claudify-agent 1.0.1 → 1.0.2

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 (47) hide show
  1. package/.claude/QUICK-REFERENCE.md +213 -213
  2. package/.claude/cost-dashboard.md +162 -162
  3. package/.claude/docs/COST-OPTIMIZATION.md +402 -403
  4. package/.claude/docs/MCP-INTEGRATION-GUIDE.md +348 -348
  5. package/.claude/docs/PLAN-MODE-OPTIMIZATION.md +835 -836
  6. package/.claude/hooks/auto-learning-review.ts +200 -195
  7. package/.claude/hooks/auto-lint-fix.ts +60 -104
  8. package/.claude/hooks/auto-security-review.ts +314 -354
  9. package/.claude/hooks/auto-validate.ts +249 -348
  10. package/.claude/hooks/lib/claude-hook.ts +168 -0
  11. package/.claude/hooks/plan-quality-tracker.ts +598 -719
  12. package/.claude/rules/anti-patterns.md +22 -22
  13. package/.claude/rules/context-tier-1.md +41 -41
  14. package/.claude/rules/context-tier-2.md +285 -285
  15. package/.claude/rules/general.md +25 -25
  16. package/.claude/rules/mcp-auto-use.md +46 -46
  17. package/.claude/rules/parallel-exploration-auto.md +30 -31
  18. package/.claude/rules/plan-mode-execution.md +289 -289
  19. package/.claude/rules/plan-mode-research.md +34 -34
  20. package/.claude/rules/plan-mode-structure.md +166 -166
  21. package/.claude/rules/plan-mode-validation.md +129 -130
  22. package/.claude/rules/security-critical.md +19 -19
  23. package/.claude/rules/tool-auto-selection.md +45 -45
  24. package/.claude/rules/tool-strategy.md +22 -22
  25. package/.claude/scripts/security-scan.js +1 -1
  26. package/.claude/security-dashboard.md +142 -142
  27. package/.claude/settings.json +50 -0
  28. package/.claude/skills/debug-optimizer/SKILL.md +420 -399
  29. package/.claude/skills/learning-loop/SKILL.md +313 -308
  30. package/.claude/skills/mcp-mastery/SKILL.md +218 -214
  31. package/.claude/skills/nextjs-guide/SKILL.md +687 -687
  32. package/.claude/skills/parallel-exploration/SKILL.md +197 -193
  33. package/.claude/skills/plan-mode-mastery/SKILL.md +268 -263
  34. package/.claude/skills/python-guide/SKILL.md +822 -822
  35. package/.claude/skills/react-guide/SKILL.md +762 -762
  36. package/.claude/skills/{security.md → security-guide/SKILL.md} +10 -0
  37. package/.claude/skills/solidity-guide/SKILL.md +5 -0
  38. package/.claude/skills/tool-selection/SKILL.md +433 -428
  39. package/.claude/skills/vite-guide/SKILL.md +445 -445
  40. package/CLAUDE.md +1 -0
  41. package/README.md +74 -35
  42. package/README.vi.md +106 -0
  43. package/bin/cli.js +13 -4
  44. package/package.json +9 -1
  45. package/.claude/skills/debug-optimizer.md +0 -12
  46. package/.claude/skills/nextjs.md +0 -13
  47. package/.claude/skills/react.md +0 -12
@@ -1,22 +1,22 @@
1
- # Anti-Pattern Detection
2
-
3
- ## Triggers
4
- Detected automatically by learning-loop skill from plan-metrics.json
5
-
6
- ## Common Anti-Patterns
7
- - Over-engineering (using expensive tools unnecessarily)
8
- - Planning without research (no SemanticSearch)
9
- - Repeated failures (low accuracy x3)
10
- - MCP overuse (>3 MCPs with low accuracy)
11
- - Skipping validation (no ReadLints/tests)
12
-
13
- ## Actions
14
- 1. Review `.cursor/plan-metrics.json` for patterns
15
- 2. Run `/learning-loop-analyze` for detailed report
16
- 3. Update rules only for repeated patterns (3+ occurrences)
17
-
18
- ## Prevention
19
- - Follow tool escalation protocol (Tier 1 → Tier 4)
20
- - Always research before planning
21
- - Auto-validate after changes
22
- - Keep rules minimal (<20 lines)
1
+ # Anti-Pattern Detection
2
+
3
+ ## Triggers
4
+ Detected automatically by learning-loop skill from plan-metrics.json
5
+
6
+ ## Common Anti-Patterns
7
+ - Over-engineering (using expensive tools unnecessarily)
8
+ - Planning without research (no Explore (quick))
9
+ - Repeated failures (low accuracy x3)
10
+ - MCP overuse (>3 MCPs with low accuracy)
11
+ - Skipping validation (no Lint check/tests)
12
+
13
+ ## Actions
14
+ 1. Review `.claude/plan-metrics.json` for patterns
15
+ 2. Run `/learning-loop-analyze` for detailed report
16
+ 3. Update rules only for repeated patterns (3+ occurrences)
17
+
18
+ ## Prevention
19
+ - Follow tool escalation protocol (Tier 1 → Tier 4)
20
+ - Always research before planning
21
+ - Auto-validate after changes
22
+ - Keep rules minimal (<20 lines)
@@ -1,41 +1,41 @@
1
- # Context Tier 1 (Always Loaded)
2
-
3
- ## Minimal Essential Context
4
-
5
- **Purpose**: Always-loaded context (5-10 lines) providing critical constraints only.
6
-
7
- ---
8
-
9
- ## Critical Constraints
10
-
11
- ```
12
- - Use ES modules (import/export), not CommonJS
13
- - TypeScript strict mode, no `any` types
14
- - All user input validated with Zod schemas
15
- ```
16
-
17
- ---
18
-
19
- ## Essential Commands
20
-
21
- ```bash
22
- npm run lint # After substantive changes
23
- npm run test # Prefer single test files
24
- npm run typecheck # After TypeScript changes
25
- ```
26
-
27
- ---
28
-
29
- ## Canonical Examples
30
-
31
- ```
32
- Component pattern: @components/Button.tsx
33
- API route pattern: @app/api/users/route.ts
34
- Test pattern: @__tests__/auth.test.ts
35
- ```
36
-
37
- ---
38
-
39
- **Note**: This is the MINIMAL context. Task-specific context loaded from Tier 2 based on keywords and file patterns.
40
-
41
- **Rule**: If it's not in this file, agent discovers via search tools (Grep, SemanticSearch, Task).
1
+ # Context Tier 1 (Always Loaded)
2
+
3
+ ## Minimal Essential Context
4
+
5
+ **Purpose**: Always-loaded context (5-10 lines) providing critical constraints only.
6
+
7
+ ---
8
+
9
+ ## Critical Constraints
10
+
11
+ ```
12
+ - Use ES modules (import/export), not CommonJS
13
+ - TypeScript strict mode, no `any` types
14
+ - All user input validated with Zod schemas
15
+ ```
16
+
17
+ ---
18
+
19
+ ## Essential Commands
20
+
21
+ ```bash
22
+ npm run lint # After substantive changes
23
+ npm run test # Prefer single test files
24
+ npm run typecheck # After TypeScript changes
25
+ ```
26
+
27
+ ---
28
+
29
+ ## Canonical Examples
30
+
31
+ ```
32
+ Component pattern: @components/Button.tsx
33
+ API route pattern: @app/api/users/route.ts
34
+ Test pattern: @__tests__/auth.test.ts
35
+ ```
36
+
37
+ ---
38
+
39
+ **Note**: This is the MINIMAL context. Task-specific context loaded from Tier 2 based on keywords and file patterns.
40
+
41
+ **Rule**: If it's not in this file, agent discovers via search tools (Grep, Explore (quick), Agent).