@triedotdev/mcp 1.0.79 → 1.0.81

package/README.md

@@ -1,4 +1,4 @@
-# Trie: Trainable AI Agent for Maintaining AI-generated Codebases
+# Trie: Trainable AI Agent for Maintaining AI-Generated Codebases
 
 **A trainable AI agent that watches all of your codebases, learns from your incidents, and prevents repeat bugs before they ship.**
 
@@ -6,10 +6,11 @@
 
 ## What Trie Does
 
-- **Central skill repository**: One place for all your skills — carry context and rules across Cursor, Claude, VS Code, CLI, and CI/CD
+- **Central skill repository**: One place for all your skills — carry context and rules across Cursor, Claude, VS Code, CLI, and CI/CD. Unlike running skills with Claude Code, Trie will check for anything malicious before you run them.
 - **Sets and tracks goals**: "Reduce login bugs by 50%" then actually measures progress and celebrates wins
 - **Tests your theories**: "Mondays have more bugs" — Trie validates with real data and builds confidence over time
 - **Learns from your incidents**: Train it on your specific patterns, not generic rules that don't fit your prompting
+- **Predicts "Gotchas" proactively**: Ingests Linear tickets and correlates them with past failures to warn you before you even push code
 
 ## Goal
 
@@ -49,15 +50,15 @@ trie status
 When bugs happen, tell Trie about them:
 
 ```bash
-# Report an incident
-trie tell "Users can't log in after the password reset"
+# Report a specific incident
+trie tell "Users can't log in after password reset"
 
-# Before pushing code
-trie check
+# Train Trie from your history (reverts/bugfixes)
+trie learn
 
-# Give feedback on warnings
-trie ok    # This warning was helpful
-trie bad   # This was a false alarm
+# Give feedback on patterns (staged files)
+trie ok    # Pattern is good
+trie bad   # Pattern is bad
 ```
 
 ## Why Trie Exists
@@ -172,6 +173,23 @@ trie watch
 
 Interactive panels for goals, memory, scout activity, and more.
 
+### JIT Defect Prediction ("Gotchas")
+Trie connects to your issue tracker and project history to predict problems *while you work*:
+
+```bash
+# 1. Connect Linear
+trie linear auth <your-api-key>
+trie linear sync
+
+# 2. Learn from history automatically
+trie learn
+
+# 3. Predict for current changes
+trie gotcha
+```
+
+Trie will warn you if your current task correlates with historical regressions or high-risk signatures.
+
 ### Integration with AI Coding Tools
 
 Trie provides MCP (Model Context Protocol) tools for seamless integration with Claude, Cursor, and other AI assistants:
@@ -237,17 +255,41 @@ trie init
 ```
 
 ### API Key Configuration
-For enhanced AI-powered analysis, set up your Anthropic API key:
+Trie works best with these keys:
+
+1. **ANTHROPIC_API_KEY**: Enables AI-powered analysis and explanations.
+2. **LINEAR_API_KEY**: Enables JIT defect prediction by syncing your active tickets.
+
+#### 1. Set via Environment (Recommended for MCP)
+Add these to your `.env` file or shell config:
 
 ```bash
-# Add to your .env file (recommended)
-echo "ANTHROPIC_API_KEY=your-api-key-here" >> .env
+export ANTHROPIC_API_KEY=sk-ant-...
+export LINEAR_API_KEY=lin_api_...
+```
 
-# Or set as environment variable
-export ANTHROPIC_API_KEY=your-api-key-here
+#### 2. Set via CLI (Persistent per project)
+```bash
+trie linear auth <your-key>
 ```
 
-**Note:** Trie works offline without an API key using built-in templates, but the AI-enhanced analysis provides much richer insights and explanations.
+#### 3. Set in MCP Config (Cursor/Claude Code)
+Add to your MCP server configuration:
+
+```json
+{
+  "mcpServers": {
+    "trie": {
+      "command": "npx",
+      "args": ["-y", "@triedotdev/mcp"],
+      "env": {
+        "ANTHROPIC_API_KEY": "your-key",
+        "LINEAR_API_KEY": "your-key"
+      }
+    }
+  }
+}
+```
 
 ### AI Tool Integration
 
@@ -260,7 +302,8 @@ Add to your MCP settings:
       "command": "trie",
       "args": ["mcp"],
       "env": {
-        "ANTHROPIC_API_KEY": "your-api-key-here"
+        "ANTHROPIC_API_KEY": "your-api-key-here",
+        "LINEAR_API_KEY": "your-key"
       }
     }
   }
@@ -279,8 +322,8 @@ Cursor has built-in MCP support. Add the above configuration to your Cursor MCP
 trie init          # Set up Trie in your project
 trie scan          # Analyze codebase with intelligent skill selection
 trie status        # View project health and memory stats
-trie check         # Quick risk check before pushing (< 500ms)
-trie tell "<msg>"  # Report an incident to build memory
+trie learn         # Train Trie from history or feedback
+trie gotcha        # Predict problems with current changes
 ```
 
 ### Memory Management
@@ -288,6 +331,7 @@ trie tell "<msg>"  # Report an incident to build memory
 trie memory search "auth"     # Search incident history
 trie memory stats             # View memory statistics
 trie memory purge smart       # Clean up old/resolved issues
+trie learn                    # Extract patterns from reverts/fixes
 ```
 
 ### Goals & Learning
@@ -295,12 +339,14 @@ trie memory purge smart       # Clean up old/resolved issues
 trie goal add "<goal>"           # Set improvement goal
 trie hypothesis add "<theory>"   # Test a hypothesis
 trie goal list                   # View progress
+trie linear sync                 # Sync Linear tickets for intent context
 ```
 
 ### Feedback & Training
 ```bash
-trie ok          # Last warning was helpful
-trie bad         # Last warning was wrong
+trie ok          # Pattern is good (alias: learn ok)
+trie bad         # Pattern is bad (alias: learn bad)
+trie learn       # Learn from your git history
 trie pause       # Disable warnings for 1 hour
 ```
 
@@ -390,6 +436,8 @@ trie memory purge resolved
 trie memory purge old --days=90
 ```
 
+**What happens at the 10,000 issue cap:** Trie will deduplicate new repeats, compact older issues into summaries, and if it still exceeds the cap it will prune the oldest/lowest-value issues (it does not “overwrite” in place).
+
 ## Custom Skills
 
 ### Adding External Skills
@@ -402,6 +450,29 @@ trie skill install anthropic/typescript-patterns
 trie skill install username/repo-name
 ```
 
+### Security & Safe Installation
+
+**Trie automatically scans all skills for security risks before installation.**
+
+When installing skills:
+- Skills are scanned for malicious patterns
+- Critical risks flagged with strong warnings
+- High risks flagged with warnings
+- **Shell commands Trie runs are logged** to `.trie/audit/` (e.g. skill install `git clone`, PR review `git/gh`, skill gating `which/where`, file picker helpers)
+
+```bash
+# View audit logs
+trie audit logs
+
+# View security info for installed skill
+trie skills info skill-name
+```
+
+**Best Practices:**
+- Only install from trusted sources (verified organizations)
+- Review security warnings and all .md carefully before using
+- Check audit logs periodically: `trie audit stats` (and investigate anything unexpected with `trie audit skill <name>`)
+
 ### Creating Your Own Skills
 ```bash
 # Create from documentation

package/dist/{agent-smith-XGYNJUCJ.js → agent-smith-MCKGNWPL.js}

@@ -1,8 +1,8 @@
 import {
   AgentSmithSkill,
   PATTERN_HUNTER_CONFIGS
-} from "./chunk-EWQF6INU.js";
-import "./chunk-Z7N7KDK3.js";
+} from "./chunk-TBRU735C.js";
+import "./chunk-DCJKNE2L.js";
 import "./chunk-CM7EHNQK.js";
 import "./chunk-MIL54SAF.js";
 import "./chunk-DGUM43GV.js";
@@ -11,4 +11,4 @@ export {
   AgentSmithSkill,
   PATTERN_HUNTER_CONFIGS
 };
-//# sourceMappingURL=agent-smith-XGYNJUCJ.js.map
+//# sourceMappingURL=agent-smith-MCKGNWPL.js.map

package/dist/{agent-smith-runner-QHYGVRNR.js → agent-smith-runner-GP5HLL7E.js}

@@ -1,11 +1,11 @@
 import {
   AgentSmithSkill
-} from "./chunk-EWQF6INU.js";
+} from "./chunk-TBRU735C.js";
 import {
   getAIStatusMessage,
   isAIAvailable,
   runAIAnalysis
-} from "./chunk-Z7N7KDK3.js";
+} from "./chunk-DCJKNE2L.js";
 import {
   getWorkingDirectory
 } from "./chunk-CM7EHNQK.js";
@@ -570,4 +570,4 @@ ${getAIStatusMessage()}`);
 export {
   runAgentSmith
 };
-//# sourceMappingURL=agent-smith-runner-QHYGVRNR.js.map
+//# sourceMappingURL=agent-smith-runner-GP5HLL7E.js.map