minovative-mind-cli 1.3.0 → 1.3.1

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 (3) hide show
  1. package/README.md +28 -21
  2. package/oclif.manifest.json +1 -1
  3. package/package.json +1 -1
package/README.md CHANGED
@@ -2,13 +2,15 @@
2
2
 
3
3
  ## The CLI agent that makes Flash models perform like Pro.
4
4
 
5
- ### The result: **Genuine Pro-level accuracy at Flash-level cost.**
6
-
7
5
  Most AI coding tools throw your entire codebase at the biggest model available
8
- and hope for the best. This CLI does the opposite — it uses a custom built
6
+ and hope for the best.
7
+
8
+ This CLI does the opposite — it uses a custom built agentic system called,
9
9
  **Precision-Context Verification (PCV)** engine to feed lightweight Flash models
10
- exactly the right context, verify the output compiles, and self-correct, if it even needs to, until
11
- the build is green.
10
+ exactly the right context, execute code, verify the output compiles, and self-correct (if it even needs to), until
11
+ the build/performance metrics are green.
12
+
13
+ > The result: **Genuine Pro-level accuracy at Flash-level cost.**
12
14
 
13
15
  [![oclif](https://img.shields.io/badge/cli-oclif-brightgreen.svg)](https://oclif.io)
14
16
  [![Version](https://img.shields.io/npm/v/minovative-mind-cli.svg)](https://npmjs.org/package/minovative-mind-cli)
@@ -18,26 +20,25 @@ the build is green.
18
20
 
19
21
  ## How it works
20
22
 
21
- Standard AI coding agents: big model + noisy context = expensive and redundant mistakes
23
+ - Standard AI coding agents: big model + noisy context = expensive and redundant mistakes
24
+ - Minovative Mind CLI: flash models + precise context + verified output = better and cheaper results.
22
25
 
23
- Minovative Mind CLI: flash models + precise context + verified output = better results.
24
-
25
- The PCV engine runs in three stages before returning a single line of code:
26
+ ### The PCV engine runs in three stages before returning a single line of code:
26
27
 
27
28
  **1. Investigate**
28
- A dedicated Context Agent reads your project structure, traces import
29
- dependencies, detects recently modified files, and searches the web for
30
- external documentation — all before the coding agent touches anything.
29
+
30
+ - **Maps your project:** Traces import dependencies and identifies recently modified files to understand your focus.
31
+ - **Researches context:** Gathers external web documentation and completes background research before touching any code.
31
32
 
32
33
  **2. Execute with precision**
33
- Instead of dumping your entire codebase into a prompt, the engine feeds the
34
- coding agent a compressed, surgical snapshot of only what's relevant.
35
- 40–50% fewer broken generations on large files vs. standard zero-shot prompts.
34
+
35
+ - **Surgical snapshots:** Feeds the agent a compressed, relevant slice of code instead of dumping the entire codebase.
36
+ - **Higher success rates:** Delivers 40–50% fewer broken generations on large files compared to standard zero-shot prompts.
36
37
 
37
38
  **3. Verify and self-correct**
38
- After every change, it runs your actual build (`npm run build`, `cargo check`,
39
- `make`, etc.), reads the exact compiler output, and autonomously fixes errors —
40
- up to 3 correction cycles without you typing a word.
39
+
40
+ - **Runs native builds & audits:** Automatically executes your actual build commands (`npm run build`, `cargo check`, etc.) and scans for performance flaws on modified files only.
41
+ - **Autonomously debugs:** Reads the exact compiler output and fixes its own errors across up to 3 hands-free correction cycles.
41
42
 
42
43
  ---
43
44
 
@@ -54,6 +55,12 @@ up to 3 correction cycles without you typing a word.
54
55
  npm install -g minovative-mind-cli
55
56
  ```
56
57
 
58
+ ### Update to latest version
59
+
60
+ ```bash
61
+ npm update -g minovative-mind-cli
62
+ ```
63
+
57
64
  Create a free account at [minovativemind.dev](https://www.minovativemind.dev),
58
65
  then:
59
66
 
@@ -77,9 +84,9 @@ Hot-swap during a session with `/models`:
77
84
  | **Gemini 3.1 Pro** | Complex architectural changes |
78
85
  | **Gemini 3.1 Flash Lite** | Maximum speed and cost efficiency |
79
86
 
80
- > Intent routing, context compression, and commit generation always run on
81
- > lightweight models automatically — you only pay Pro rates when you
82
- > explicitly ask for it.
87
+ > Background tasks (routing, compression, commits) always use lightweight
88
+ > models automatically. You only pay for what your selected model costs
89
+ > during chat and code execution. Use `/debug` to see exactly what's running.
83
90
 
84
91
  ---
85
92
 
package/oclif.manifest.json CHANGED
@@ -65,5 +65,5 @@
65
65
  ]
66
66
  }
67
67
  },
68
- "version": "1.3.0"
68
+ "version": "1.3.1"
69
69
  }
package/package.json CHANGED
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "name": "minovative-mind-cli",
3
3
  "description": "An automated AI agent powered by Vertex AI that helps you write software",
4
- "version": "1.3.0",
4
+ "version": "1.3.1",
5
5
  "author": "Daniel Ward",
6
6
  "bin": {
7
7
  "minovative-mind-cli": "./bin/run.js"