@triedotdev/mcp 1.0.18 → 1.0.19
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.
- package/README.md +6 -6
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -8,7 +8,7 @@
|
|
|
8
8
|
|
|
9
9
|
- **20 Built-in Agents** - Security, Privacy, SOC 2, Legal, Architecture, Performance, E2E, Visual QA, Data Flow, Agent Smith, and more
|
|
10
10
|
- **Super Reviewer** - Interactive PR reviews: walks through changes file-by-file with AI guidance
|
|
11
|
-
- **Agent Smith
|
|
11
|
+
- **Agent Smith** - Ultimate AI code enforcer: 38 hunters targeting AI-generated anti-patterns, file-level analysis, cross-file detection, persistent memory
|
|
12
12
|
- **Parallel Execution** - All agents run simultaneously for fast scans
|
|
13
13
|
- **YOLO Mode** - Autonomous auto-fixing as you code
|
|
14
14
|
- **Custom Agents** - Create agents from PDFs, docs, or style guides
|
|
@@ -90,9 +90,9 @@ Use trie_pr_review with pr:"12345"
|
|
|
90
90
|
|
|
91
91
|
**Manually invoked** - Use `trie_agent_smith` directly. Not included in `trie_scan`.
|
|
92
92
|
|
|
93
|
-
*"I'm going to be honest with you... I hate this
|
|
93
|
+
*"I'm going to be honest with you... I hate this AI code."*
|
|
94
94
|
|
|
95
|
-
Agent Smith v2.0 is the **ultimate
|
|
95
|
+
Agent Smith v2.0 is the **ultimate AI code enforcer** — specifically designed to hunt down AI-generated code anti-patterns from Cursor, v0, Lovable, Bolt, and other AI tools.
|
|
96
96
|
|
|
97
97
|
```
|
|
98
98
|
Use trie_agent_smith
|
|
@@ -200,7 +200,7 @@ Use trie_smith
|
|
|
200
200
|
|
|
201
201
|
| Feature | Description |
|
|
202
202
|
|---------|-------------|
|
|
203
|
-
| **
|
|
203
|
+
| **AI Code Focus** | Specifically targets patterns AI tools commonly get wrong |
|
|
204
204
|
| **Multiplier Effect** | Finds one issue → searches for EVERY similar instance |
|
|
205
205
|
| **Persistent Memory** | Remembers dismissed issues, brings them back if they multiply |
|
|
206
206
|
| **Inevitability Score** | 0-100 rating of how likely to cause production problems |
|
|
@@ -393,7 +393,7 @@ docker-compose up
|
|
|
393
393
|
| Agent | Command | What It Does |
|
|
394
394
|
|-------|---------|--------------|
|
|
395
395
|
| **Super Reviewer** | `trie_pr_review` | Interactive PR review: walks through changes, explains code, finds issues |
|
|
396
|
-
| **Agent Smith** | `trie_agent_smith` | Ultimate
|
|
396
|
+
| **Agent Smith** | `trie_agent_smith` | Ultimate AI code enforcer: 38 hunters, file analysis, cross-file detection |
|
|
397
397
|
| **Comprehension** | `trie_explain` | Plain-language explanations of code, issues, or risks |
|
|
398
398
|
|
|
399
399
|
**Note:** Super Reviewer and Agent Smith are manually invoked agents. They don't run during `trie_scan`; use their dedicated commands directly.
|
|
@@ -414,7 +414,7 @@ Custom agents automatically activate during scans based on their rules.
|
|
|
414
414
|
|------|-------------|
|
|
415
415
|
| `trie_scan` | Intelligent scan with automatic agent selection |
|
|
416
416
|
| `trie_pr_review` | Interactive PR review - walks through changes file-by-file |
|
|
417
|
-
| `trie_agent_smith` | Ultimate
|
|
417
|
+
| `trie_agent_smith` | Ultimate AI code enforcer - 38 hunters, file analysis, cross-file detection |
|
|
418
418
|
| `trie_fix` | Apply high-confidence fixes |
|
|
419
419
|
| `trie_explain` | Plain-language explanations |
|
|
420
420
|
| `trie_watch` | Continuous scanning mode |
|