npm - cokit-cli - Versions diffs - 1.2.7 → 1.4.0 - Mend

cokit-cli 1.2.7 → 1.4.0

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 (1206) hide show

package/templates/repo/.github/skills/git/references/workflow-merge.md DELETED Viewed

@@ -1,48 +0,0 @@
-# Merge Workflow
-Execute via `git-manager` agent.
-## Variables
-- TO_BRANCH: target (defaults to `main`)
-- FROM_BRANCH: source (defaults to current branch)
-## Step 1: Sync with Remote
-**IMPORTANT: Always merge `main` (or any default branch) to current branch first.**
-```bash
-git fetch origin
-git checkout {TO_BRANCH}
-git pull origin {TO_BRANCH}
-```
-## Step 2: Merge from REMOTE
-```bash
-git merge origin/{FROM_BRANCH} --no-ff -m "merge: {FROM_BRANCH} into {TO_BRANCH}"
-```
-**Why `origin/{FROM_BRANCH}`:** Ensures merging only committed+pushed changes, not local WIP.
-## Step 3: Resolve Conflicts
-If conflicts:
-1. Resolve manually
-2. `git add . && git commit`
-3. If clarifications needed, report to main agent
-## Step 4: Push
-```bash
-git push origin {TO_BRANCH}
-```
-## Pre-Merge Checklist
-- Fetch latest: `git fetch origin`
-- Ensure FROM_BRANCH pushed to remote
-- Check for conflicts: `git merge --no-commit --no-ff origin/{FROM_BRANCH}` then abort
-## Error Handling
-| Error | Action |
-|-------|--------|
-| Merge conflicts | Resolve manually, then commit |
-| Branch not found | Verify branch name, ensure pushed |
-| Push rejected | `git pull --rebase`, retry |

package/templates/repo/.github/skills/git/references/workflow-pr.md DELETED Viewed

@@ -1,58 +0,0 @@
-# Pull Request Workflow
-Execute via `git-manager` agent.
-## Variables
-- TO_BRANCH: target (defaults to `main`)
-- FROM_BRANCH: source (defaults to current branch)
-## CRITICAL: Use REMOTE diff
-PRs based on remote branches. Local diff includes unpushed changes.
-## Tool 1: Sync + Analyze
-**IMPORTANT: Always merge `main` (or any default branch) to current branch first.**
-```bash
-git fetch origin && \
-git push -u origin HEAD 2>/dev/null || true && \
-BASE=${BASE_BRANCH:-main} && \
-HEAD=$(git rev-parse --abbrev-ref HEAD) && \
-echo "=== PR: $HEAD → $BASE ===" && \
-echo "=== COMMITS ===" && \
-git log origin/$BASE...origin/$HEAD --oneline && \
-echo "=== FILES ===" && \
-git diff origin/$BASE...origin/$HEAD --stat
-```
-**If "Branch not on remote":** Push first, retry.
-## Tool 2: Generate Content
-**Title:** Conventional commit format, <72 chars, NO version numbers
-**Body:** Summary bullets + Test plan checklist
-## Tool 3: Create PR
-```bash
-gh pr create --base $BASE --head $HEAD --title "..." --body "$(cat <<'EOF'
-## Summary
-- Bullet points
-## Test plan
-- [ ] Test item
-EOF
-)"
-```
-## DO NOT use (local comparison)
-- ❌ `git diff main...HEAD`
-- ❌ `git diff --cached`
-- ❌ `git status`
-## Error Handling
-| Error | Action |
-|-------|--------|
-| Branch not on remote | `git push -u origin HEAD`, retry |
-| Empty diff | Warn: "No changes for PR" |
-| Push rejected | `git pull --rebase`, resolve, push |
-| No upstream | `git push -u origin HEAD` |

package/templates/repo/.github/skills/git/references/workflow-push.md DELETED Viewed

@@ -1,52 +0,0 @@
-# Push Workflow
-Execute via `git-manager` agent.
-## Pre-Push Checklist
-1. All changes committed
-2. Secrets scanned (see `safety-protocols.md`)
-3. Branch pushed to remote
-## Tool 1: Verify State
-```bash
-git status && \
-git log origin/$(git rev-parse --abbrev-ref HEAD)..HEAD --oneline 2>/dev/null || echo "NO_UPSTREAM"
-```
-**If uncommitted changes:** Warn user, suggest commit first.
-**If NO_UPSTREAM:** Use `git push -u origin HEAD`.
-## Tool 2: Push
-```bash
-git push origin HEAD
-```
-**On success:** Report commit hashes pushed.
-## Error Handling
-| Error | Cause | Solution |
-|-------|-------|----------|
-| `rejected - non-fast-forward` | Remote has newer commits | `git pull --rebase`, resolve conflicts, push again |
-| `no upstream branch` | Branch not tracked | `git push -u origin HEAD` |
-| `Authentication failed` | Invalid credentials | Check `gh auth status` or SSH keys |
-| `Repository not found` | Wrong remote URL | Verify `git remote -v` |
-| `Permission denied` | No write access | Check repository permissions |
-## Force Push (DANGER)
-**NEVER force push to main/master/production branches.**
-If user explicitly requests force push on feature branch:
-```bash
-git push -f origin HEAD
-```
-**Warn user:** "Force push rewrites history. Collaborators may lose work."
-## Output Format
-```
-✓ pushed: N commits to origin/{branch}
-  - abc123 feat(auth): add login
-  - def456 fix(api): resolve timeout
-```

package/templates/repo/.github/skills/mcp-management/README.md DELETED Viewed

@@ -1,219 +0,0 @@
-# MCP Management Skill
-Intelligent management and execution of Model Context Protocol (MCP) servers.
-## Overview
-This skill enables the agent to discover, analyze, and execute MCP server capabilities without polluting the main context window. Perfect for context-efficient MCP integration using agent-based architecture.
-## Features
-- **Multi-Server Management**: Connect to multiple MCP servers from single config
-- **Intelligent Tool Discovery**: Analyze which tools are relevant for specific tasks
-- **Progressive Disclosure**: Load only necessary tool definitions
-- **Execution Engine**: Call MCP tools with proper parameter handling
-- **Context Efficiency**: Delegate MCP operations to `mcp-manager` agent
-## Quick Start
-### 1. Install Dependencies
-```bash
-cd $HOME/.copilot/skills/mcp-management/scripts
-npm install
-```
-### 2. Configure MCP Servers
-Create `$HOME/.copilot/.mcp.json`:
-```json
-{
-  "mcpServers": {
-    "memory": {
-      "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-memory"]
-    },
-    "filesystem": {
-      "command": "npx",
-      "args": ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"]
-    }
-  }
-}
-```
-See `$HOME/.copilot/.mcp.json.example` for more examples.
-### 3. Test Connection
-```bash
-cd $HOME/.copilot/skills/mcp-management/scripts
-npx ts-node cli.ts list-tools
-```
-## Usage Patterns
-### Pattern 1: Discover Available Tools
-```bash
-npx ts-node scripts/cli.ts list-tools
-npx ts-node scripts/cli.ts list-prompts
-npx ts-node scripts/cli.ts list-resources
-```
-### Pattern 2: LLM-Driven Tool Selection
-The LLM reads `assets/tools.json` and intelligently selects tools. No separate analysis command needed - the LLM's understanding of context and intent is superior to keyword matching.
-### Pattern 3: Execute MCP Tools
-```bash
-npx ts-node scripts/cli.ts call-tool memory add '{"key":"name","value":"Alice"}'
-```
-### Pattern 4: Use with Agent
-In main conversation:
-```
-User: "I need to search the web and save results"
-Main Agent: [Spawns mcp-manager agent]
-mcp-manager: Discovers brave-search + memory tools, reports back
-Main Agent: Uses recommended tools for implementation
-```
-## Architecture
-```
-Main Agent
-    ↓ (delegates MCP tasks)
-mcp-manager Agent
-    ↓ (uses skill)
-mcp-management Skill
-    ↓ (connects via)
-MCP Servers (memory, filesystem, etc.)
-```
-**Benefits**:
-- Main agent context stays clean
-- MCP discovery happens in isolated agent context
-- Only relevant tool definitions loaded when needed
-- Reduced token usage
-## File Structure
-```
-mcp-management/
-├── SKILL.md                    # Skill definition
-├── README.md                   # This file
-├── scripts/
-│   ├── mcp-client.ts          # Core MCP client manager
-│   ├── analyze-tools.ts       # Intelligent tool selection
-│   ├── cli.ts                 # Command-line interface
-│   ├── package.json           # Dependencies
-│   ├── tsconfig.json          # TypeScript config
-│   └── .env.example           # Environment template
-└── references/
-    ├── mcp-protocol.md        # MCP protocol reference
-    └── configuration.md       # Config guide
-```
-## Scripts Reference
-### mcp-client.ts
-Core client manager class:
-- Load config from `$HOME/.copilot/.mcp.json`
-- Connect to multiple MCP servers
-- List/execute tools, prompts, resources
-- Lifecycle management
-### cli.ts
-Command-line interface:
-- `list-tools` - Show all tools and save to assets/tools.json
-- `list-prompts` - Show all prompts
-- `list-resources` - Show all resources
-- `call-tool <server> <tool> <json>` - Execute tool
-**Note**: Tool analysis is performed by the LLM reading `assets/tools.json`, which provides better context understanding than algorithmic matching.
-## Configuration
-### Environment Variables
-Scripts check for variables in this order:
-1. `process.env` (runtime)
-2. `$HOME/.copilot/skills/mcp-management/.env`
-3. `$HOME/.copilot/skills/.env`
-4. `$HOME/.copilot/.env`
-### MCP Config Format
-```json
-{
-  "mcpServers": {
-    "server-name": {
-      "command": "executable",          // Required
-      "args": ["arg1", "arg2"],        // Required
-      "env": {                          // Optional
-        "VAR": "value",
-        "API_KEY": "${ENV_VAR}"        // Reference env vars
-      }
-    }
-  }
-}
-```
-## Common MCP Servers
-Install with `npx`:
-- `@modelcontextprotocol/server-memory` - Key-value storage
-- `@modelcontextprotocol/server-filesystem` - File operations
-- `@modelcontextprotocol/server-brave-search` - Web search
-- `@modelcontextprotocol/server-puppeteer` - Browser automation
-- `@modelcontextprotocol/server-fetch` - HTTP requests
-## Integration with mcp-manager Agent
-The `mcp-manager` agent (`$HOME/.copilot/agents/mcp-manager.md`) uses this skill to:
-1. **Discover**: Connect to MCP servers, list capabilities
-2. **Analyze**: Filter relevant tools for tasks
-3. **Execute**: Call MCP tools on behalf of main agent
-4. **Report**: Send concise results back to main agent
-This architecture keeps main context clean and enables efficient MCP integration.
-## Troubleshooting
-### "Config not found"
-Ensure `$HOME/.copilot/.mcp.json` exists and is valid JSON.
-### "Server connection failed"
-Check:
-- Server command is installed (`npx` packages installed?)
-- Server args are correct
-- Environment variables are set
-### "Tool not found"
-List available tools first:
-```bash
-npx ts-node scripts/cli.ts list-tools
-```
-## Resources
-- [MCP Specification](https://modelcontextprotocol.io/specification/latest)
-- [MCP TypeScript SDK](https://github.com/modelcontextprotocol/typescript-sdk)
-- [Official MCP Servers](https://github.com/modelcontextprotocol/servers)
-- [Skill References](./references/)
-## License
-MIT

package/templates/repo/.github/skills/mcp-management/SKILL.md DELETED Viewed

@@ -1,209 +0,0 @@
----
-name: mcp-management
-description: Manage MCP servers - discover, analyze, execute tools/prompts/resources. Use for MCP integrations, intelligent tool selection, multi-server management, context-efficient capability discovery.
----
-# MCP Management
-Skill for managing and interacting with Model Context Protocol (MCP) servers.
-## Overview
-MCP is an open protocol enabling AI agents to connect to external tools and data sources. This skill provides scripts and utilities to discover, analyze, and execute MCP capabilities from configured servers without polluting the main context window.
-**Key Benefits**:
-- Progressive disclosure of MCP capabilities (load only what's needed)
-- Intelligent tool/prompt/resource selection based on task requirements
-- Multi-server management from single config file
-- Context-efficient: agents handle MCP discovery and execution
-- Persistent tool catalog: automatically saves discovered tools to JSON for fast reference
-## When to Use This Skill
-Use this skill when:
-1. **Discovering MCP Capabilities**: Need to list available tools/prompts/resources from configured servers
-2. **Task-Based Tool Selection**: Analyzing which MCP tools are relevant for a specific task
-3. **Executing MCP Tools**: Calling MCP tools programmatically with proper parameter handling
-4. **MCP Integration**: Building or debugging MCP client implementations
-5. **Context Management**: Avoiding context pollution by delegating MCP operations to agents
-## Core Capabilities
-### 1. Configuration Management
-MCP servers configured in `$HOME/.copilot/.mcp.json`.
-**Gemini CLI Integration** (recommended): Create symlink to `.gemini/settings.json`:
-```bash
-mkdir -p .gemini && ln -sf $HOME/.copilot/.mcp.json .gemini/settings.json
-```
-See [references/configuration.md](references/configuration.md) and [references/gemini-cli-integration.md](references/gemini-cli-integration.md).
-**GEMINI.md Response Format**: Project root contains `GEMINI.md` that Gemini CLI auto-loads, enforcing structured JSON responses:
-```json
-{"server":"name","tool":"name","success":true,"result":<data>,"error":null}
-```
-This ensures parseable, consistent output instead of unpredictable natural language. The file defines:
-- Mandatory JSON-only response format (no markdown, no explanations)
-- Maximum 500 character responses
-- Error handling structure
-- Available MCP servers reference
-**Benefits**: Programmatically parseable output, consistent error reporting, DRY configuration (format defined once), context-efficient (auto-loaded by Gemini CLI).
-### 2. Capability Discovery
-```bash
-npx tsx scripts/cli.ts list-tools  # Saves to assets/tools.json
-npx tsx scripts/cli.ts list-prompts
-npx tsx scripts/cli.ts list-resources
-```
-Aggregates capabilities from multiple servers with server identification.
-### 3. Intelligent Tool Analysis
-LLM analyzes `assets/tools.json` directly - better than keyword matching algorithms.
-### 4. Tool Execution
-**Primary: Gemini CLI** (if available)
-```bash
-# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)
-echo "Take a screenshot of https://example.com" | gemini -y -m <gemini.model>
-```
-**Secondary: Direct Scripts**
-```bash
-npx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'
-```
-**Fallback: mcp-manager Agent**
-See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete examples.
-## Implementation Patterns
-### Pattern 1: Gemini CLI Auto-Execution (Primary)
-Use Gemini CLI for automatic tool discovery and execution. Gemini CLI auto-loads `GEMINI.md` from project root to enforce structured JSON responses.
-**Quick Example**:
-```bash
-# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)
-# Add "Return JSON only per GEMINI.md instructions" to enforce structured output
-echo "Take a screenshot of https://example.com. Return JSON only per GEMINI.md instructions." | gemini -y -m <gemini.model>
-```
-**Expected Output**:
-```json
-{"server":"puppeteer","tool":"screenshot","success":true,"result":"screenshot.png","error":null}
-```
-**Benefits**:
-- Automatic tool discovery
-- Structured JSON responses (parseable by the agent)
-- GEMINI.md auto-loaded for consistent formatting
-- Faster than agent orchestration
-- No natural language ambiguity
-See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete guide.
-### Pattern 2: Agent-Based Execution (Fallback)
-Use `mcp-manager` agent when Gemini CLI unavailable. Agent discovers tools, selects relevant ones, executes tasks, reports back.
-**Benefit**: Main context stays clean, only relevant tool definitions loaded when needed.
-### Pattern 3: LLM-Driven Tool Selection
-LLM reads `assets/tools.json`, intelligently selects relevant tools using context understanding, synonyms, and intent recognition.
-### Pattern 4: Multi-Server Orchestration
-Coordinate tools across multiple servers. Each tool knows its source server for proper routing.
-## Scripts Reference
-### scripts/mcp-client.ts
-Core MCP client manager class. Handles:
-- Config loading from `$HOME/.copilot/.mcp.json`
-- Connecting to multiple MCP servers
-- Listing tools/prompts/resources across all servers
-- Executing tools with proper error handling
-- Connection lifecycle management
-### scripts/cli.ts
-Command-line interface for MCP operations. Commands:
-- `list-tools` - Display all tools and save to `assets/tools.json`
-- `list-prompts` - Display all prompts
-- `list-resources` - Display all resources
-- `call-tool <server> <tool> <json>` - Execute a tool
-**Note**: `list-tools` persists complete tool catalog to `assets/tools.json` with full schemas for fast reference, offline browsing, and version control.
-## Quick Start
-**Method 1: Gemini CLI** (recommended)
-```bash
-npm install -g gemini-cli
-mkdir -p .gemini && ln -sf $HOME/.copilot/.mcp.json .gemini/settings.json
-# IMPORTANT: Use stdin piping, NOT -p flag (deprecated, skips MCP init)
-# GEMINI.md auto-loads to enforce JSON responses
-echo "Take a screenshot of https://example.com. Return JSON only per GEMINI.md instructions." | gemini -y -m <gemini.model>
-```
-Returns structured JSON: `{"server":"puppeteer","tool":"screenshot","success":true,"result":"screenshot.png","error":null}`
-**Method 2: Scripts**
-```bash
-cd $HOME/.copilot/skills/mcp-management/scripts && npm install
-npx tsx cli.ts list-tools  # Saves to assets/tools.json
-npx tsx cli.ts call-tool memory create_entities '{"entities":[...]}'
-```
-**Method 3: mcp-manager Agent**
-See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete guide.
-## Technical Details
-See [references/mcp-protocol.md](references/mcp-protocol.md) for:
-- JSON-RPC protocol details
-- Message types and formats
-- Error codes and handling
-- Transport mechanisms (stdio, HTTP+SSE)
-- Best practices
-## Integration Strategy
-### Execution Priority
-1. **Gemini CLI** (Primary): Fast, automatic, intelligent tool selection
-   - Check: `command -v gemini`
-   - Execute: `echo "<task>" | gemini -y -m <gemini.model>`
-   - **IMPORTANT**: Use stdin piping, NOT `-p` flag (deprecated, skips MCP init)
-   - Best for: All tasks when available
-2. **Direct CLI Scripts** (Secondary): Manual tool specification
-   - Use when: Need specific tool/server control
-   - Execute: `npx tsx scripts/cli.ts call-tool <server> <tool> <args>`
-3. **mcp-manager Agent** (Fallback): Context-efficient delegation
-   - Use when: Gemini unavailable or failed
-   - Keeps main context clean
-### Integration with Agents
-The `mcp-manager` agent uses this skill to:
-- Check Gemini CLI availability first
-- Execute via `gemini` command if available
-- Fallback to direct script execution
-- Discover MCP capabilities without loading into main context
-- Report results back to main agent
-This keeps main agent context clean and enables efficient MCP integration.