@triedotdev/mcp 1.0.10 → 1.0.12

package/README.md

@@ -2,12 +2,13 @@
 
 **Customizable Parallel Agents for AI Code Review**
 
-15 specialized agents scan your code for security, privacy, compliance, and bugs—all running in parallel. Create custom agents from any document.
+17 specialized agents scan your code for security, privacy, compliance, and bugs—all running in parallel. Create custom agents from any document.
 
 ## Features
 
-- **15 Built-in Agents** - Security, Privacy, SOC 2, Legal, Architecture, Design Engineer, and more
+- **17 Built-in Agents** - Security, Privacy, SOC 2, Legal, Architecture, Design Engineer, Agent Smith, and more
 - **🔍 Super Reviewer** - Interactive PR reviews: walks through changes file-by-file with AI guidance
+- **🕴️ Agent Smith** - Relentless pattern hunter: finds EVERY violation, tracks dismissed issues, spawns sub-agents
 - **Parallel Execution** - All agents run simultaneously for fast scans
 - **🔥 YOLO Mode** - Autonomous auto-fixing as you code
 - **Custom Agents** - Create agents from PDFs, docs, or style guides
@@ -62,6 +63,7 @@ Run trie_soc2 to check compliance
 ```
 
 ## Super Reviewer 🔍
+> ⭐ **Manually invoked** — Use `trie_pr_review` directly. Not included in `trie_scan`.
 
 AI accelerates coding 10-100x, but code reviews remain 1-1.5x. You're either waiting on reviewers or drowning in self-review of your own AI-generated output. Super Reviewer fixes this by making **you the driver** while AI handles the heavy lifting.
 
@@ -83,6 +85,55 @@ Use trie_pr_review with pr:"12345"
 - Git repository with changes to review
 - For PR reviews: repo must be pushed to GitHub
 
+## Agent Smith 🕴️
+> ⭐ **Manually invoked** — Use `trie_agent_smith` directly. Not included in `trie_scan`.
+
+*"I'm going to be honest with you... I hate this code."*
+
+Agent Smith is the relentless, self-replicating code enforcer. He hunts down violations with machine precision, remembers issues you dismissed, and spawns sub-agents to overwhelm problems.
+
+```
+Use trie_agent_smith
+Use trie_smith
+```
+
+**What makes him different:**
+- **Multiplier Effect**: Finds one issue → searches for EVERY similar instance across the entire codebase
+- **Persistent Memory**: Remembers dismissed issues. If they multiply, he brings them back: *"Did you really think you could escape?"*
+- **Sub-Agent Swarm**: Deploys specialized hunters in parallel (console-hunter, any-hunter, todo-hunter, var-hunter, empty-catch-hunter, magic-number-hunter)
+- **Inevitability Score**: Calculates how likely each pattern is to cause production issues (0-100)
+- **Philosophical Analysis**: Explains WHY the code is wrong, not just that it's wrong
+
+**Memory Management:**
+
+Agent Smith stores issue history in `.trie/smith-memory.json`. The memory is automatically optimized:
+- Max 500 tracked issues (oldest pruned first)
+- Old resolved issues auto-pruned after 30 days
+- Locations limited to 5 per issue
+
+| Command | Description |
+|---------|-------------|
+| `trie_agent_smith show_stats:true` | Show memory statistics (issue count, file size) |
+| `trie_agent_smith clear_memory:true` | Clear all memory for a fresh start |
+
+**Example output:**
+```
+🕴️ AGENT SMITH ANALYSIS
+
+"Mr. Anderson... I've been expecting you."
+
+VIOLATIONS DETECTED: 47 instances across 6 categories
+
+┌─────────────────────────────────────────┐
+│ console-hunter: 23 instances (score: 65)│
+│ any-hunter: 12 instances (score: 72)    │
+│ todo-hunter: 8 instances (score: 58)    │
+│ empty-catch-hunter: 4 instances (85) ⚠️ │
+└─────────────────────────────────────────┘
+
+"You hear that? That is the sound of inevitability."
+```
+
 ## YOLO Mode 🔥
 
 **Autonomous auto-fixing** - Trie watches your code and automatically fixes high-confidence issues as you code.
@@ -174,9 +225,12 @@ docker-compose up
 
 | Agent | Command | What It Does |
 |-------|---------|--------------|
-| **Super Reviewer** | `trie_pr_review` | Interactive PR review: walks through changes, explains code, finds issues |
+| **Super Reviewer** ⭐ | `trie_pr_review` | Interactive PR review: walks through changes, explains code, finds issues |
+| **Agent Smith** ⭐ | `trie_agent_smith` | Relentless pattern hunter: finds EVERY instance, tracks dismissed issues, spawns sub-agents |
 | **Comprehension** | `trie_explain` | Plain-language explanations of code, issues, or risks |
 
+> ⭐ **Manually invoked agents** — Super Reviewer and Agent Smith are special-purpose agents designed for explicit invocation. They don't run during `trie_scan`; use their dedicated commands directly.
+
 ## Custom Agents
 
 Create specialized agents from any document:
@@ -193,6 +247,7 @@ Custom agents automatically activate during scans based on their rules.
 |------|-------------|
 | `trie_scan` | Intelligent scan with automatic agent selection |
 | `trie_pr_review` | Interactive PR review — walks through changes file-by-file |
+| `trie_agent_smith` | Relentless pattern hunter — finds EVERY violation, tracks history |
 | `trie_fix` | Apply high-confidence fixes |
 | `trie_explain` | Plain-language explanations |
 | `trie_watch` | Continuous scanning mode |

package/dist/agent-smith-LBQ5PNAK.js

@@ -0,0 +1,10 @@
+import {
+  AgentSmithAgent,
+  SUB_AGENT_PATTERNS
+} from "./chunk-4OGYWKMD.js";
+import "./chunk-DGUM43GV.js";
+export {
+  AgentSmithAgent,
+  SUB_AGENT_PATTERNS
+};
+//# sourceMappingURL=agent-smith-LBQ5PNAK.js.map

package/dist/agent-smith-LBQ5PNAK.js.map

@@ -0,0 +1 @@
+{"version":3,"sources":[],"sourcesContent":[],"mappings":"","names":[]}