hyntx 2.6.0 → 2.7.0

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 (2) hide show
  1. package/README.md +25 -7
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -119,6 +119,15 @@ hyntx --from 2025-01-15 --to 2025-01-22 --project backend-api
119
119
 
120
120
  # Generate markdown report for yesterday
121
121
  hyntx --date yesterday --output yesterday-analysis.md
122
+
123
+ # Deep analysis with individual mode for critical project
124
+ hyntx -m individual --project production-api --date today
125
+
126
+ # Fast batch analysis across date range
127
+ hyntx --from 2025-01-15 --to 2025-01-20 --analysis-mode batch -o report.md
128
+
129
+ # Watch mode with individual analysis (slower but detailed)
130
+ hyntx --watch -m individual --project critical-app
122
131
  ```
123
132
 
124
133
  ## Configuration
@@ -151,16 +160,25 @@ hyntx --analysis-mode individual # Use individual mode
151
160
  hyntx -m individual # Short form
152
161
  ```
153
162
 
154
- #### Mode Comparison
163
+ #### Quick Mode Comparison
164
+
165
+ | Mode | Speed/Prompt | Use Case | Accuracy | When to Use |
166
+ | ---------- | ------------ | -------------------------- | -------- | ----------------------------------------- |
167
+ | Batch | ~300-400ms | Daily analysis, monitoring | Good | Quick feedback, large datasets |
168
+ | Individual | ~1-1.5s | Deep analysis, learning | Better | Quality-focused reviews, critical prompts |
169
+
170
+ **Speedup**: Batch mode is 3-4x faster than individual mode.
171
+
172
+ **Recommendation**: Use batch mode (default) for daily analysis to get fast feedback. Switch to individual mode when:
155
173
 
156
- | Mode | Speed/Prompt | Use Case | Accuracy |
157
- | ---------- | ------------ | -------------- | -------- |
158
- | Batch | ~300-400ms | Daily analysis | Good |
159
- | Individual | ~1-1.5s | Deep analysis | Better |
174
+ - You need detailed, nuanced feedback on each prompt
175
+ - You're learning prompt engineering patterns
176
+ - Analyzing high-stakes or complex prompts
177
+ - Conducting quality audits or teaching sessions
160
178
 
161
- **Recommendation**: Use batch mode for daily analysis (faster feedback), switch to individual mode when you need maximum quality or are learning prompt engineering techniques.
179
+ **Performance Note**: Numbers based on `llama3.2` on CPU. Actual speed varies by hardware, model size, and prompt complexity.
162
180
 
163
- **Note**: Performance numbers are based on `llama3.2` running on CPU. Actual speed depends on your hardware and model choice.
181
+ **Detailed Guide**: See [Analysis Modes Documentation](./docs/ANALYSIS_MODES.md) for comprehensive comparison, examples, and decision guidelines.
164
182
 
165
183
  ### Rules Configuration
166
184
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "hyntx",
3
- "version": "2.6.0",
3
+ "version": "2.7.0",
4
4
  "description": "CLI that analyzes Claude Code prompts and generates improvement suggestions",
5
5
  "type": "module",
6
6
  "packageManager": "pnpm@9.15.4",