cokit-cli 1.2.0 → 1.2.2

package/skills/fix/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: fix
 description: ALWAYS activate this skill before fixing ANY bug, error, test failure, CI/CD issue, type error, lint, log error, UI issue, code problem.
-version: 1.1.0
 ---
 
 # Fixing
@@ -18,7 +17,7 @@ Unified skill for fixing issues of any complexity with intelligent routing.
 
 ### Step 1: Mode Selection
 
-**First action:** If there is no "auto" keyword in the request, use `AskUserQuestion` to determine workflow mode:
+**First action:** If there is no "auto" keyword in the request, ask the user directly to choose a workflow mode (then wait for response):
 
 | Option | Recommend When | Behavior |
 |--------|----------------|----------|
@@ -26,13 +25,13 @@ Unified skill for fixing issues of any complexity with intelligent routing.
 | **Human-in-the-loop Review** | Critical/production code | Pause for approval at each step |
 | **Quick** | Type errors, lint, trivial bugs | Fast debug → fix → review cycle |
 
-See `references/mode-selection.md` for AskUserQuestion format.
+See `references/mode-selection.md` for question format.
 
 ### Step 2: Debug
 
 - Activate `debug` skill.
 - Guess all possible root causes.
-- Spawn multiple `Explore` subagents in parallel to verify each hypothesis.
+- Search in parallel to verify each hypothesis.
 - Create report with all findings for the next step.
 
 ### Step 3: Complexity Assessment & Fix Implementation
@@ -49,25 +48,25 @@ Classify before routing. See `references/complexity-assessment.md`.
 ### Step 4: Fix Verification & Prevent Future Issues
 
 - Read and analyze all the implemented changes.
-- Spawn multiple `Explore` subagents to find possible related code for verification.
+- Search in parallel to find possible related code for verification.
 - Make sure these fixes don't break other parts of the codebase.
 - Prevent future issues by adding comprehensive validation.
 
 ### Step 5: Finalize
 
 - Report summary to user with confidence level/score, all the changes and related files.
-- Ask to commit via `git-manager` subagent and update docs if needed via `docs-manager` subagent (in parallel).
+- Ask to commit via `git-manager` agent and update docs if needed via `docs-manager` agent (in parallel).
 
 ---
 
-## IMPORTANT: Skill/Subagent Activation Matrix
+## IMPORTANT: Skill/Agent Activation Matrix
 
 See `references/skill-activation-matrix.md` for complete matrix.
 
 **Always activate:** `debug` (all workflows)
 **Conditional:** `problem-solving`, `sequential-thinking`, `brainstorming`, `context-engineering`
-**Subagents:** `debugger`, `researcher`, `planner`, `code-reviewer`, `tester`, `Bash`
-**Parallel:** Multiple `Explore` agents for scouting, `Bash` agents for verification
+**Agents:** `debugger`, `researcher`, `planner`, `code-reviewer`, `tester`
+**Parallel:** Multiple parallel searches for scouting, terminal commands for verification
 
 ## Output Format
 
@@ -84,14 +83,14 @@ Unified step markers:
 ## References
 
 Load as needed:
-- `references/mode-selection.md` - AskUserQuestion format for mode
+- `references/mode-selection.md` - Mode selection question format
 - `references/complexity-assessment.md` - Classification criteria
 - `references/workflow-quick.md` - Quick: debug → fix → review
 - `references/workflow-standard.md` - Standard: full pipeline
 - `references/workflow-deep.md` - Deep: research + brainstorm + plan
 - `references/review-cycle.md` - Review logic (autonomous vs HITL)
 - `references/skill-activation-matrix.md` - When to activate each skill
-- `references/parallel-exploration.md` - Parallel Explore/Bash subagents patterns
+- `references/parallel-exploration.md` - Parallel search and execution patterns
 
 **Specialized Workflows:**
 - `references/workflow-ci.md` - GitHub Actions/CI failures

package/skills/fix/references/mode-selection.md

@@ -1,32 +1,16 @@
 # Mode Selection
 
-Use `AskUserQuestion` at start of fixing workflow.
-
-## AskUserQuestion Format
-
-```json
-{
-  "questions": [{
-    "question": "How should I handle the fix workflow?",
-    "header": "Fix Mode",
-    "options": [
-      {
-        "label": "Autonomous (Recommended)",
-        "description": "Auto-approve if quality high, only ask when stuck"
-      },
-      {
-        "label": "Human-in-the-loop",
-        "description": "Pause for approval at each major step"
-      },
-      {
-        "label": "Quick fix",
-        "description": "Fast debug-fix-review cycle for simple issues"
-      }
-    ],
-    "multiSelect": false
-  }]
-}
-```
+Ask the user at start of fixing workflow to choose a mode. Present the question directly in your response, then stop and wait for their answer.
+
+## Question Format
+
+Ask the user:
+
+> **Fix Mode:** How should I handle the fix workflow?
+>
+> 1. **Autonomous (Recommended)** — Auto-approve if quality high, only ask when stuck
+> 2. **Human-in-the-loop** — Pause for approval at each major step
+> 3. **Quick fix** — Fast debug-fix-review cycle for simple issues
 
 ## Mode Recommendations
 

package/skills/fix/references/parallel-exploration.md

@@ -1,19 +1,19 @@
 # Parallel Exploration
 
-Patterns for launching multiple subagents in parallel to scout codebase and verify implementation.
+Patterns for launching multiple agents in parallel to scout codebase and verify implementation.
 
 ## Parallel Exploration (Scouting)
 
-Launch multiple `Explore` subagents simultaneously when needing to find:
+Launch multiple `Explore` agents simultaneously when needing to find:
 - Related files across different areas
 - Similar implementations/patterns
 - Dependencies and usage
 
 **Pattern:**
 ```
-Task(subagent_type="Explore", prompt="Find [X] in [area1]", description="Scout area1")
-Task(subagent_type="Explore", prompt="Find [Y] in [area2]", description="Scout area2")
-Task(subagent_type="Explore", prompt="Find [Z] in [area3]", description="Scout area3")
+Task(agent_type="Explore", prompt="Find [X] in [area1]", description="Scout area1")
+Task(agent_type="Explore", prompt="Find [Y] in [area2]", description="Scout area2")
+Task(agent_type="Explore", prompt="Find [Z] in [area3]", description="Scout area3")
 ```
 
 **Example - Multi-area scouting:**
@@ -26,12 +26,12 @@ Task("Explore", "Find test files for auth module", "Scout tests")
 
 ## Parallel Verification (Bash)
 
-Launch multiple `Bash` subagents to verify implementation from different angles.
+Launch multiple `Bash` agents to verify implementation from different angles.
 
 **Pattern:**
 ```
-Task(subagent_type="Bash", prompt="Run [command1]", description="Verify X")
-Task(subagent_type="Bash", prompt="Run [command2]", description="Verify Y")
+Task(agent_type="Bash", prompt="Run [command1]", description="Verify X")
+Task(agent_type="Bash", prompt="Run [command2]", description="Verify Y")
 ```
 
 **Example - Multi-verification:**
@@ -73,5 +73,5 @@ Task("Bash", "Run build", "Verify build")
 ## Resource Limits
 
 - Max 3 parallel agents recommended (system resources)
-- Each subagent has 200K token context limit
+- Each agent has 200K token context limit
 - Keep prompts concise to avoid context bloat

package/skills/fix/references/review-cycle.md

@@ -20,9 +20,9 @@ LOOP:
      → cycle++, GOTO LOOP
 
   4. ELSE IF cycle >= 3:
-     → ESCALATE to user via AskUserQuestion
+     → ESCALATE to user directly in response
      → Display findings
-     → Options: "Fix manually" / "Approve anyway" / "Abort"
+     → Ask: "Fix manually" / "Approve anyway" / "Abort" — wait for response
 
   5. ELSE (score < 9.5, no critical):
      → Output: "✓ Review [score]/10 - Approved with [N] warnings"
@@ -44,7 +44,7 @@ ALWAYS:
      │ Suggestions ([N]): [list]           │
      └─────────────────────────────────────┘
 
-  3. Use AskUserQuestion:
+  3. Ask user directly in response, then wait for answer:
      IF critical_count > 0:
        - "Fix critical issues"
        - "Fix all issues"

package/skills/fix/references/skill-activation-matrix.md

@@ -18,9 +18,9 @@ When to activate each skill during fixing workflows.
 | `context-engineering` | Fixing AI/LLM/agent code, context window issues |
 | ImageMagick/FFmpeg | Image/video processing, visual asset manipulation |
 
-## Subagent Usage
+## Agent Usage
 
-| Subagent | Activate When |
+| Agent | Activate When |
 |----------|---------------|
 | `debugger` | Root cause unclear, need deep investigation |
 | `Explore` (parallel) | Scout multiple areas simultaneously |
@@ -61,5 +61,5 @@ See `references/parallel-exploration.md` for detailed patterns.
 | "stuck", "tried everything" | `problem-solving` |
 | "complex", "multi-step" | `sequential-thinking` |
 | "which approach", "options" | `brainstorming` |
-| "latest docs", "best practice" | `researcher` subagent |
+| "latest docs", "best practice" | `researcher` agent |
 | Screenshot attached | Visual analysis |

package/skills/fix/references/workflow-deep.md

@@ -5,7 +5,7 @@ Full pipeline with research, brainstorming, and planning for complex issues.
 ## Steps
 
 ### Step 1: Debug & Parallel Investigation
-Activate `debug` skill. Launch 2-3 `Explore` subagents in parallel:
+Activate `debug` skill. Launch 2-3 `Explore` agents in parallel:
 ```
 Task("Explore", "Find error origin", "Trace error")
 Task("Explore", "Find affected components", "Map deps")
@@ -16,7 +16,7 @@ See `references/parallel-exploration.md` for patterns.
 **Output:** `✓ Step 1: Root cause - [summary], system impact: [scope]`
 
 ### Step 2: Research
-Use `researcher` subagent for external knowledge.
+Use `researcher` agent for external knowledge.
 
 - Search latest docs, best practices
 - Find similar issues/solutions
@@ -34,7 +34,7 @@ Activate `brainstorming` skill.
 **Output:** `✓ Step 3: Approach selected - [chosen approach]`
 
 ### Step 4: Plan
-Use `planner` subagent to create implementation plan.
+Use `planner` agent to create implementation plan.
 
 - Break down into phases
 - Identify dependencies
@@ -51,7 +51,7 @@ See `references/parallel-exploration.md`
 **Output:** `✓ Step 5: Implemented - [N] files, [M] phases, verified`
 
 ### Step 6: Test
-Use `tester` subagent.
+Use `tester` agent.
 
 - Comprehensive testing
 - Edge cases, security, performance
@@ -60,24 +60,24 @@ Use `tester` subagent.
 **Output:** `✓ Step 6: Tests [X/X passed]`
 
 ### Step 7: Review
-Use `code-reviewer` subagent.
+Use `code-reviewer` agent.
 
 See `references/review-cycle.md` for mode-specific handling.
 
 **Output:** `✓ Step 7: Review [score]/10 - [status]`
 
 ### Step 8: Finalize
-- Use `project-manager` subagent to update roadmap
-- Use `docs-manager` subagent for documentation
-- Use `git-manager` subagent for commit
+- Use `project-manager` agent to update roadmap
+- Use `docs-manager` agent for documentation
+- Use `git-manager` agent for commit
 
 **Output:** `✓ Step 8: Complete - [actions taken]`
 
-## Skills/Subagents Activated
+## Skills/Agents Activated
 
-| Step | Skills/Subagents |
+| Step | Skills/Agents |
 |------|------------------|
-| 1 | `debug`, parallel `Explore` subagents for investigation |
+| 1 | `debug`, parallel `Explore` agents for investigation |
 | 2 | `researcher` |
 | 3 | `brainstorm` |
 | 4 | `planner` |

package/skills/fix/references/workflow-quick.md

@@ -5,7 +5,7 @@ Fast debug-fix-review cycle for simple issues.
 ## Steps
 
 ### Step 1: Debug
-Activate `debug` skill. Find root cause quickly. Verify the root cause with multiple `Explore` subagents in parallel.
+Activate `debug` skill. Find root cause quickly. Verify the root cause with multiple `Explore` agents in parallel.
 - Read error message/logs
 - Locate affected file(s)
 - Identify exact fix needed
@@ -29,7 +29,7 @@ See `references/parallel-exploration.md` for patterns.
 **Output:** `✓ Step 2: Fixed - [N] files, verified (types/lint passed)`
 
 ### Step 3: Verify
-Use `code-reviewer` subagent for quick review.
+Use `code-reviewer` agent for quick review.
 
 Prompt: "Quick review of fix for [issue]. Check: correctness, security, no regressions. Score X/10."
 
@@ -40,16 +40,16 @@ Prompt: "Quick review of fix for [issue]. Check: correctness, security, no regre
 ### Step 4: Complete
 Report summary to user.
 
-**If autonomous mode:** Ask to commit via `git-manager` subagent if score >= 9.0
+**If autonomous mode:** Ask to commit via `git-manager` agent if score >= 9.0
 **If HITL mode:** Ask user next action
 
 **Output:** `✓ Step 4: Complete - [action]`
 
-## Skills/Subagents Activated
+## Skills/Agents Activated
 
 - `debug` - Always (Step 1)
 - Parallel `git-manager` - Verification (Step 2)
-- `code-reviewer` subagent - Always (Step 3)
+- `code-reviewer` agent - Always (Step 3)
 - `context-engineering` - If dealing with AI/LLM code
 
 ## Notes

package/skills/fix/references/workflow-standard.md

@@ -5,7 +5,7 @@ Full pipeline for moderate complexity issues.
 ## Steps
 
 ### Step 1: Debug & Investigate
-Activate `debug` skill. Use `debugger` subagent if needed.
+Activate `debug` skill. Use `debugger` agent if needed.
 
 - Read error messages, logs, stack traces
 - Reproduce the issue
@@ -15,7 +15,7 @@ Activate `debug` skill. Use `debugger` subagent if needed.
 **Output:** `✓ Step 1: Root cause - [summary], [N] files affected`
 
 ### Step 2: Parallel Scout
-Launch multiple `Explore` subagents in parallel to scout and verify the root cause.
+Launch multiple `Explore` agents in parallel to scout and verify the root cause.
 
 **Pattern:** In SINGLE message, launch 2-3 Explore agents:
 ```
@@ -48,7 +48,7 @@ Task("Bash", "Run build", "Verify build")
 **Output:** `✓ Step 3: Implemented - [N] files, verified (types/lint/build passed)`
 
 ### Step 4: Test
-Use `tester` subagent to run tests.
+Use `tester` agent to run tests.
 
 - Write new tests if needed
 - Run existing test suite
@@ -57,7 +57,7 @@ Use `tester` subagent to run tests.
 **Output:** `✓ Step 4: Tests [X/X passed]`
 
 ### Step 5: Review
-Use `code-reviewer` subagent.
+Use `code-reviewer` agent.
 
 See `references/review-cycle.md` for mode-specific handling.
 
@@ -65,21 +65,21 @@ See `references/review-cycle.md` for mode-specific handling.
 
 ### Step 6: Finalize
 - Report summary to user
-- Ask to commit via `git-manager` subagent
+- Ask to commit via `git-manager` agent
 - Update docs if needed via `docs-manager`
 
 **Output:** `✓ Step 6: Complete - [action]`
 
-## Skills/Subagents Activated
+## Skills/Agents Activated
 
-| Step | Skills/Subagents |
+| Step | Skills/Agents |
 |------|------------------|
-| 1 | `debug`, `debugger` subagent |
-| 2 | Multiple `Explore` subagents in parallel (optional) |
+| 1 | `debug`, `debugger` agent |
+| 2 | Multiple `Explore` agents in parallel (optional) |
 | 3 | `problem-solving`, `sequential-thinking`, parallel `Bash` for verification |
-| 4 | `tester` subagent |
-| 5 | `code-reviewer` subagent |
-| 6 | `git-manager`, `docs-manager` subagents |
+| 4 | `tester` agent |
+| 5 | `code-reviewer` agent |
+| 6 | `git-manager`, `docs-manager` agents |
 
 **Rules:** Don't skip steps. Validate before proceeding. One phase at a time.
 **Frontend:** Use `agent-browser` or browser automation tools to verify.

package/skills/frontend-design/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: frontend-design
 description: Create polished frontend interfaces from designs/screenshots. Use for web components, replicating UI designs, quick prototypes, avoiding AI slop.
-license: Complete terms in LICENSE.txt
 ---
 
 Create distinctive, production-grade frontend interfaces. Implement real working code with exceptional aesthetic attention.
@@ -22,7 +21,7 @@ Choose workflow based on input type:
 ## Screenshot/Video Replication (Quick Reference)
 
 1. **Analyze** visually - extract colors, fonts, spacing, effects
-2. **Plan** with `ui-ux-designer` subagent - create phased implementation
+2. **Plan** with `ui-ux-designer` agent - create phased implementation
 3. **Implement** - match source precisely
 4. **Verify** - compare to original
 5. **Document** - update `./docs/design-guidelines.md` if approved
@@ -72,4 +71,4 @@ DO:
 - Match complexity to vision (maximalist = elaborate; minimalist = precise)
 - Make unexpected, context-specific choices
 
-Remember: Claude is capable of extraordinary creative work. Commit fully to distinctive visions.
+Remember: The AI agent is capable of extraordinary creative work. Commit fully to distinctive visions.

package/skills/frontend-design/references/workflow-describe.md

@@ -50,7 +50,7 @@ Analyze and describe exhaustively:
 **Font Prediction**: Match actual fonts, avoid Inter/Poppins defaults.
 
 ### 2. Create Implementation Plan
-Use `ui-ux-designer` subagent:
+Use `ui-ux-designer` agent:
 - Create plan directory (use `## Naming` pattern)
 - Write `plan.md` overview (<80 lines)
 - Add detailed `phase-XX-name.md` files

package/skills/frontend-design/references/workflow-quick.md

@@ -14,7 +14,7 @@ Quick reference from `ui-styling` skill:
 ## Workflow Steps
 
 ### 1. Start Design Process
-Use `ui-ux-designer` subagent directly:
+Use `ui-ux-designer` agent directly:
 - Skip extensive planning
 - Move to implementation quickly
 - Make design decisions on-the-fly

package/skills/frontend-design/references/workflow-screenshot.md

@@ -22,7 +22,7 @@ Extract from screenshot:
 **Font Prediction**: Avoid defaulting to Inter/Poppins. Match actual fonts visible.
 
 ### 2. Create Implementation Plan
-Use `ui-ux-designer` subagent:
+Use `ui-ux-designer` agent:
 - Create plan directory (use `## Naming` pattern from hooks)
 - Write `plan.md` (<80 lines, generic overview)
 - Add `phase-XX-name.md` files with:

package/skills/git/SKILL.md

@@ -1,18 +1,17 @@
 ---
 name: git
 description: Git operations with conventional commits. Use for staging, committing, pushing, PRs, merges. Auto-splits commits by type/scope. Security scans for secrets.
-version: 1.0.0
 ---
 
 # Git Operations
 
-Execute git workflows via `git-manager` subagent to isolate verbose output.
+Execute git workflows via `git-manager` agent to isolate verbose output.
 Activate `context-engineering` skill.
 
 **IMPORTANT:**
 - Sacrifice grammar for the sake of concision.
 - Ensure token efficiency while maintaining high quality.
-- Pass these rules to subagents.
+- Pass these rules to agents.
 
 ## Arguments
 - `cm`: Stage files & create commits

package/skills/git/references/commit-standards.md

@@ -26,8 +26,8 @@ type(scope): description
 - Only use `feat`, `fix`, or `perf` prefixes for files in `.copilot` directory (do not use `docs`).
 
 ## NEVER Include AI Attribution
-- ❌ "Generated with Claude"
-- ❌ "Co-Authored-By: Claude"
+- ❌ "Generated with AI"
+- ❌ "Co-Authored-By: AI"
 - ❌ Any AI reference
 
 ## Good Examples

package/skills/git/references/workflow-commit.md

@@ -1,6 +1,6 @@
 # Commit Workflow
 
-Execute via `git-manager` subagent.
+Execute via `git-manager` agent.
 
 ## Tool 1: Stage + Analyze
 ```bash

package/skills/git/references/workflow-merge.md

@@ -1,6 +1,6 @@
 # Merge Workflow
 
-Execute via `git-manager` subagent.
+Execute via `git-manager` agent.
 
 ## Variables
 - TO_BRANCH: target (defaults to `main`)

package/skills/git/references/workflow-pr.md

@@ -1,6 +1,6 @@
 # Pull Request Workflow
 
-Execute via `git-manager` subagent.
+Execute via `git-manager` agent.
 
 ## Variables
 - TO_BRANCH: target (defaults to `main`)

package/skills/git/references/workflow-push.md

@@ -1,6 +1,6 @@
 # Push Workflow
 
-Execute via `git-manager` subagent.
+Execute via `git-manager` agent.
 
 ## Pre-Push Checklist
 1. All changes committed

package/skills/install.ps1

@@ -1,5 +1,5 @@
-# Skills Installation Script for Windows (PowerShell)
-# Installs all dependencies for Claude Code skills
+# CoKit Skills Installation Script for Windows (PowerShell)
+# Installs all dependencies for skills
 #
 # Exit codes (rustup model):
 #   0 = Success (full or partial)
@@ -1093,13 +1093,13 @@ function Show-Usage {
     Write-Host "  ..copilot\skills\.venv\Scripts\Activate.ps1"
     Write-Host ""
     Write-Host "For more information, see:" -ForegroundColor Blue
-    Write-Host "  .claude\skills\INSTALLATION.md"
+    Write-Host "  .copilot\skills\INSTALLATION.md"
     Write-Host ""
 }
 
 # Show help
 function Show-Help {
-    Write-Host "Claude Code Skills Installation Script for Windows"
+    Write-Host "CoKit Skills Installation Script for Windows"
     Write-Host ""
     Write-Host "Usage:"
     Write-Host "  .\install.ps1 [Options]"
@@ -1146,7 +1146,7 @@ function Main {
     }
 
     Write-Host ""  # Just add spacing, don't clear terminal
-    Write-Header "Claude Code Skills Installation (Windows)"
+    Write-Header "CoKit Skills Installation (Windows)"
     Write-Info "Script directory: $ScriptDir"
 
     # Store preference in script scope for functions to access

package/skills/install.sh

@@ -1,6 +1,6 @@
 #!/bin/bash
 # Skills Installation Script for Linux/macOS
-# Installs all dependencies for Claude Code skills
+# Installs all dependencies for skills
 #
 # Exit codes (rustup model):
 #   0 = Success (full or partial)
@@ -1199,7 +1199,7 @@ print_usage() {
 # Main installation flow
 main() {
     echo ""  # Just add spacing, don't clear terminal
-    print_header "Claude Code Skills Installation"
+    print_header "CoKit Skills Installation"
     print_info "OS: $OS"
     if [[ "$OS" == "linux" ]] || [[ "$OS" == "wsl" ]]; then
         print_info "Distro: $DISTRO"

package/skills/mcp-management/README.md

@@ -4,7 +4,7 @@ Intelligent management and execution of Model Context Protocol (MCP) servers.
 
 ## Overview
 
-This skill enables Claude to discover, analyze, and execute MCP server capabilities without polluting the main context window. Perfect for context-efficient MCP integration using subagent-based architecture.
+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
 
@@ -12,7 +12,7 @@ This skill enables Claude to discover, analyze, and execute MCP server capabilit
 - **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` subagent
+- **Context Efficiency**: Delegate MCP operations to `mcp-manager` agent
 
 ## Quick Start
 
@@ -71,13 +71,13 @@ The LLM reads `assets/tools.json` and intelligently selects tools. No separate a
 npx ts-node scripts/cli.ts call-tool memory add '{"key":"name","value":"Alice"}'
 ```
 
-### Pattern 4: Use with Subagent
+### Pattern 4: Use with Agent
 
-In main Claude conversation:
+In main conversation:
 
 ```
 User: "I need to search the web and save results"
-Main Agent: [Spawns mcp-manager subagent]
+Main Agent: [Spawns mcp-manager agent]
 mcp-manager: Discovers brave-search + memory tools, reports back
 Main Agent: Uses recommended tools for implementation
 ```
@@ -85,9 +85,9 @@ Main Agent: Uses recommended tools for implementation
 ## Architecture
 
 ```
-Main Agent (Claude)
+Main Agent
     ↓ (delegates MCP tasks)
-mcp-manager Subagent
+mcp-manager Agent
     ↓ (uses skill)
 mcp-management Skill
     ↓ (connects via)
@@ -96,7 +96,7 @@ MCP Servers (memory, filesystem, etc.)
 
 **Benefits**:
 - Main agent context stays clean
-- MCP discovery happens in isolated subagent context
+- MCP discovery happens in isolated agent context
 - Only relevant tool definitions loaded when needed
 - Reduced token usage