bobo-ai-cli 3.0.4 → 3.0.5

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 (238) hide show
  1. package/LICENSE +21 -21
  2. package/README.md +259 -259
  3. package/bundled-skills/CORE_SKILLS.txt +18 -18
  4. package/bundled-skills/backend-expert/SKILL.md +97 -97
  5. package/bundled-skills/code-review/SKILL.md +280 -280
  6. package/bundled-skills/code-review-expert/SKILL.md +85 -85
  7. package/bundled-skills/context-budget-analyzer/SKILL.md +76 -76
  8. package/bundled-skills/context-compressor/SKILL.md +75 -75
  9. package/bundled-skills/context-optimization-suite/SKILL.md +162 -162
  10. package/bundled-skills/frontend-expert/SKILL.md +93 -93
  11. package/bundled-skills/github/SKILL.md +12 -12
  12. package/bundled-skills/high-agency/SKILL.md +473 -473
  13. package/bundled-skills/high-agency/references/builder-patterns.md +126 -126
  14. package/bundled-skills/high-agency/references/recovery-playbook.md +298 -298
  15. package/bundled-skills/memory-manager/SKILL.md +214 -214
  16. package/bundled-skills/memory-manager/references/advanced-config.md +65 -65
  17. package/bundled-skills/orchestrator/SKILL.md +681 -681
  18. package/bundled-skills/planning-with-files/SKILL.md +193 -193
  19. package/bundled-skills/skill-creator/SKILL.md +220 -220
  20. package/bundled-skills/testing-expert/SKILL.md +99 -99
  21. package/bundled-skills/verify/SKILL.md +15 -15
  22. package/dist/agent.d.ts +5 -0
  23. package/dist/agent.js +11 -1
  24. package/dist/agent.js.map +1 -1
  25. package/dist/agents/catalog.d.ts +47 -0
  26. package/dist/agents/catalog.js +63 -5
  27. package/dist/agents/catalog.js.map +1 -1
  28. package/dist/agents/router.d.ts +12 -1
  29. package/dist/agents/router.js +43 -3
  30. package/dist/agents/router.js.map +1 -1
  31. package/dist/agents/spawn.js +36 -18
  32. package/dist/agents/spawn.js.map +1 -1
  33. package/dist/autonomous.js +5 -5
  34. package/dist/cli.js +23 -21
  35. package/dist/cli.js.map +1 -1
  36. package/dist/compactor.js +39 -39
  37. package/dist/dream.js +29 -29
  38. package/dist/image-input.d.ts +44 -0
  39. package/dist/image-input.js +161 -0
  40. package/dist/image-input.js.map +1 -0
  41. package/dist/memory.js +13 -13
  42. package/dist/project.js +15 -15
  43. package/dist/repl.js +88 -0
  44. package/dist/repl.js.map +1 -1
  45. package/dist/skills.js +54 -54
  46. package/dist/sub-agents.js +65 -65
  47. package/dist/tools/browser.js +21 -21
  48. package/dist/tools/claude-code.js +10 -10
  49. package/dist/web.js +7 -7
  50. package/dist/wiki-commands.d.ts +2 -0
  51. package/dist/wiki-commands.js +249 -0
  52. package/dist/wiki-commands.js.map +1 -0
  53. package/dist/wiki.d.ts +90 -0
  54. package/dist/wiki.js +614 -0
  55. package/dist/wiki.js.map +1 -0
  56. package/knowledge/advanced-patterns.md +70 -70
  57. package/knowledge/agent-directives.md +74 -74
  58. package/knowledge/api-integration-patterns.md +102 -0
  59. package/knowledge/code-review-protocol.md +69 -0
  60. package/knowledge/dream.md +36 -36
  61. package/knowledge/engineering.md +52 -46
  62. package/knowledge/error-catalog.md +38 -33
  63. package/knowledge/event-driven-architecture.md +43 -0
  64. package/knowledge/external-alignment.md +47 -0
  65. package/knowledge/high-agency.md +73 -0
  66. package/knowledge/image-generation.md +48 -0
  67. package/knowledge/index.json +194 -169
  68. package/knowledge/llm-wiki-pattern.md +71 -0
  69. package/knowledge/long-task-management.md +79 -0
  70. package/knowledge/memory/cache-optimization-and-skill-integration.md +102 -102
  71. package/knowledge/memory/engineering-patterns.md +134 -134
  72. package/knowledge/memory/feedback_root_structure.md +15 -15
  73. package/knowledge/memory/project-contexts.md +69 -69
  74. package/knowledge/memory/tools-and-services.md +85 -85
  75. package/knowledge/memory-management.md +72 -0
  76. package/knowledge/rules/advisor-strategy.md +204 -0
  77. package/knowledge/rules/agents.md +62 -62
  78. package/knowledge/rules/blocking-rules.md +323 -323
  79. package/knowledge/rules/cache-management.md +379 -379
  80. package/knowledge/rules/capability-evolution.md +132 -132
  81. package/knowledge/rules/coding.md +126 -126
  82. package/knowledge/rules/engineering-workflows.md +225 -225
  83. package/knowledge/rules/evomap-content-guidelines.md +354 -354
  84. package/knowledge/rules/evomap-guide.md +224 -224
  85. package/knowledge/rules/external-alignment.md +22 -0
  86. package/knowledge/rules/git.md +31 -31
  87. package/knowledge/rules/hooks.md +106 -106
  88. package/knowledge/rules/performance.md +101 -101
  89. package/knowledge/rules/remotion-auto-production.md +1120 -1120
  90. package/knowledge/rules/security.md +46 -46
  91. package/knowledge/rules/testing.md +32 -32
  92. package/knowledge/rules/work-mode.md +208 -208
  93. package/knowledge/rules.md +62 -62
  94. package/knowledge/self-evolution.md +78 -0
  95. package/knowledge/self-rationalization-guard.md +52 -0
  96. package/knowledge/skills/Skill_Seekers.md +1722 -1722
  97. package/knowledge/skills/ab-test-setup.md +557 -557
  98. package/knowledge/skills/agent-sdk-dev.md +238 -238
  99. package/knowledge/skills/agent-tools.md +136 -136
  100. package/knowledge/skills/analytics-tracking.md +597 -597
  101. package/knowledge/skills/artifacts-builder.md +89 -89
  102. package/knowledge/skills/asana.md +12 -12
  103. package/knowledge/skills/backend-expert.md +97 -97
  104. package/knowledge/skills/brand-voice.md +481 -481
  105. package/knowledge/skills/browser-use.md +419 -419
  106. package/knowledge/skills/cache-optimization-skill.md +179 -179
  107. package/knowledge/skills/canvas-design.md +147 -147
  108. package/knowledge/skills/citation-validator.md +203 -203
  109. package/knowledge/skills/clangd-lsp.md +52 -52
  110. package/knowledge/skills/code-review-expert.md +85 -85
  111. package/knowledge/skills/code-review.md +280 -280
  112. package/knowledge/skills/code-simplifier.md +12 -12
  113. package/knowledge/skills/commit-commands.md +258 -258
  114. package/knowledge/skills/competitor-alternatives.md +795 -795
  115. package/knowledge/skills/content-atomizer.md +910 -910
  116. package/knowledge/skills/content-research-writer.md +605 -605
  117. package/knowledge/skills/context-optimization-suite.md +162 -162
  118. package/knowledge/skills/context7.md +12 -12
  119. package/knowledge/skills/copy-editing.md +494 -494
  120. package/knowledge/skills/copywriting.md +510 -510
  121. package/knowledge/skills/csharp-lsp.md +40 -40
  122. package/knowledge/skills/decision-making-framework.md +154 -154
  123. package/knowledge/skills/developer-growth-analysis.md +335 -335
  124. package/knowledge/skills/direct-response-copy.md +2336 -2336
  125. package/knowledge/skills/docker-expert.md +229 -229
  126. package/knowledge/skills/document-skills.md +12 -12
  127. package/knowledge/skills/documentation-expert.md +126 -126
  128. package/knowledge/skills/email-sequence.md +1061 -1061
  129. package/knowledge/skills/email-sequences.md +910 -910
  130. package/knowledge/skills/example-plugin.md +72 -72
  131. package/knowledge/skills/explanatory-output-style.md +82 -82
  132. package/knowledge/skills/feature-dev.md +458 -458
  133. package/knowledge/skills/file-organizer.md +466 -466
  134. package/knowledge/skills/firebase.disabled.md +12 -12
  135. package/knowledge/skills/form-cro.md +488 -488
  136. package/knowledge/skills/free-tool-strategy.md +636 -636
  137. package/knowledge/skills/frontend-design-offical.md +55 -55
  138. package/knowledge/skills/frontend-design.md +41 -41
  139. package/knowledge/skills/frontend-expert.md +93 -93
  140. package/knowledge/skills/github.md +12 -12
  141. package/knowledge/skills/gitlab.md +12 -12
  142. package/knowledge/skills/gopls-lsp.md +32 -32
  143. package/knowledge/skills/got-controller.md +218 -218
  144. package/knowledge/skills/greptile.md +72 -72
  145. package/knowledge/skills/hookify.md +376 -376
  146. package/knowledge/skills/image-editor.md +189 -189
  147. package/knowledge/skills/image-enhancer.md +109 -109
  148. package/knowledge/skills/jdtls-lsp.md +49 -49
  149. package/knowledge/skills/json-canvas.md +654 -654
  150. package/knowledge/skills/keyword-research.md +559 -559
  151. package/knowledge/skills/kotlin-lsp.md +28 -28
  152. package/knowledge/skills/laravel-boost.md +12 -12
  153. package/knowledge/skills/launch-strategy.md +394 -394
  154. package/knowledge/skills/lead-magnet.md +393 -393
  155. package/knowledge/skills/learning-output-style.md +106 -106
  156. package/knowledge/skills/linear.md +12 -12
  157. package/knowledge/skills/lua-lsp.md +47 -47
  158. package/knowledge/skills/marketing-ideas.md +720 -720
  159. package/knowledge/skills/marketing-psychology.md +534 -534
  160. package/knowledge/skills/mcp-builder.md +369 -369
  161. package/knowledge/skills/meeting-insights-analyzer.md +347 -347
  162. package/knowledge/skills/memory-evolution-system.md +172 -172
  163. package/knowledge/skills/multi-lens-thinking.md +407 -407
  164. package/knowledge/skills/nano-banana-pro.md +116 -116
  165. package/knowledge/skills/newsletter.md +736 -736
  166. package/knowledge/skills/notebooklm.md +296 -296
  167. package/knowledge/skills/obsidian-bases.md +634 -634
  168. package/knowledge/skills/obsidian-markdown.md +651 -651
  169. package/knowledge/skills/onboarding-cro.md +494 -494
  170. package/knowledge/skills/orchestrator.md +681 -681
  171. package/knowledge/skills/page-cro.md +379 -379
  172. package/knowledge/skills/paid-ads.md +624 -624
  173. package/knowledge/skills/paywall-upgrade-cro.md +651 -651
  174. package/knowledge/skills/php-lsp.md +36 -36
  175. package/knowledge/skills/planning-with-files.md +193 -193
  176. package/knowledge/skills/playwright.md +12 -12
  177. package/knowledge/skills/plugin-dev.md +434 -434
  178. package/knowledge/skills/popup-cro.md +520 -520
  179. package/knowledge/skills/positioning-angles.md +330 -330
  180. package/knowledge/skills/pr-review-toolkit.md +359 -359
  181. package/knowledge/skills/pricing-strategy.md +777 -777
  182. package/knowledge/skills/programmatic-seo.md +714 -714
  183. package/knowledge/skills/pyright-lsp.md +43 -43
  184. package/knowledge/skills/quality-assurance-framework.md +168 -168
  185. package/knowledge/skills/question-refiner.md +160 -160
  186. package/knowledge/skills/ralph-loop.md +205 -205
  187. package/knowledge/skills/refactoring-expert.md +103 -103
  188. package/knowledge/skills/referral-program.md +668 -668
  189. package/knowledge/skills/research-executor.md +164 -164
  190. package/knowledge/skills/review-with-security.md +12 -12
  191. package/knowledge/skills/rust-analyzer-lsp.md +50 -50
  192. package/knowledge/skills/schema-markup.md +647 -647
  193. package/knowledge/skills/security-audit-expert.md +124 -124
  194. package/knowledge/skills/security-expert.md +140 -140
  195. package/knowledge/skills/security-guidance.md +12 -12
  196. package/knowledge/skills/seedance-prompt.md +139 -139
  197. package/knowledge/skills/self-evolution.md +1160 -1160
  198. package/knowledge/skills/seo-audit.md +432 -432
  199. package/knowledge/skills/seo-content.md +787 -787
  200. package/knowledge/skills/serena.md +12 -12
  201. package/knowledge/skills/signup-flow-cro.md +409 -409
  202. package/knowledge/skills/skill-creator.md +220 -220
  203. package/knowledge/skills/skill-manager.md +226 -226
  204. package/knowledge/skills/skill-share.md +98 -98
  205. package/knowledge/skills/slack.md +12 -12
  206. package/knowledge/skills/social-content.md +878 -878
  207. package/knowledge/skills/spec-flow-skill.md +124 -124
  208. package/knowledge/skills/stripe.md +12 -12
  209. package/knowledge/skills/supabase.md +12 -12
  210. package/knowledge/skills/swift-lsp.md +40 -40
  211. package/knowledge/skills/synthesizer.md +236 -236
  212. package/knowledge/skills/template-skill.md +16 -16
  213. package/knowledge/skills/testing-expert.md +99 -99
  214. package/knowledge/skills/theme-factory.md +72 -72
  215. package/knowledge/skills/tiktok-research.md +208 -208
  216. package/knowledge/skills/typescript-lsp.md +36 -36
  217. package/knowledge/skills/ui-ux-pro-max.md +247 -247
  218. package/knowledge/skills/verify.md +15 -15
  219. package/knowledge/skills/visual-prompt-engineer.md +102 -102
  220. package/knowledge/skills/webapp-testing.md +111 -111
  221. package/knowledge/skills/wide-research.md +191 -191
  222. package/knowledge/system.md +93 -93
  223. package/knowledge/task-router.md +46 -37
  224. package/knowledge/verification.md +38 -38
  225. package/knowledge/worker-prompt-craft.md +66 -0
  226. package/knowledge/workflows/3d-viz.md +47 -47
  227. package/knowledge/workflows/data-pipeline.md +47 -47
  228. package/knowledge/workflows/db-migration.md +51 -51
  229. package/knowledge/workflows/feature-dev.md +41 -41
  230. package/knowledge/workflows/tdd-flow.md +52 -52
  231. package/knowledge/workflows/ui-verify.md +51 -51
  232. package/package.json +74 -74
  233. package/dist/claude-bridge.d.ts +0 -18
  234. package/dist/claude-bridge.js +0 -91
  235. package/dist/claude-bridge.js.map +0 -1
  236. package/dist/tools/claude-bridge-tool.d.ts +0 -4
  237. package/dist/tools/claude-bridge-tool.js +0 -44
  238. package/dist/tools/claude-bridge-tool.js.map +0 -1
@@ -1,179 +1,179 @@
1
- ---
2
- id: "cache-optimization-skill"
3
- title: "Cache Optimization Skill"
4
- category: "agent-engineering"
5
- tags: ["cache optimization skill", "what the patches do", "installation status", "installed location", "patched cli", "usage", "cache health monitoring", "optimization strategy matrix", "troubleshooting", "restore from backup"]
6
- triggers: []
7
- dependencies: []
8
- source: "E:/Bobo's Coding cache/.claude/skills/cache-optimization-skill"
9
- ---
10
-
11
- ---
12
- name: cache-optimization-skill
13
- description: Token cache optimization based on cc-cache-fix. Auto-applies 3 patches (attachment persistence, hash stability, 1h TTL) and monitors cache health. Use when starting sessions, resuming conversations, or auditing token usage.
14
- ---
15
-
16
- # Cache Optimization Skill
17
-
18
- > **Source**: cc-cache-fix by Rangizingo
19
- > **Effect**: ~60-70% token savings via 3 targeted patches
20
- > **Status**: Installed as `claude-patched` (v2.1.81)
21
-
22
- ## What The Patches Do
23
-
24
- ### Patch 1: Attachment Persistence (db8 filter)
25
- **Problem**: Claude Code drops `deferred_tools_delta` and `mcp_instructions_delta` attachments on save, breaking cache on resume.
26
-
27
- **Fix**: Allow these attachment types through the filter:
28
- ```javascript
29
- // Before: only hook_additional_context passes
30
- if(A.attachment.type==="hook_additional_context") return!0;
31
- return!1;
32
-
33
- // After: also allow delta types
34
- if(A.attachment.type==="deferred_tools_delta") return!0;
35
- if(A.attachment.type==="mcp_instructions_delta") return!0;
36
- return!1;
37
- ```
38
-
39
- **Effect**: +30% cache hit rate on session resume.
40
-
41
- ### Patch 1b: Fingerprint Meta Skip
42
- **Problem**: First user message (including meta/system messages) is used for cache fingerprinting, causing different fingerprints for identical content.
43
-
44
- **Fix**: Skip meta user messages in fingerprint selector:
45
- ```javascript
46
- // Before: finds first user message regardless of meta status
47
- let q = A.find((_) => _.type === "user");
48
-
49
- // After: skip meta messages
50
- let q = A.find((_) => _.type === "user" && !("isMeta" in _ && _.isMeta));
51
- ```
52
-
53
- **Effect**: More stable cache keys across turns.
54
-
55
- ### Patch 2: Force 1-Hour Cache TTL
56
- **Problem**: Default 5-minute TTL is too short for most tasks. The `sjY()` function checks subscription/feature flags to gate 1h TTL.
57
-
58
- **Fix**: Bypass the check entirely:
59
- ```javascript
60
- // Before: conditional TTL based on plan
61
- function sjY(A) { if(QA()==="bedrock" ... }
62
-
63
- // After: always allow 1h TTL
64
- function sjY(A) { return!0; if(QA()==="bedrock" ... }
65
- ```
66
-
67
- **Effect**: Cache lives 12x longer, reducing recomputation.
68
-
69
- ---
70
-
71
- ## Installation Status
72
-
73
- ```bash
74
- # Installed location
75
- E:/Bobo's Coding cache/cc-cache-fix/
76
-
77
- # Patched CLI
78
- claude-patched.cmd → node cli.js (patched v2.1.81)
79
-
80
- # Usage
81
- claude-patched # Start patched Claude Code
82
- claude-patched --version # Verify: "2.1.81 (Claude Code)"
83
- ```
84
-
85
- ## Cache Health Monitoring
86
-
87
- ### Quick Check
88
- ```bash
89
- cd "E:/Bobo's Coding cache/cc-cache-fix"
90
- python test_cache.py
91
- ```
92
-
93
- ### Usage Audit
94
- ```bash
95
- python usage_audit.py
96
- ```
97
-
98
- ### Health Thresholds
99
-
100
- | Metric | Green | Yellow | Red |
101
- |--------|-------|--------|-----|
102
- | Cache hit rate | >70% | 50-70% | <50% |
103
- | Token efficiency | >65% | 45-65% | <45% |
104
- | TTL utilization | >80% | 60-80% | <60% |
105
-
106
- ---
107
-
108
- ## Optimization Strategy Matrix
109
-
110
- ### With cc-cache-fix (default)
111
- ```
112
- Strategy: Trust the cache, minimize re-reads
113
- - Read files once, trust they'll be cached
114
- - Resume sessions confidently (delta attachments preserved)
115
- - Work in longer sessions (1h TTL)
116
- ```
117
-
118
- ### Without cc-cache-fix (fallback)
119
- ```
120
- Strategy: Minimize context, split sessions
121
- - Use Grep instead of full file reads
122
- - Split long tasks into 15-20 min sessions
123
- - Compress context before it exceeds 70%
124
- ```
125
-
126
- ---
127
-
128
- ## Combined with Other Optimizations
129
-
130
- | Optimization | Token Savings | Requires |
131
- |-------------|---------------|----------|
132
- | **cc-cache-fix** | 60-70% | `claude-patched` |
133
- | **Context compression** | 90-95% of context size | Manual trigger |
134
- | **Session splitting** | 30-40% for long tasks | Task planning |
135
- | **Cache warmup** | 30% on first operation | Session start |
136
- | **Total combined** | ~80% overall | All above |
137
-
138
- ---
139
-
140
- ## Troubleshooting
141
-
142
- ### Patch Not Applied
143
- ```bash
144
- cd "E:/Bobo's Coding cache/cc-cache-fix"
145
- # Restore from backup
146
- cp node/node_modules/@anthropic-ai/claude-code/cli.js.orig node/node_modules/@anthropic-ai/claude-code/cli.js
147
- # Re-apply
148
- python patches/apply-patches.py node/node_modules/@anthropic-ai/claude-code/cli.js
149
- ```
150
-
151
- ### Version Mismatch After Claude Code Update
152
- ```bash
153
- # The patch targets specific function names (db8, sjY, FA9)
154
- # If these change in a new version, the patch will fail gracefully
155
- # Check: python patches/apply-patches.py --dry-run <path-to-new-cli.js>
156
- ```
157
-
158
- ### Revert to Stock
159
- ```bash
160
- # Simply use 'claude' instead of 'claude-patched'
161
- claude # Unpatched version
162
- ```
163
-
164
- ---
165
-
166
- ## Maintenance
167
-
168
- ### Weekly
169
- - Run `usage_audit.py` to track cache efficiency trends
170
- - Check for cc-cache-fix updates: `cd cc-cache-fix && git pull`
171
-
172
- ### Monthly
173
- - Verify patch status: `python test_cache.py`
174
- - Re-run installer if Claude Code updated: `powershell -File install-windows.ps1`
175
-
176
- ### On Claude Code Major Update
177
- - Check if patches still apply
178
- - Wait for cc-cache-fix update if function names changed
179
- - Fall back to `claude` (stock) if patches fail
1
+ ---
2
+ id: "cache-optimization-skill"
3
+ title: "Cache Optimization Skill"
4
+ category: "agent-engineering"
5
+ tags: ["cache optimization skill", "what the patches do", "installation status", "installed location", "patched cli", "usage", "cache health monitoring", "optimization strategy matrix", "troubleshooting", "restore from backup"]
6
+ triggers: []
7
+ dependencies: []
8
+ source: "E:/Bobo's Coding cache/.claude/skills/cache-optimization-skill"
9
+ ---
10
+
11
+ ---
12
+ name: cache-optimization-skill
13
+ description: Token cache optimization based on cc-cache-fix. Auto-applies 3 patches (attachment persistence, hash stability, 1h TTL) and monitors cache health. Use when starting sessions, resuming conversations, or auditing token usage.
14
+ ---
15
+
16
+ # Cache Optimization Skill
17
+
18
+ > **Source**: cc-cache-fix by Rangizingo
19
+ > **Effect**: ~60-70% token savings via 3 targeted patches
20
+ > **Status**: Installed as `claude-patched` (v2.1.81)
21
+
22
+ ## What The Patches Do
23
+
24
+ ### Patch 1: Attachment Persistence (db8 filter)
25
+ **Problem**: Claude Code drops `deferred_tools_delta` and `mcp_instructions_delta` attachments on save, breaking cache on resume.
26
+
27
+ **Fix**: Allow these attachment types through the filter:
28
+ ```javascript
29
+ // Before: only hook_additional_context passes
30
+ if(A.attachment.type==="hook_additional_context") return!0;
31
+ return!1;
32
+
33
+ // After: also allow delta types
34
+ if(A.attachment.type==="deferred_tools_delta") return!0;
35
+ if(A.attachment.type==="mcp_instructions_delta") return!0;
36
+ return!1;
37
+ ```
38
+
39
+ **Effect**: +30% cache hit rate on session resume.
40
+
41
+ ### Patch 1b: Fingerprint Meta Skip
42
+ **Problem**: First user message (including meta/system messages) is used for cache fingerprinting, causing different fingerprints for identical content.
43
+
44
+ **Fix**: Skip meta user messages in fingerprint selector:
45
+ ```javascript
46
+ // Before: finds first user message regardless of meta status
47
+ let q = A.find((_) => _.type === "user");
48
+
49
+ // After: skip meta messages
50
+ let q = A.find((_) => _.type === "user" && !("isMeta" in _ && _.isMeta));
51
+ ```
52
+
53
+ **Effect**: More stable cache keys across turns.
54
+
55
+ ### Patch 2: Force 1-Hour Cache TTL
56
+ **Problem**: Default 5-minute TTL is too short for most tasks. The `sjY()` function checks subscription/feature flags to gate 1h TTL.
57
+
58
+ **Fix**: Bypass the check entirely:
59
+ ```javascript
60
+ // Before: conditional TTL based on plan
61
+ function sjY(A) { if(QA()==="bedrock" ... }
62
+
63
+ // After: always allow 1h TTL
64
+ function sjY(A) { return!0; if(QA()==="bedrock" ... }
65
+ ```
66
+
67
+ **Effect**: Cache lives 12x longer, reducing recomputation.
68
+
69
+ ---
70
+
71
+ ## Installation Status
72
+
73
+ ```bash
74
+ # Installed location
75
+ E:/Bobo's Coding cache/cc-cache-fix/
76
+
77
+ # Patched CLI
78
+ claude-patched.cmd → node cli.js (patched v2.1.81)
79
+
80
+ # Usage
81
+ claude-patched # Start patched Claude Code
82
+ claude-patched --version # Verify: "2.1.81 (Claude Code)"
83
+ ```
84
+
85
+ ## Cache Health Monitoring
86
+
87
+ ### Quick Check
88
+ ```bash
89
+ cd "E:/Bobo's Coding cache/cc-cache-fix"
90
+ python test_cache.py
91
+ ```
92
+
93
+ ### Usage Audit
94
+ ```bash
95
+ python usage_audit.py
96
+ ```
97
+
98
+ ### Health Thresholds
99
+
100
+ | Metric | Green | Yellow | Red |
101
+ |--------|-------|--------|-----|
102
+ | Cache hit rate | >70% | 50-70% | <50% |
103
+ | Token efficiency | >65% | 45-65% | <45% |
104
+ | TTL utilization | >80% | 60-80% | <60% |
105
+
106
+ ---
107
+
108
+ ## Optimization Strategy Matrix
109
+
110
+ ### With cc-cache-fix (default)
111
+ ```
112
+ Strategy: Trust the cache, minimize re-reads
113
+ - Read files once, trust they'll be cached
114
+ - Resume sessions confidently (delta attachments preserved)
115
+ - Work in longer sessions (1h TTL)
116
+ ```
117
+
118
+ ### Without cc-cache-fix (fallback)
119
+ ```
120
+ Strategy: Minimize context, split sessions
121
+ - Use Grep instead of full file reads
122
+ - Split long tasks into 15-20 min sessions
123
+ - Compress context before it exceeds 70%
124
+ ```
125
+
126
+ ---
127
+
128
+ ## Combined with Other Optimizations
129
+
130
+ | Optimization | Token Savings | Requires |
131
+ |-------------|---------------|----------|
132
+ | **cc-cache-fix** | 60-70% | `claude-patched` |
133
+ | **Context compression** | 90-95% of context size | Manual trigger |
134
+ | **Session splitting** | 30-40% for long tasks | Task planning |
135
+ | **Cache warmup** | 30% on first operation | Session start |
136
+ | **Total combined** | ~80% overall | All above |
137
+
138
+ ---
139
+
140
+ ## Troubleshooting
141
+
142
+ ### Patch Not Applied
143
+ ```bash
144
+ cd "E:/Bobo's Coding cache/cc-cache-fix"
145
+ # Restore from backup
146
+ cp node/node_modules/@anthropic-ai/claude-code/cli.js.orig node/node_modules/@anthropic-ai/claude-code/cli.js
147
+ # Re-apply
148
+ python patches/apply-patches.py node/node_modules/@anthropic-ai/claude-code/cli.js
149
+ ```
150
+
151
+ ### Version Mismatch After Claude Code Update
152
+ ```bash
153
+ # The patch targets specific function names (db8, sjY, FA9)
154
+ # If these change in a new version, the patch will fail gracefully
155
+ # Check: python patches/apply-patches.py --dry-run <path-to-new-cli.js>
156
+ ```
157
+
158
+ ### Revert to Stock
159
+ ```bash
160
+ # Simply use 'claude' instead of 'claude-patched'
161
+ claude # Unpatched version
162
+ ```
163
+
164
+ ---
165
+
166
+ ## Maintenance
167
+
168
+ ### Weekly
169
+ - Run `usage_audit.py` to track cache efficiency trends
170
+ - Check for cc-cache-fix updates: `cd cc-cache-fix && git pull`
171
+
172
+ ### Monthly
173
+ - Verify patch status: `python test_cache.py`
174
+ - Re-run installer if Claude Code updated: `powershell -File install-windows.ps1`
175
+
176
+ ### On Claude Code Major Update
177
+ - Check if patches still apply
178
+ - Wait for cc-cache-fix update if function names changed
179
+ - Fall back to `claude` (stock) if patches fail