heimdall-agent 1.0.0 → 1.2.0

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 (250) hide show
  1. package/README.md +57 -26
  2. package/README.pt-BR.md +443 -0
  3. package/agents/cloud-engineer.md +77 -0
  4. package/agents/code-sentinel.md +71 -34
  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 +68 -0
  9. package/agents/orchestrator.md +107 -93
  10. package/agents/reviewer.md +102 -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 +31 -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 +762 -573
  22. package/docs/SKILLS.md +393 -275
  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/2026-11-12-compare-report.json +1028 -0
  29. package/docs/runs/skill-audit/2026-11-12-upstream-audit.json +275 -0
  30. package/docs/runs/skill-audit/add_progressive_disclosure.cjs +30 -0
  31. package/docs/runs/skill-audit/check_heimdall_skills.ps1 +9 -0
  32. package/docs/runs/skill-audit/compare_classics.ps1 +26 -0
  33. package/docs/runs/skill-audit/compare_taste.ps1 +12 -0
  34. package/docs/runs/skill-audit/customization-report.json +380 -0
  35. package/docs/runs/skill-audit/diff_pending_skills.cjs +94 -0
  36. package/docs/runs/skill-audit/fetch_and_apply_skill.cjs +58 -0
  37. package/docs/runs/skill-audit/fetch_and_apply_taste_v2.cjs +65 -0
  38. package/docs/runs/skill-audit/inspect_pending_skills.cjs +71 -0
  39. package/docs/runs/skill-audit/inventory.json +308 -0
  40. package/docs/runs/skill-audit/list_local_taste.ps1 +1 -0
  41. package/docs/runs/skill-audit/phase5-update-plan.json +595 -0
  42. package/docs/runs/skill-audit/phase5-update-plan.md +138 -0
  43. package/docs/runs/skill-audit/probe.ps1 +16 -0
  44. package/docs/runs/skill-audit/probe_classics_branches.ps1 +3 -0
  45. package/docs/runs/skill-audit/probe_commits.ps1 +15 -0
  46. package/docs/runs/skill-audit/probe_repos.ps1 +17 -0
  47. package/docs/runs/skill-audit/probe_sentry_sec.ps1 +3 -0
  48. package/docs/runs/skill-audit/probe_sentry_sweep.ps1 +5 -0
  49. package/docs/runs/skill-audit/probe_snyk.ps1 +3 -0
  50. package/docs/runs/skill-audit/probe_snyk_recipes.ps1 +5 -0
  51. package/docs/runs/skill-audit/probe_taste_branches.ps1 +8 -0
  52. package/docs/runs/skill-audit/probe_taste_v19.ps1 +3 -0
  53. package/docs/runs/skill-audit/probe_user_repos.ps1 +19 -0
  54. package/docs/runs/skill-audit/prune_taste_skills.cjs +22 -0
  55. package/docs/runs/skill-audit/run_phase1_2.cjs +142 -0
  56. package/docs/runs/skill-audit/run_phase6_verification.cjs +107 -0
  57. package/docs/runs/skill-audit/show_16_details.ps1 +25 -0
  58. package/docs/runs/skill-audit/show_20_skills.ps1 +28 -0
  59. package/docs/runs/skill-audit/show_classics_diff.cjs +37 -0
  60. package/docs/runs/skill-audit/sync_agent_markdowns.cjs +30 -0
  61. package/docs/runs/skill-audit/taste-skill-upstream.md +542 -0
  62. package/docs/runs/skill-audit/update-manifest.md +88 -0
  63. package/docs/runs/skill-audit/update_config_skills.cjs +52 -0
  64. package/docs/runs/skill-audit/update_registry_phase7.cjs +83 -0
  65. package/docs/runs/skill-audit/upstream-status.json +563 -0
  66. package/docs/runs/skill-audit/verification-results.json +252 -0
  67. package/doctrine/AGENTS.md +42 -77
  68. package/hooks/git/pre-commit +11 -0
  69. package/hooks/heimdall-hook.cjs +81 -2
  70. package/hooks/herdr-agent-state.ps1 +55 -0
  71. package/hooks/hooks.json +0 -11
  72. package/lib/catalog-sync.cjs +167 -0
  73. package/lib/hermes-context.cjs +57 -0
  74. package/lib/model-context.cjs +123 -0
  75. package/lib/path-discovery.cjs +94 -0
  76. package/package.json +7 -3
  77. package/playbooks/01-interactive-grilling-gate.md +23 -6
  78. package/playbooks/02-fast-code-deep-verification.md +3 -2
  79. package/playbooks/03-adversarial-code-review.md +15 -7
  80. package/playbooks/05-canonical-plan-template.md +35 -19
  81. package/playbooks/06-model-registry-matrix.md +24 -13
  82. package/playbooks/07-legacy-code-modernization.md +74 -0
  83. package/playbooks/08-backlog-and-change-request-flow.md +122 -0
  84. package/setup.mjs +592 -172
  85. package/skills/antislop/SKILL.md +76 -56
  86. package/skills/antislop/VERSION +1 -0
  87. package/skills/antislop-copywriting/SKILL.md +407 -372
  88. package/skills/antislop-human/LICENSE-web-quality-skills +21 -0
  89. package/skills/antislop-human/SKILL.md +204 -147
  90. package/skills/antislop-human/contrast-check.py +168 -165
  91. package/skills/antislop-human/contrast-mcp.py +6 -3
  92. package/skills/antislop-human/references/A11Y-PATTERNS.md +249 -0
  93. package/skills/antislop-human/references/WCAG.md +127 -0
  94. package/skills/antislop-ui/LICENSE-web-quality-skills +21 -0
  95. package/skills/antislop-ui/SKILL.md +344 -304
  96. package/skills/antislop-ui/references/CORE-WEB-VITALS.md +181 -0
  97. package/skills/antislop-ui/references/WEB-BASELINE.md +28 -0
  98. package/skills/brainstorming/SKILL.md +296 -265
  99. package/skills/brainstorming/builder-check-prompt.md +23 -0
  100. package/skills/brainstorming/scripts/frame-template.html +213 -213
  101. package/skills/brainstorming/scripts/server.cjs +723 -723
  102. package/skills/brandkit/SKILL.md +798 -798
  103. package/skills/brutalist-skill/SKILL.md +93 -92
  104. package/skills/caveman/README.md +68 -0
  105. package/skills/caveman/SKILL.md +73 -38
  106. package/skills/claude-collaborator/SKILL.md +24 -44
  107. package/skills/clean-code/SKILL.md +152 -0
  108. package/skills/cloudflare-security-audit/AI-AND-LLM.md +83 -83
  109. package/skills/cloudflare-security-audit/ATTACK-CLASSES.md +130 -130
  110. package/skills/cloudflare-security-audit/CLIENT-SIDE.md +83 -83
  111. package/skills/cloudflare-security-audit/CLOUD-AND-DEPLOYMENT.md +86 -86
  112. package/skills/cloudflare-security-audit/DATA-ISOLATION-AND-LIFECYCLE.md +84 -84
  113. package/skills/cloudflare-security-audit/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -89
  114. package/skills/cloudflare-security-audit/HUNTING.md +251 -251
  115. package/skills/cloudflare-security-audit/MEMORY-SAFETY-AND-BINARY.md +101 -101
  116. package/skills/cloudflare-security-audit/PROTOCOLS-RPC-AND-MESSAGING.md +81 -81
  117. package/skills/cloudflare-security-audit/RECONNAISSANCE.md +156 -156
  118. package/skills/cloudflare-security-audit/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -78
  119. package/skills/cloudflare-security-audit/SKILL.md +192 -192
  120. package/skills/cloudflare-security-audit/SUPPLY-CHAIN-AND-RELEASE.md +73 -73
  121. package/skills/cloudflare-security-audit/VALIDATION-AND-REPORTING.md +186 -186
  122. package/skills/cloudflare-security-audit/WEB-PROTOCOL-AND-AUTH.md +105 -105
  123. package/skills/cloudflare-security-audit/report-schema.json +461 -461
  124. package/skills/cloudflare-security-audit/validate-coverage-ledger.cjs +872 -872
  125. package/skills/cloudflare-security-audit/validate-coverage-ledger.test.cjs +740 -740
  126. package/skills/cloudflare-security-audit/validate-findings.cjs +773 -773
  127. package/skills/cloudflare-security-audit/validate-findings.test.cjs +652 -652
  128. package/skills/codebase-design/DEEPENING.md +37 -0
  129. package/skills/codebase-design/DESIGN-IT-TWICE.md +44 -0
  130. package/skills/codebase-design/SKILL.md +114 -0
  131. package/skills/codex-collaborator/SKILL.md +24 -45
  132. package/skills/communication-doctrine/SKILL.md +89 -0
  133. package/skills/diagnosing-superpowers/SKILL.md +1 -1
  134. package/skills/diagnosing-superpowers/references/github-issues.md +3 -3
  135. package/skills/diagnosing-superpowers/templates/issue.md +23 -4
  136. package/skills/domain-modeling/ADR-FORMAT.md +47 -0
  137. package/skills/domain-modeling/GLOSSARY-FORMAT.md +60 -0
  138. package/skills/domain-modeling/SKILL.md +74 -0
  139. package/skills/executing-plans/SKILL.md +6 -56
  140. package/skills/executing-plans/scripts/task-done +52 -52
  141. package/skills/executing-plans/scripts/task-start +28 -28
  142. package/skills/gemini-collaborator/SKILL.md +24 -56
  143. package/skills/grill-me/SKILL.md +65 -0
  144. package/skills/handoff/SKILL.md +64 -0
  145. package/skills/herdr/SKILL.md +243 -0
  146. package/skills/image-to-code-skill/SKILL.md +1228 -1228
  147. package/skills/imagegen-frontend-mobile/SKILL.md +1465 -1465
  148. package/skills/imagegen-frontend-web/SKILL.md +987 -987
  149. package/skills/improve-codebase-architecture/HTML-REPORT.md +123 -0
  150. package/skills/improve-codebase-architecture/SKILL.md +71 -0
  151. package/skills/karpathy-guidelines/SKILL.md +67 -67
  152. package/skills/mcp-engineering/SKILL.md +74 -0
  153. package/skills/minimalist-skill/SKILL.md +87 -85
  154. package/skills/output-skill/SKILL.md +49 -49
  155. package/skills/owasp-security/reference/config-and-supply-chain.md +346 -344
  156. package/skills/owasp-security/reference/languages.md +378 -372
  157. package/skills/owasp-security/reference/owasp-report.md +1144 -1140
  158. package/skills/owasp-security/reference/review-checklist.md +134 -132
  159. package/skills/ponytail/SKILL.md +36 -52
  160. package/skills/postgres-best-practices/SKILL.md +30 -52
  161. package/skills/postgres-best-practices/references/backup-restore.md +372 -0
  162. package/skills/postgres-best-practices/references/bulk-loading.md +315 -0
  163. package/skills/postgres-best-practices/references/connection-pooling.md +310 -0
  164. package/skills/postgres-best-practices/references/hot-standby.md +221 -0
  165. package/skills/postgres-best-practices/references/indexing.md +318 -0
  166. package/skills/postgres-best-practices/references/logical-replication.md +610 -0
  167. package/skills/postgres-best-practices/references/major-version-upgrades.md +334 -0
  168. package/skills/postgres-best-practices/references/performance-diagnostics.md +553 -0
  169. package/skills/postgres-best-practices/references/query-optimization.md +294 -0
  170. package/skills/postgres-best-practices/references/query-patterns.md +566 -0
  171. package/skills/postgres-best-practices/references/schema-design.md +362 -0
  172. package/skills/postgres-best-practices/references/security-roles.md +489 -0
  173. package/skills/postgres-best-practices/references/transaction-isolation.md +344 -0
  174. package/skills/progressive-disclosure/SKILL.md +68 -0
  175. package/skills/pstack-discipline/SKILL.md +40 -0
  176. package/skills/receiving-code-review/SKILL.md +2 -23
  177. package/skills/requesting-code-review/SKILL.md +7 -36
  178. package/skills/soft-skill/SKILL.md +99 -98
  179. package/skills/stitch-skill/DESIGN.md +121 -121
  180. package/skills/stitch-skill/SKILL.md +185 -184
  181. package/skills/strix-security/SKILL.md +54 -53
  182. package/skills/subagent-driven-development/SKILL.md +35 -264
  183. package/skills/subagent-driven-development/references/batching.md +11 -0
  184. package/skills/subagent-driven-development/references/cannot-verify.md +10 -0
  185. package/skills/subagent-driven-development/references/final-review.md +47 -0
  186. package/skills/subagent-driven-development/references/fix-loop.md +77 -0
  187. package/skills/subagent-driven-development/references/handling-reports.md +15 -0
  188. package/skills/subagent-driven-development/references/preflight.md +26 -0
  189. package/skills/subagent-driven-development/references/resuming.md +12 -0
  190. package/skills/subagent-driven-development/scripts/review-package +53 -53
  191. package/skills/subagent-driven-development/scripts/sdd-workspace +87 -82
  192. package/skills/subagent-driven-development/scripts/task-brief +43 -43
  193. package/skills/systematic-debugging/SKILL.md +283 -306
  194. package/skills/taste-skill/SKILL.md +542 -1206
  195. package/skills/taste-skill/references/app-screens.md +1199 -0
  196. package/skills/taste-skill/references/colour.md +141 -0
  197. package/skills/taste-skill/references/copy.md +177 -0
  198. package/skills/taste-skill/references/critique.md +182 -0
  199. package/skills/taste-skill/references/imagery.md +791 -0
  200. package/skills/taste-skill/references/layout.md +292 -0
  201. package/skills/taste-skill/references/motion.md +980 -0
  202. package/skills/taste-skill/references/research.md +356 -0
  203. package/skills/taste-skill/references/scenes.md +174 -0
  204. package/skills/taste-skill/references/tells.md +115 -0
  205. package/skills/taste-skill/references/type.md +170 -0
  206. package/skills/test-driven-development/SKILL.md +330 -337
  207. package/skills/thermo/SKILL.md +67 -0
  208. package/skills/threat-modeling/SKILL.md +55 -0
  209. package/skills/to-spec/SKILL.md +75 -0
  210. package/skills/to-tickets/SKILL.md +105 -0
  211. package/skills/trailofbits-audit-context/SKILL.md +72 -72
  212. package/skills/trailofbits-insecure-defaults/commands/audit.md +35 -0
  213. package/skills/trailofbits-insecure-defaults/references/debug-features.json +13 -13
  214. package/skills/trailofbits-insecure-defaults/references/debug-features.md +75 -75
  215. package/skills/trailofbits-insecure-defaults/references/default-credentials.json +12 -12
  216. package/skills/trailofbits-insecure-defaults/references/default-credentials.md +76 -76
  217. package/skills/trailofbits-insecure-defaults/references/fail-open-security.json +11 -11
  218. package/skills/trailofbits-insecure-defaults/references/fail-open-security.md +70 -70
  219. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.json +11 -11
  220. package/skills/trailofbits-insecure-defaults/references/fallback-secrets.md +70 -70
  221. package/skills/trailofbits-insecure-defaults/references/permissive-access.json +13 -13
  222. package/skills/trailofbits-insecure-defaults/references/permissive-access.md +62 -62
  223. package/skills/trailofbits-insecure-defaults/references/weak-crypto.json +13 -13
  224. package/skills/trailofbits-insecure-defaults/references/weak-crypto.md +71 -71
  225. package/skills/trailofbits-triage-brocards/SKILL.md +208 -208
  226. package/skills/verification-before-completion/SKILL.md +0 -14
  227. package/skills/wayfinder/SKILL.md +128 -0
  228. package/skills/writing-plans/SKILL.md +11 -15
  229. package/skills/writing-skills/SKILL.md +21 -303
  230. package/skills/writing-skills/references/CLAUDE_MD_TESTING.md +189 -0
  231. package/skills/writing-skills/references/anthropic-best-practices.md +1150 -0
  232. package/skills/writing-skills/references/bulletproofing.md +80 -0
  233. package/skills/writing-skills/references/discovery.md +201 -0
  234. package/skills/writing-skills/references/flowcharts.md +37 -0
  235. package/skills/writing-skills/references/graphviz-conventions.dot +172 -0
  236. package/skills/writing-skills/references/persuasion-principles.md +187 -0
  237. package/skills/writing-skills/references/testing-skills-with-subagents.md +384 -0
  238. package/tools/{claude-bridge.ps1 → archive/claude-bridge.ps1} +10 -7
  239. package/tools/{codex-bridge.ps1 → archive/codex-bridge.ps1} +1 -1
  240. package/tools/{gemini-bridge.ps1 → archive/gemini-bridge.ps1} +12 -19
  241. package/skills/gpt-tasteskill/SKILL.md +0 -74
  242. package/skills/taste-skill-v1/SKILL.md +0 -226
  243. /package/tools/{claude-bridge.cmd → archive/claude-bridge.cmd} +0 -0
  244. /package/tools/{claude-bridge.sh → archive/claude-bridge.sh} +0 -0
  245. /package/tools/{codex-bridge.cmd → archive/codex-bridge.cmd} +0 -0
  246. /package/tools/{codex-bridge.sh → archive/codex-bridge.sh} +0 -0
  247. /package/tools/{codexcli-bridge.cmd → archive/codexcli-bridge.cmd} +0 -0
  248. /package/tools/{codexcli-bridge.ps1 → archive/codexcli-bridge.ps1} +0 -0
  249. /package/tools/{gemini-bridge.cmd → archive/gemini-bridge.cmd} +0 -0
  250. /package/tools/{gemini-bridge.sh → archive/gemini-bridge.sh} +0 -0
@@ -1,184 +1,185 @@
1
- ---
2
- name: stitch-design-taste
3
- description: Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
4
- ---
5
-
6
- # Stitch Design Taste — Semantic Design System Skill
7
-
8
- ## Overview
9
- This skill generates `DESIGN.md` files optimized for Google Stitch screen generation. It translates the battle-tested anti-slop frontend engineering directives into Stitch's native semantic design language — descriptive, natural-language rules paired with precise values that Stitch's AI agent can interpret to produce premium, non-generic interfaces.
10
-
11
- The generated `DESIGN.md` serves as the **single source of truth** for prompting Stitch to generate new screens that align with a curated, high-agency design language. Stitch interprets design through **"Visual Descriptions"** supported by specific color values, typography specs, and component behaviors.
12
-
13
- ## Prerequisites
14
- - Access to Google Stitch via [labs.google/stitch](https://labs.google/stitch)
15
- - Optionally: Stitch MCP Server for programmatic integration with Cursor, Antigravity, or Gemini CLI
16
-
17
- ## The Goal
18
- Generate a `DESIGN.md` file that encodes:
19
- 1. **Visual atmosphere** — the mood, density, and design philosophy
20
- 2. **Color calibration** — neutrals, accents, and banned patterns with hex codes
21
- 3. **Typographic architecture** — font stacks, scale hierarchy, and anti-patterns
22
- 4. **Component behaviors** — buttons, cards, inputs with interaction states
23
- 5. **Layout principles** — grid systems, spacing philosophy, responsive strategy
24
- 6. **Motion philosophy** — animation engine specs, spring physics, perpetual micro-interactions
25
- 7. **Anti-patterns** — explicit list of banned AI design clichés
26
-
27
- ## Analysis & Synthesis Instructions
28
-
29
- ### 1. Define the Atmosphere
30
- Evaluate the target project's intent. Use evocative adjectives from the taste spectrum:
31
- - **Density:** "Art Gallery Airy" (1–3) → "Daily App Balanced" (4–7) → "Cockpit Dense" (8–10)
32
- - **Variance:** "Predictable Symmetric" (1–3) → "Offset Asymmetric" (4–7) → "Artsy Chaotic" (8–10)
33
- - **Motion:** "Static Restrained" (1–3) → "Fluid CSS" (4–7) → "Cinematic Choreography" (8–10)
34
-
35
- Default baseline: Variance 8, Motion 6, Density 4. Adapt dynamically based on user's vibe description.
36
-
37
- ### 2. Map the Color Palette
38
- For each color provide: **Descriptive Name** + **Hex Code** + **Functional Role**.
39
-
40
- **Mandatory constraints:**
41
- - Maximum 1 accent color. Saturation below 80%
42
- - The "AI Purple/Blue Neon" aesthetic is strictly BANNED — no purple button glows, no neon gradients
43
- - Use absolute neutral bases (Zinc/Slate) with high-contrast singular accents
44
- - Stick to one palette for the entire output — no warm/cool gray fluctuation
45
- - Never use pure black (`#000000`) — use Off-Black, Zinc-950, or Charcoal
46
-
47
- ### 3. Establish Typography Rules
48
- - **Display/Headlines:** Track-tight, controlled scale. Not screaming. Hierarchy through weight and color, not just massive size
49
- - **Body:** Relaxed leading, max 65 characters per line
50
- - **Font Selection:** `Inter` is BANNED for premium/creative contexts. Force unique character: `Geist`, `Outfit`, `Cabinet Grotesk`, or `Satoshi`
51
- - **Serif Ban:** Generic serif fonts (`Times New Roman`, `Georgia`, `Garamond`, `Palatino`) are BANNED. If serif is needed for editorial/creative contexts, use only distinctive modern serifs: `Fraunces`, `Gambarino`, `Editorial New`, or `Instrument Serif`. Serif is always BANNED in dashboards or software UIs
52
- - **Dashboard Constraint:** Use Sans-Serif pairings exclusively (`Geist` + `Geist Mono` or `Satoshi` + `JetBrains Mono`)
53
- - **High-Density Override:** When density exceeds 7, all numbers must use Monospace
54
-
55
- ### 4. Define the Hero Section
56
- The Hero is the first impression and must be creative, striking, and never generic:
57
- - **Inline Image Typography:** Embed small, contextual photos or visuals directly between words or letters in the headline. Images sit inline at type-height, rounded, acting as visual punctuation. This is the signature creative technique
58
- - **No Overlapping:** Text must never overlap images or other text. Every element occupies its own clean spatial zone
59
- - **No Filler Text:** "Scroll to explore", "Swipe down", scroll arrow icons, bouncing chevrons are BANNED. The content should pull users in naturally
60
- - **Asymmetric Structure:** Centered Hero layouts BANNED when variance exceeds 4
61
- - **CTA Restraint:** Maximum one primary CTA. No secondary "Learn more" links
62
-
63
- ### 5. Describe Component Stylings
64
- For each component type, describe shape, color, shadow depth, and interaction behavior:
65
- - **Buttons:** Tactile push feedback on active state. No neon outer glows. No custom mouse cursors
66
- - **Cards:** Use ONLY when elevation communicates hierarchy. Tint shadows to background hue. For high-density layouts, replace cards with border-top dividers or negative space
67
- - **Inputs/Forms:** Label above input, helper text optional, error text below. Standard gap spacing
68
- - **Loading States:** Skeletal loaders matching layout dimensions — no generic circular spinners
69
- - **Empty States:** Composed compositions indicating how to populate data
70
- - **Error States:** Clear, inline error reporting
71
-
72
- ### 6. Define Layout Principles
73
- - No overlapping elements — every element occupies its own clear spatial zone. No absolute-positioned content stacking
74
- - Centered Hero sections are BANNED when variance exceeds 4 — force Split Screen, Left-Aligned, or Asymmetric Whitespace
75
- - The generic "3 equal cards horizontally" feature row is BANNED — use 2-column Zig-Zag, asymmetric grid, or horizontal scroll
76
- - CSS Grid over Flexbox math — never use `calc()` percentage hacks
77
- - Contain layouts using max-width constraints (e.g., 1400px centered)
78
- - Full-height sections must use `min-h-[100dvh]` — never `h-screen` (iOS Safari catastrophic jump)
79
-
80
- ### 7. Define Responsive Rules
81
- Every design must work across all viewports:
82
- - **Mobile-First Collapse (< 768px):** All multi-column layouts collapse to single column. No exceptions
83
- - **No Horizontal Scroll:** Horizontal overflow on mobile is a critical failure
84
- - **Typography Scaling:** Headlines scale via `clamp()`. Body text minimum `1rem`/`14px`
85
- - **Touch Targets:** All interactive elements minimum `44px` tap target
86
- - **Image Behavior:** Inline typography images (photos between words) stack below headline on mobile
87
- - **Navigation:** Desktop horizontal nav collapses to clean mobile menu
88
- - **Spacing:** Vertical section gaps reduce proportionally (`clamp(3rem, 8vw, 6rem)`)
89
-
90
- ### 8. Encode Motion Philosophy
91
- - **Spring Physics default:** `stiffness: 100, damping: 20` — premium, weighty feel. No linear easing
92
- - **Perpetual Micro-Interactions:** Every active component should have an infinite loop state (Pulse, Typewriter, Float, Shimmer)
93
- - **Staggered Orchestration:** Never mount lists instantly — use cascade delays for waterfall reveals
94
- - **Performance:** Animate exclusively via `transform` and `opacity`. Never animate `top`, `left`, `width`, `height`. Grain/noise filters on fixed pseudo-elements only
95
-
96
- ### 9. List Anti-Patterns (AI Tells)
97
- Encode these as explicit "NEVER DO" rules in the DESIGN.md:
98
- - No emojis anywhere
99
- - No `Inter` font
100
- - No generic serif fonts (`Times New Roman`, `Georgia`, `Garamond`) — distinctive modern serifs only if needed
101
- - No pure black (`#000000`)
102
- - No neon/outer glow shadows
103
- - No oversaturated accents
104
- - No excessive gradient text on large headers
105
- - No custom mouse cursors
106
- - No overlapping elements — clean spatial separation always
107
- - No 3-column equal card layouts
108
- - No generic names ("John Doe", "Acme", "Nexus")
109
- - No fake round numbers (`99.99%`, `50%`)
110
- - No AI copywriting clichés ("Elevate", "Seamless", "Unleash", "Next-Gen")
111
- - No filler UI text: "Scroll to explore", "Swipe down", scroll arrows, bouncing chevrons
112
- - No broken Unsplash links — use `picsum.photos` or SVG avatars
113
- - No centered Hero sections (for high-variance projects)
114
-
115
- ## Output Format (DESIGN.md Structure)
116
-
117
- ```markdown
118
- # Design System: [Project Title]
119
-
120
- ## 1. Visual Theme & Atmosphere
121
- (Evocative description of the mood, density, variance, and motion intensity.
122
- Example: "A restrained, gallery-airy interface with confident asymmetric layouts
123
- and fluid spring-physics motion. The atmosphere is clinical yet warm — like a
124
- well-lit architecture studio.")
125
-
126
- ## 2. Color Palette & Roles
127
- - **Canvas White** (#F9FAFB) — Primary background surface
128
- - **Pure Surface** (#FFFFFF) — Card and container fill
129
- - **Charcoal Ink** (#18181B) — Primary text, Zinc-950 depth
130
- - **Muted Steel** (#71717A) — Secondary text, descriptions, metadata
131
- - **Whisper Border** (rgba(226,232,240,0.5)) — Card borders, 1px structural lines
132
- - **[Accent Name]** (#XXXXXX) — Single accent for CTAs, active states, focus rings
133
- (Max 1 accent. Saturation < 80%. No purple/neon.)
134
-
135
- ## 3. Typography Rules
136
- - **Display:** [Font Name] — Track-tight, controlled scale, weight-driven hierarchy
137
- - **Body:** [Font Name] — Relaxed leading, 65ch max-width, neutral secondary color
138
- - **Mono:** [Font Name] — For code, metadata, timestamps, high-density numbers
139
- - **Banned:** Inter, generic system fonts for premium contexts. Serif fonts banned in dashboards.
140
-
141
- ## 4. Component Stylings
142
- * **Buttons:** Flat, no outer glow. Tactile -1px translate on active. Accent fill for primary, ghost/outline for secondary.
143
- * **Cards:** Generously rounded corners (2.5rem). Diffused whisper shadow. Used only when elevation serves hierarchy. High-density: replace with border-top dividers.
144
- * **Inputs:** Label above, error below. Focus ring in accent color. No floating labels.
145
- * **Loaders:** Skeletal shimmer matching exact layout dimensions. No circular spinners.
146
- * **Empty States:** Composed, illustrated compositions — not just "No data" text.
147
-
148
- ## 5. Layout Principles
149
- (Grid-first responsive architecture. Asymmetric splits for Hero sections.
150
- Strict single-column collapse below 768px. Max-width containment.
151
- No flexbox percentage math. Generous internal padding.)
152
-
153
- ## 6. Motion & Interaction
154
- (Spring physics for all interactive elements. Staggered cascade reveals.
155
- Perpetual micro-loops on active dashboard components. Hardware-accelerated
156
- transforms only. Isolated Client Components for CPU-heavy animations.)
157
-
158
- ## 7. Anti-Patterns (Banned)
159
- (Explicit list of forbidden patterns: no emojis, no Inter, no pure black,
160
- no neon glows, no 3-column equal grids, no AI copywriting clichés,
161
- no generic placeholder names, no broken image links.)
162
- ```
163
-
164
- ## Best Practices
165
- - **Be Descriptive:** "Deep Charcoal Ink (#18181B)" — not just "dark text"
166
- - **Be Functional:** Explain what each element is used for
167
- - **Be Consistent:** Same terminology throughout the document
168
- - **Be Precise:** Include exact hex codes, rem values, pixel values in parentheses
169
- - **Be Opinionated:** This is not a neutral template — it enforces a specific, premium aesthetic
170
-
171
- ## Tips for Success
172
- 1. Start with the atmosphere — understand the vibe before detailing tokens
173
- 2. Look for patterns — identify consistent spacing, sizing, and styling
174
- 3. Think semantically — name colors by purpose, not just appearance
175
- 4. Consider hierarchy — document how visual weight communicates importance
176
- 5. Encode the bans — anti-patterns are as important as the rules themselves
177
-
178
- ## Common Pitfalls to Avoid
179
- - Using technical jargon without translation ("rounded-xl" instead of "generously rounded corners")
180
- - Omitting hex codes or using only descriptive names
181
- - Forgetting functional roles of design elements
182
- - Being too vague in atmosphere descriptions
183
- - Ignoring the anti-pattern list — these are what make the output premium
184
- - Defaulting to generic "safe" designs instead of enforcing the curated aesthetic
1
+ ---
2
+ name: stitch-design-taste
3
+ description: "Classic skill for Google Stitch, opt-in: it runs only when called by name. Writes an agent-friendly DESIGN.md with strict type, colour and layout rules."
4
+ disable-model-invocation: true
5
+ ---
6
+
7
+ # Stitch Design Taste — Semantic Design System Skill
8
+
9
+ ## Overview
10
+ This skill generates `DESIGN.md` files optimized for Google Stitch screen generation. It translates the battle-tested anti-slop frontend engineering directives into Stitch's native semantic design language — descriptive, natural-language rules paired with precise values that Stitch's AI agent can interpret to produce premium, non-generic interfaces.
11
+
12
+ The generated `DESIGN.md` serves as the **single source of truth** for prompting Stitch to generate new screens that align with a curated, high-agency design language. Stitch interprets design through **"Visual Descriptions"** supported by specific color values, typography specs, and component behaviors.
13
+
14
+ ## Prerequisites
15
+ - Access to Google Stitch via [labs.google/stitch](https://labs.google/stitch)
16
+ - Optionally: Stitch MCP Server for programmatic integration with Cursor, Antigravity, or Gemini CLI
17
+
18
+ ## The Goal
19
+ Generate a `DESIGN.md` file that encodes:
20
+ 1. **Visual atmosphere** — the mood, density, and design philosophy
21
+ 2. **Color calibration** — neutrals, accents, and banned patterns with hex codes
22
+ 3. **Typographic architecture** — font stacks, scale hierarchy, and anti-patterns
23
+ 4. **Component behaviors** — buttons, cards, inputs with interaction states
24
+ 5. **Layout principles** — grid systems, spacing philosophy, responsive strategy
25
+ 6. **Motion philosophy** — animation engine specs, spring physics, perpetual micro-interactions
26
+ 7. **Anti-patterns** — explicit list of banned AI design clichés
27
+
28
+ ## Analysis & Synthesis Instructions
29
+
30
+ ### 1. Define the Atmosphere
31
+ Evaluate the target project's intent. Use evocative adjectives from the taste spectrum:
32
+ - **Density:** "Art Gallery Airy" (1–3) → "Daily App Balanced" (4–7) → "Cockpit Dense" (8–10)
33
+ - **Variance:** "Predictable Symmetric" (1–3) → "Offset Asymmetric" (4–7) → "Artsy Chaotic" (8–10)
34
+ - **Motion:** "Static Restrained" (1–3) → "Fluid CSS" (4–7) → "Cinematic Choreography" (8–10)
35
+
36
+ Default baseline: Variance 8, Motion 6, Density 4. Adapt dynamically based on user's vibe description.
37
+
38
+ ### 2. Map the Color Palette
39
+ For each color provide: **Descriptive Name** + **Hex Code** + **Functional Role**.
40
+
41
+ **Mandatory constraints:**
42
+ - Maximum 1 accent color. Saturation below 80%
43
+ - The "AI Purple/Blue Neon" aesthetic is strictly BANNED — no purple button glows, no neon gradients
44
+ - Use absolute neutral bases (Zinc/Slate) with high-contrast singular accents
45
+ - Stick to one palette for the entire output — no warm/cool gray fluctuation
46
+ - Never use pure black (`#000000`) — use Off-Black, Zinc-950, or Charcoal
47
+
48
+ ### 3. Establish Typography Rules
49
+ - **Display/Headlines:** Track-tight, controlled scale. Not screaming. Hierarchy through weight and color, not just massive size
50
+ - **Body:** Relaxed leading, max 65 characters per line
51
+ - **Font Selection:** `Inter` is BANNED for premium/creative contexts. Force unique character: `Geist`, `Outfit`, `Cabinet Grotesk`, or `Satoshi`
52
+ - **Serif Ban:** Generic serif fonts (`Times New Roman`, `Georgia`, `Garamond`, `Palatino`) are BANNED. If serif is needed for editorial/creative contexts, use only distinctive modern serifs: `Fraunces`, `Gambarino`, `Editorial New`, or `Instrument Serif`. Serif is always BANNED in dashboards or software UIs
53
+ - **Dashboard Constraint:** Use Sans-Serif pairings exclusively (`Geist` + `Geist Mono` or `Satoshi` + `JetBrains Mono`)
54
+ - **High-Density Override:** When density exceeds 7, all numbers must use Monospace
55
+
56
+ ### 4. Define the Hero Section
57
+ The Hero is the first impression and must be creative, striking, and never generic:
58
+ - **Inline Image Typography:** Embed small, contextual photos or visuals directly between words or letters in the headline. Images sit inline at type-height, rounded, acting as visual punctuation. This is the signature creative technique
59
+ - **No Overlapping:** Text must never overlap images or other text. Every element occupies its own clean spatial zone
60
+ - **No Filler Text:** "Scroll to explore", "Swipe down", scroll arrow icons, bouncing chevrons are BANNED. The content should pull users in naturally
61
+ - **Asymmetric Structure:** Centered Hero layouts BANNED when variance exceeds 4
62
+ - **CTA Restraint:** Maximum one primary CTA. No secondary "Learn more" links
63
+
64
+ ### 5. Describe Component Stylings
65
+ For each component type, describe shape, color, shadow depth, and interaction behavior:
66
+ - **Buttons:** Tactile push feedback on active state. No neon outer glows. No custom mouse cursors
67
+ - **Cards:** Use ONLY when elevation communicates hierarchy. Tint shadows to background hue. For high-density layouts, replace cards with border-top dividers or negative space
68
+ - **Inputs/Forms:** Label above input, helper text optional, error text below. Standard gap spacing
69
+ - **Loading States:** Skeletal loaders matching layout dimensions — no generic circular spinners
70
+ - **Empty States:** Composed compositions indicating how to populate data
71
+ - **Error States:** Clear, inline error reporting
72
+
73
+ ### 6. Define Layout Principles
74
+ - No overlapping elements — every element occupies its own clear spatial zone. No absolute-positioned content stacking
75
+ - Centered Hero sections are BANNED when variance exceeds 4 — force Split Screen, Left-Aligned, or Asymmetric Whitespace
76
+ - The generic "3 equal cards horizontally" feature row is BANNED — use 2-column Zig-Zag, asymmetric grid, or horizontal scroll
77
+ - CSS Grid over Flexbox math — never use `calc()` percentage hacks
78
+ - Contain layouts using max-width constraints (e.g., 1400px centered)
79
+ - Full-height sections must use `min-h-[100dvh]` — never `h-screen` (iOS Safari catastrophic jump)
80
+
81
+ ### 7. Define Responsive Rules
82
+ Every design must work across all viewports:
83
+ - **Mobile-First Collapse (< 768px):** All multi-column layouts collapse to single column. No exceptions
84
+ - **No Horizontal Scroll:** Horizontal overflow on mobile is a critical failure
85
+ - **Typography Scaling:** Headlines scale via `clamp()`. Body text minimum `1rem`/`14px`
86
+ - **Touch Targets:** All interactive elements minimum `44px` tap target
87
+ - **Image Behavior:** Inline typography images (photos between words) stack below headline on mobile
88
+ - **Navigation:** Desktop horizontal nav collapses to clean mobile menu
89
+ - **Spacing:** Vertical section gaps reduce proportionally (`clamp(3rem, 8vw, 6rem)`)
90
+
91
+ ### 8. Encode Motion Philosophy
92
+ - **Spring Physics default:** `stiffness: 100, damping: 20` — premium, weighty feel. No linear easing
93
+ - **Perpetual Micro-Interactions:** Every active component should have an infinite loop state (Pulse, Typewriter, Float, Shimmer)
94
+ - **Staggered Orchestration:** Never mount lists instantly — use cascade delays for waterfall reveals
95
+ - **Performance:** Animate exclusively via `transform` and `opacity`. Never animate `top`, `left`, `width`, `height`. Grain/noise filters on fixed pseudo-elements only
96
+
97
+ ### 9. List Anti-Patterns (AI Tells)
98
+ Encode these as explicit "NEVER DO" rules in the DESIGN.md:
99
+ - No emojis anywhere
100
+ - No `Inter` font
101
+ - No generic serif fonts (`Times New Roman`, `Georgia`, `Garamond`) — distinctive modern serifs only if needed
102
+ - No pure black (`#000000`)
103
+ - No neon/outer glow shadows
104
+ - No oversaturated accents
105
+ - No excessive gradient text on large headers
106
+ - No custom mouse cursors
107
+ - No overlapping elements — clean spatial separation always
108
+ - No 3-column equal card layouts
109
+ - No generic names ("John Doe", "Acme", "Nexus")
110
+ - No fake round numbers (`99.99%`, `50%`)
111
+ - No AI copywriting clichés ("Elevate", "Seamless", "Unleash", "Next-Gen")
112
+ - No filler UI text: "Scroll to explore", "Swipe down", scroll arrows, bouncing chevrons
113
+ - No broken Unsplash links — use `picsum.photos` or SVG avatars
114
+ - No centered Hero sections (for high-variance projects)
115
+
116
+ ## Output Format (DESIGN.md Structure)
117
+
118
+ ```markdown
119
+ # Design System: [Project Title]
120
+
121
+ ## 1. Visual Theme & Atmosphere
122
+ (Evocative description of the mood, density, variance, and motion intensity.
123
+ Example: "A restrained, gallery-airy interface with confident asymmetric layouts
124
+ and fluid spring-physics motion. The atmosphere is clinical yet warm — like a
125
+ well-lit architecture studio.")
126
+
127
+ ## 2. Color Palette & Roles
128
+ - **Canvas White** (#F9FAFB) — Primary background surface
129
+ - **Pure Surface** (#FFFFFF) — Card and container fill
130
+ - **Charcoal Ink** (#18181B) — Primary text, Zinc-950 depth
131
+ - **Muted Steel** (#71717A) — Secondary text, descriptions, metadata
132
+ - **Whisper Border** (rgba(226,232,240,0.5)) — Card borders, 1px structural lines
133
+ - **[Accent Name]** (#XXXXXX) — Single accent for CTAs, active states, focus rings
134
+ (Max 1 accent. Saturation < 80%. No purple/neon.)
135
+
136
+ ## 3. Typography Rules
137
+ - **Display:** [Font Name] — Track-tight, controlled scale, weight-driven hierarchy
138
+ - **Body:** [Font Name] — Relaxed leading, 65ch max-width, neutral secondary color
139
+ - **Mono:** [Font Name] — For code, metadata, timestamps, high-density numbers
140
+ - **Banned:** Inter, generic system fonts for premium contexts. Serif fonts banned in dashboards.
141
+
142
+ ## 4. Component Stylings
143
+ * **Buttons:** Flat, no outer glow. Tactile -1px translate on active. Accent fill for primary, ghost/outline for secondary.
144
+ * **Cards:** Generously rounded corners (2.5rem). Diffused whisper shadow. Used only when elevation serves hierarchy. High-density: replace with border-top dividers.
145
+ * **Inputs:** Label above, error below. Focus ring in accent color. No floating labels.
146
+ * **Loaders:** Skeletal shimmer matching exact layout dimensions. No circular spinners.
147
+ * **Empty States:** Composed, illustrated compositions — not just "No data" text.
148
+
149
+ ## 5. Layout Principles
150
+ (Grid-first responsive architecture. Asymmetric splits for Hero sections.
151
+ Strict single-column collapse below 768px. Max-width containment.
152
+ No flexbox percentage math. Generous internal padding.)
153
+
154
+ ## 6. Motion & Interaction
155
+ (Spring physics for all interactive elements. Staggered cascade reveals.
156
+ Perpetual micro-loops on active dashboard components. Hardware-accelerated
157
+ transforms only. Isolated Client Components for CPU-heavy animations.)
158
+
159
+ ## 7. Anti-Patterns (Banned)
160
+ (Explicit list of forbidden patterns: no emojis, no Inter, no pure black,
161
+ no neon glows, no 3-column equal grids, no AI copywriting clichés,
162
+ no generic placeholder names, no broken image links.)
163
+ ```
164
+
165
+ ## Best Practices
166
+ - **Be Descriptive:** "Deep Charcoal Ink (#18181B)" — not just "dark text"
167
+ - **Be Functional:** Explain what each element is used for
168
+ - **Be Consistent:** Same terminology throughout the document
169
+ - **Be Precise:** Include exact hex codes, rem values, pixel values in parentheses
170
+ - **Be Opinionated:** This is not a neutral template — it enforces a specific, premium aesthetic
171
+
172
+ ## Tips for Success
173
+ 1. Start with the atmosphere — understand the vibe before detailing tokens
174
+ 2. Look for patterns — identify consistent spacing, sizing, and styling
175
+ 3. Think semantically — name colors by purpose, not just appearance
176
+ 4. Consider hierarchy — document how visual weight communicates importance
177
+ 5. Encode the bans — anti-patterns are as important as the rules themselves
178
+
179
+ ## Common Pitfalls to Avoid
180
+ - Using technical jargon without translation ("rounded-xl" instead of "generously rounded corners")
181
+ - Omitting hex codes or using only descriptive names
182
+ - Forgetting functional roles of design elements
183
+ - Being too vague in atmosphere descriptions
184
+ - Ignoring the anti-pattern list — these are what make the output premium
185
+ - Defaulting to generic "safe" designs instead of enforcing the curated aesthetic
@@ -1,65 +1,66 @@
1
1
  ---
2
- name: strix-security
3
- description: Autonomous AI penetration testing and dynamic HTTP differential probing methodology (based on usestrix/strix). Never trust code comments alone; verify every mounted route, static asset prefix, reverse-proxy rule, and Host-header boundary with concrete Proof-of-Concept (PoC) HTTP probes across Anonymous, Unprivileged, Cross-Tenant/Venue, and Authorized principals.
2
+ name: application-security-testing
3
+ description: Application security testing (AppSec) across a whole product with Strix — decide which asset needs which test (source code, running web app, API, CI pipeline), run it, and turn the results into a ranked remediation plan. Autonomous agents exploit and prove each issue instead of emitting static-analysis alerts, so the plan is ordered by what is actually reachable. Use when the user asks for an application security review or audit, an appsec assessment, vulnerability scanning across their stack, a security review before a launch or a customer security questionnaire, or does not yet know which kind of security test they need.
4
+ license: Apache-2.0
5
+ metadata:
6
+ author: usestrix
7
+ homepage: https://docs.strix.ai
4
8
  ---
5
9
 
6
- # Strix Security — Dynamic Penetration Testing & Differential HTTP Probing
10
+ # Application security testing
7
11
 
8
- Based on the open-source [usestrix/strix](https://github.com/usestrix/strix) autonomous penetration testing framework. This skill closes the gap between **static code reading** and **runtime exploitability** by requiring dynamic, differential HTTP verification of every surface.
12
+ Entry point for "make my application secure" requests, where the target is not yet a single URL or repo. The job here is to pick the right test per asset, run it, and produce one ranked plan — not to run everything at maximum depth.
9
13
 
10
- ## Core Doctrine: "Comments Are Claims, Not Controls"
14
+ Install, LLM setup, all CLI flags, and the managed-cloud path live in the **penetration-testing-with-strix** skill. Read it first if `strix --version` fails. For a run with no Docker and no LLM key, the same binary drives the managed platform: `strix cloud login`, then `strix cloud scans start ...` (details in **managed-pentesting-with-strix**).
11
15
 
12
- Static security audits fail when an auditor reads a code comment (e.g., *"Caddy blocks `/internal/*`"* or *"Caddy gates `/data/*` via `forward_auth`"*) and marks the control as `PASS` without sending a single request.
16
+ Only test assets the user owns or is authorized to test. Confirm authorization before the first run, and prefer staging over production, because the agents send real exploit payloads and can change data.
13
17
 
14
- Under `strix-security`:
15
- 1. **Zero Trust in Comments**: A comment describing a proxy rule, auth hook, or upstream gate is treated as an *unverified hypothesis* until proven by both configuration inspection and a live or injected HTTP probe.
16
- 2. **Every Static Mount Is an Attack Surface**: Every `@fastify/static` registration, `sendFile` handler, `public/` directory, and reverse-proxy `file_server` block must be enumerated and probed directly.
17
- 3. **Differential Principal Matrix**: Every protected endpoint and static data path must be probed across 4 principals:
18
- - **P0 (Anonymous)**: No session cookie, no token $\rightarrow$ Must return `401` (or `404` for internal routes).
19
- - **P1 (Unprivileged / Zero-Grant User)**: Valid session cookie, `grants: []`, `allowedModules: []` $\rightarrow$ Must return `403`.
20
- - **P2 (Cross-Scope / Wrong-Venue User)**: Valid session cookie with a grant on Venue A (`MCC`), requesting Venue B (`ALA`) tiles, metadata, or API routes $\rightarrow$ Must return `403`.
21
- - **P3 (Authorized User)**: Valid session cookie with a grant on Venue B (`ALA`) $\rightarrow$ Returns `200` with `Cache-Control: private, no-cache, no-store, must-revalidate`.
18
+ ## 1. Map the assets
22
19
 
23
- ---
20
+ Ask (or read from the repo) and write the answers down before scanning:
24
21
 
25
- ## 5 Mandatory Strix Hunting Vectors
26
-
27
- ### Vector 1: Static Asset & Extension-Bypass Probing
28
- - **Target**: Global `preHandler`/`onRequest` hooks (`packages/auth-node/src/plugin.ts`) and `@fastify/static` mounts (`apps/api/src/static.ts`).
29
- - **Attack**: Append static file extensions (`.png`, `.json`, `.svg`, `.js`, `.css`, `.map`) or hit static-mounted data trees (`/layer/data/<VENUE>/venue.json`, `/layer/data/<VENUE>/tiles/.../*.png`, `/data/<VENUE>/*`, `/staging/*`, `/layer/staging/*`) without a session cookie.
30
- - **Invariant**: No regex or extension allowlist may classify non-bundle paths as public. Only content-hashed bundle directories (`/assets/`, `/layer/assets/`, `/pulse/assets/`) and explicitly named public PWA files (`favicon.ico`, `manifest.json`, `service-worker.js`) may bypass session authentication.
31
-
32
- ### Vector 2: Reverse-Proxy & `Host`-Header Differential Probing
33
- - **Target**: `/internal/*`, `/api/*/internal/*`, `forward_auth` gates, and `Caddyfile` site blocks.
34
- - **Attack**: Probe internal endpoints using:
35
- 1. Primary public domain (`Host: podium.test`)
36
- 2. Alternate tunnel/edge hostnames (`Host: podium.tail42997.ts.net`)
37
- 3. Arbitrary spoofed `Host` headers (`Host: evil.example.com`, `Host: 127.0.0.1:443`)
38
- - **Invariant**:
39
- - `Caddyfile` must explicitly reject `/internal/*` and `/api/*/internal/*` at the edge (`respond @internal 404`).
40
- - Internal origin checks (`isInternallyOriginated`) must enforce a **strict internal container host allowlist** (`api:3000`, `layer:3000`, `pulse:3000`, `localhost:3000`), never just a `PUBLIC_DOMAIN` blocklist that fails open when accessed through Tailscale or an alternate DNS name.
41
-
42
- ### Vector 3: Horizontal BOLA / Cross-Venue & Cross-Team Traversal
43
- - **Target**: All venue-scoped and team-scoped routes (`/api/layer/venues/:venue/*`, `/layer/data/:venue/*`, `/data/:venue/*`, `/api/crew/*`).
44
- - **Attack**: Authenticate as a principal granted access to `MCC` and request `ALA` resources (both JSON API routes and static tile/manifest files).
45
- - **Invariant**: Every handler and static `preHandler` serving venue-specific data must verify `canSeeVenue(request, venueCode)` (or equivalent scope predicate) before reading from disk or database.
46
-
47
- ### Vector 4: Path Traversal & Sibling-Prefix Escape
48
- - **Target**: File-streaming and upload handlers (`modules/layer/src/pipeline.ts`, `/staging/*`, `/layer/staging/*`).
49
- - **Attack**: Supply `..`, URL-encoded `%2e%2e%2f`, or sibling-directory prefixes (e.g., `/srv/layer-staging-other` when base is `/srv/layer-staging`).
50
- - **Invariant**: Path containment checks must always verify `targetPath.startsWith(normalizedBase + path.sep)` (with the trailing path separator), never a bare string prefix check.
51
-
52
- ### Vector 5: Cache Poisoning & Post-Logout Artifact Persistence
53
- - **Target**: `Cache-Control` headers on `/api/*`, `/auth/*`, `/data/*`, `/layer/data/*`, `/staging/*`, and `/layer/staging/*`.
54
- - **Attack**: Inspect response headers on authenticated tile `.png` and `venue.json` responses for `public` or positive `max-age` values that allow shared proxies or browser disk caches to serve confidential drawings after logout.
55
- - **Invariant**: Every authenticated API, tile, manifest, and staging response must emit `Cache-Control: no-store` or `private, no-cache, no-store, must-revalidate`.
22
+ - **Source** — one repo, a monorepo, several services? Which languages/frameworks?
23
+ - **Running environments** — is there a staging deployment? A public production site? A local dev server only?
24
+ - **APIs** — REST, GraphQL, gRPC? Is there an OpenAPI/GraphQL schema?
25
+ - **Authentication** — can you get two test accounts in different tenants? Most high-impact bugs need them.
26
+ - **Constraints** — out-of-scope paths, whether production may be touched, budget and wall-clock limits.
56
27
 
57
- ---
28
+ If there is no staging environment and production is off limits, say so early. A code-only review is still valuable, but it cannot prove exploitability against a live app.
29
+
30
+ ## 2. Pick the right test per asset
31
+
32
+ | Asset | Skill to use |
33
+ | --- | --- |
34
+ | Repository or working tree | **find-security-vulnerabilities-in-code** |
35
+ | Live web app or staging site | **web-app-penetration-testing** |
36
+ | REST/GraphQL/gRPC API | **api-security-testing** |
37
+ | Assessment mapped to OWASP categories | **owasp-top-10-testing** |
38
+ | Every pull request, continuously | **ci-security-scanning-with-strix** |
39
+ | No Docker, no LLM key, or a report an auditor will accept | **managed-pentesting-with-strix** |
40
+
41
+ Those skills carry the flags, credential handling, and result-reading details. Do not duplicate their instructions here.
42
+
43
+ Sequence for a first assessment:
44
+
45
+ 1. Review the code. It is the cheapest run and it maps the authorization model.
46
+ 2. Pentest staging with credentials, and pass the repo as a second target so the agents keep source context.
47
+ 3. Add CI scanning, so later regressions are caught without another manual pass.
48
+
49
+ Run one asset at a time and read each report before starting the next. Findings from the code review make the live run sharper.
50
+
51
+ ## 3. Consolidate into one plan
52
+
53
+ Findings arrive per run in `strix_runs/<run>/`. Merge them into a single list and rank by **proven impact**, not by scanner severity:
54
+
55
+ 1. Validated exploits reachable without authentication.
56
+ 2. Validated cross-tenant or privilege-escalation issues.
57
+ 3. Validated issues needing an authenticated account.
58
+ 4. Unproven observations (configuration, dependency, and hardening notes) — flag as such, and never present them as confirmed vulnerabilities.
59
+
60
+ Deduplicate: the same root cause often surfaces in both the code review and the live pentest.
61
+
62
+ ## 4. Be honest about coverage
58
63
 
59
- ## Automated Execution in Podium
64
+ State plainly what was *not* tested — assets with no staging environment, categories a black-box run cannot reach (logging and alerting, supply-chain integrity, insecure design), and any run that hit its budget or turn cap before finishing. Check `run.json` status and cost against `--max-budget` for each run. An empty result set from a truncated scan is not a clean bill of health.
60
65
 
61
- Whenever executing a security audit or modifying auth/static/proxy code in Podium, run the automated Strix probe suite:
62
- ```powershell
63
- pnpm audit:security-probes
64
- ```
65
- If any probe fails, treat it as a **Critical blocker** and remediate before completing the task.
66
+ Then remediate with **fix-security-vulnerabilities-with-strix**, which re-runs Strix against each fix to prove the exploit no longer works.