verified | `tsc --noEmit` passing (types compile ≠ app works) |
52
- | Service healthy | Actual feature functionality verified | "Container healthy" (daemon started ≠ feature works) |
53
- | Code edit works | Running app verified in runtime/browser | Reading source code to confirm edit is present |
54
-
55
- ## Browser & UI Verification Gate (Playwright E2E)
56
-
57
- For any task with UI impact (including backend tasks like database migrations or API payload changes that affect user screens):
58
- - **Mandatory Browser Execution**: Must execute Playwright E2E tests in a real browser context.
59
- - **Visual DOM & Layout Checks**: Assert element visibility (`expect(locator).toBeVisible()`) and non-zero bounding box geometry (`boundingBox().height > 0`).
60
- - **Console Trapping**: Listen for uncaught runtime exceptions via `page.on('pageerror')`.
61
- - **Screenshot Policy**: Do not save screenshots to disk unless explicitly requested by the user.
62
- - **Environment Gate**: If Playwright is not in the workspace, flag during planning to confirm installation path with user.
63
49
 
64
50
  ## Red Flags - STOP
65
51
 
@@ -40,20 +40,20 @@ deliverable needs them; split only where a reviewer could meaningfully
40
40
  reject one task while approving its neighbor. Each task ends with an
41
41
  independently testable deliverable.
42
42
 
43
- ## Step Granularity
44
-
45
- **Each step is one action with a checkable result:**
46
- - "Write the failing test" - step
47
- - "Run it to make sure it fails" - step
48
- - "Implement the minimal code to make the test pass" - step
49
- - "Run the tests and make sure they pass" - step
50
- - "Commit" - step
43
+ ## Step Granularity & STE Discipline
44
+
45
+ **Each step is one action with a checkable result, adhering strictly to Simplified Technical English (STE):**
46
+ - **Imperative Verb First**: Begin with `Create`, `Modify`, `Assert`, `Verify`, `Delete`, `Run`, or `Replace`.
47
+ - **Word Limit**: Maximum 20 words per procedural step.
48
+ - **Banned Vague Qualifiers**: Never use `ensure`, `properly`, `appropriately`, `as needed`, `gracefully`, `robustly`, or `etc.` Replace with observable, testable assertions.
49
+ - "Write the failing test in `tests/feature.test.ts`" - step
50
+ - "Run `npm test tests/feature.test.ts` to confirm failure" - step
51
+ - "Implement minimal code in `src/feature.ts` to pass test" - step
52
+ - "Run `npm test` and assert exit code 0" - step
53
+ - "Commit changes with concise message" - step
51
54
 
52
55
  ## Plan Document Header
53
56
 
54
- > [!IMPORTANT]
55
- > **Canonical Plan Schema**: In cross-agent environments governed by Heimdall doctrine, plans must strictly adhere to the 7-Section Canonical Plan Template in [`playbooks/05-canonical-plan-template.md`](file:///C:/Apps/heimdall-agent/playbooks/05-canonical-plan-template.md). Generic or abbreviated templates are strictly prohibited.
56
-
57
57
  **Every plan MUST start with this header:**
58
58
 
59
59
  ```markdown
@@ -154,10 +154,6 @@ of step carries what makes it unambiguous and nothing more:
154
154
  tests do not determine, or for exact copy the spec fixes.
155
155
  - **A verification step:** the command to run and the output that means it
156
156
  passed.
157
- - **No Pseudo-Verification**: For UI or user-facing features, never specify `tsc --noEmit`, `curl`, `grep bundle`, or container status as the verification step.
158
- - **Browser E2E Required**: Web/UI tasks must specify Playwright E2E browser verification (checking DOM state, `toBeVisible()`, and non-zero bounding box geometry).
159
- - **Backend Tasks with UI Impact**: If a backend task (e.g. database migration, API payload change) alters data visible on user screens, include browser UI verification in the plan.
160
- - **Playwright Environment Detection**: If Playwright is not yet present in the workspace, the plan must surface this during initial authoring and prompt the human for preferred setup.
161
157
  - **A reference to another task:** that task's Interfaces block says what
162
158
  to use; the plan does not repeat that task's code.
163
159