cokit-cli 1.2.0 → 1.2.2

package/skills/mcp-management/SKILL.md

@@ -15,7 +15,7 @@ MCP is an open protocol enabling AI agents to connect to external tools and data
 - 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: subagents handle MCP discovery and execution
+- 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
@@ -25,7 +25,7 @@ Use this skill when:
 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 subagents
+5. **Context Management**: Avoiding context pollution by delegating MCP operations to agents
 
 ## Core Capabilities
 
@@ -80,7 +80,7 @@ echo "Take a screenshot of https://example.com" | gemini -y -m <gemini.model>
 npx tsx scripts/cli.ts call-tool memory create_entities '{"entities":[...]}'
 ```
 
-**Fallback: mcp-manager Subagent**
+**Fallback: mcp-manager Agent**
 
 See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete examples.
 
@@ -104,16 +104,16 @@ echo "Take a screenshot of https://example.com. Return JSON only per GEMINI.md i
 
 **Benefits**:
 - Automatic tool discovery
-- Structured JSON responses (parseable by Claude)
+- Structured JSON responses (parseable by the agent)
 - GEMINI.md auto-loaded for consistent formatting
-- Faster than subagent orchestration
+- Faster than agent orchestration
 - No natural language ambiguity
 
 See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete guide.
 
-### Pattern 2: Subagent-Based Execution (Fallback)
+### Pattern 2: Agent-Based Execution (Fallback)
 
-Use `mcp-manager` agent when Gemini CLI unavailable. Subagent discovers tools, selects relevant ones, executes tasks, reports back.
+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.
 
@@ -166,7 +166,7 @@ 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 Subagent**
+**Method 3: mcp-manager Agent**
 
 See [references/gemini-cli-integration.md](references/gemini-cli-integration.md) for complete guide.
 
@@ -193,7 +193,7 @@ See [references/mcp-protocol.md](references/mcp-protocol.md) for:
    - Use when: Need specific tool/server control
    - Execute: `npx tsx scripts/cli.ts call-tool <server> <tool> <args>`
 
-3. **mcp-manager Subagent** (Fallback): Context-efficient delegation
+3. **mcp-manager Agent** (Fallback): Context-efficient delegation
    - Use when: Gemini unavailable or failed
    - Keeps main context clean
 

package/skills/mcp-management/references/gemini-cli-integration.md

@@ -97,7 +97,7 @@ echo "Search for latest Next.js 15 features and summarize the top 3" | gemini -y
 
 **Multi-Tool Orchestration**:
 ```bash
-echo "Search for Claude AI documentation, take a screenshot of the homepage, and save both to memory" | gemini -y -m <gemini.model>
+echo "Search for AI documentation, take a screenshot of the homepage, and save both to memory" | gemini -y -m <gemini.model>
 ```
 
 **Browser Automation**:
@@ -212,7 +212,7 @@ Shows detailed MCP communication logs.
 | Direct Scripts | ⭐⭐ | ⭐⭐⭐ | ⭐⭐⭐ | Specific tools |
 | mcp-manager | ⭐ | ⭐⭐ | ⭐⭐⭐ | Fallback |
 
-**Recommendation**: Use Gemini CLI as primary method, fallback to scripts/subagent when unavailable.
+**Recommendation**: Use Gemini CLI as primary method, fallback to scripts/agent when unavailable.
 
 ## Resources
 

package/skills/mcp-management/scripts/.env.example

@@ -1,7 +1,7 @@
 # MCP Management Scripts Environment Variables
 
-# Path to MCP configuration file (optional, defaults to .claude/.mcp.json)
-MCP_CONFIG_PATH=.claude/.mcp.json
+# Path to MCP configuration file (optional, defaults to .copilot/.mcp.json)
+MCP_CONFIG_PATH=.copilot/.mcp.json
 
 # Logging level (optional, defaults to info)
 LOG_LEVEL=info

package/skills/planning/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: planning
 description: Plan implementations, design architectures, create technical roadmaps with detailed phases. Use for feature planning, system design, solution architecture, implementation strategy, phase documentation.
-license: MIT
 ---
 
 # Planning
@@ -60,11 +59,11 @@ Load: `references/output-standards.md`
 
 ## Task Integration (Optional)
 
-When session has `CLAUDE_CODE_TASK_LIST_ID` set (active plan):
-- Use TaskCreate to create tasks for each phase with clear subjects
+When session has `TASK_LIST_ID` set (active plan):
+- Create tasks for each phase with clear subjects
 - Set dependencies: Phase N+1 `blockedBy` Phase N
-- Subagents coordinate via shared task list automatically
-- Use TaskUpdate to mark progress (in_progress → completed)
+- Agents coordinate via shared task list automatically
+- Update tasks to mark progress (in_progress → completed)
 
 ### Important
 DO NOT create plans or reports in USER directory.

package/skills/planning/references/output-standards.md

@@ -98,7 +98,7 @@ List affected files with:
 - Prioritize actionable info
 
 ### Unresolved Questions
-**IMPORTANT:** Use `AskUserQuestion` to ask users for unresolved questions at the end
+**IMPORTANT:** List unresolved questions at the end of your response and ask users directly. Wait for their answers before finalizing.
 - Questions needing clarification
 - Technical decisions requiring input
 - Unknowns impacting implementation

package/skills/planning/references/plan-organization.md

@@ -48,7 +48,7 @@ Check the `## Plan Context` section injected by hooks:
 
 **After Creating Plan:**
 ```bash
-# Update session state so subagents get the new plan context:
+# Update session state so agents get the new plan context:
 node $HOME/.copilot/scripts/set-active-plan.cjs {plan-dir}
 ```
 

package/skills/problem-solving/SKILL.md

@@ -1,7 +1,6 @@
 ---
-name: Problem-Solving Techniques
+name: problem-solving
 description: Apply systematic problem-solving techniques when stuck. Use for complexity spirals, innovation blocks, recurring patterns, assumption constraints, simplification cascades, scale uncertainty.
-version: 2.0.0
 ---
 
 # Problem-Solving Techniques

package/skills/repomix/SKILL.md

@@ -5,7 +5,7 @@ description: Pack repositories into AI-friendly files with Repomix (XML, Markdow
 
 # Repomix Skill
 
-Repomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like Claude, ChatGPT, and Gemini.
+Repomix packs entire repositories into single, AI-friendly files. Perfect for feeding codebases to LLMs like ChatGPT, Gemini, and others.
 
 ## When to Use
 
@@ -153,7 +153,7 @@ repomix --init  # creates repomix.config.json
 Repomix automatically counts tokens for individual files, total repository, and per-format output.
 
 Typical LLM context limits:
-- Claude Sonnet 4.5: ~200K tokens
+- Model (Medium): ~200K tokens
 - GPT-4: ~128K tokens
 - GPT-3.5: ~16K tokens
 

package/skills/repomix/references/usage-patterns.md

@@ -144,9 +144,9 @@ repomix --include "$(cat staged-files.txt | tr '\n' ',')" -o .context/latest.xml
 {"version": "2.0.0", "tasks": [{"label": "Package for AI", "type": "shell", "command": "repomix --include 'src/**' --remove-comments --copy"}]}
 ```
 
-### Claude Code
+### AI Coding Agent
 ```bash
-repomix --style markdown --copy  # Then paste into Claude
+repomix --style markdown --copy  # Then paste into the AI agent
 ```
 
 ## Language-Specific Patterns

package/skills/research/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: research
 description: Research technical solutions, analyze architectures, gather requirements thoroughly. Use for technology evaluation, best practices research, solution design, scalability/security/maintainability analysis.
-license: MIT
 ---
 
 # Research

package/skills/scout/SKILL.md

@@ -1,7 +1,6 @@
 ---
 name: scout
-description: Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal (Explore) and external (Gemini/OpenCode) agents.
-version: 1.0.0
+description: Fast codebase scouting using parallel agents. Use for file discovery, task context gathering, quick searches across directories. Supports internal and external search agents.
 ---
 
 # Scout
@@ -9,7 +8,7 @@ version: 1.0.0
 Fast, token-efficient codebase scouting using parallel agents to find files needed for tasks.
 
 ## Arguments
-- Default: Scout using built-in Explore subagents in parallel (`./references/internal-scouting.md`)
+- Default: Scout using built-in search agents in parallel (`./references/internal-scouting.md`)
 - `ext`: Scout using external Gemini/OpenCode CLI tools in parallel (`./references/external-scouting.md`)
 
 ## When to Use
@@ -37,7 +36,7 @@ Read from `$HOME/.copilot/.ck.json`:
 ### 1. Analyze Task
 - Parse user prompt for search targets
 - Identify key directories, patterns, file types, lines of code
-- Determine optimal SCALE value of subagents to spawn
+- Determine optimal SCALE value of agents to spawn
 
 ### 2. Divide and Conquer
 - Split codebase into logical segments per agent
@@ -46,14 +45,14 @@ Read from `$HOME/.copilot/.ck.json`:
 
 ### 3. Spawn Parallel Agents
 Load appropriate reference based on decision tree:
-- **Internal (Default):** `references/internal-scouting.md` (Explore subagents)
+- **Internal (Default):** `references/internal-scouting.md` (search agents)
 - **External:** `references/external-scouting.md` (Gemini/OpenCode)
 
 **Notes:**
-- Prompt detailed instructions for each subagent with exact directories or files it should read
-- Remember that each subagent has less than 200K tokens of context window
-- Amount of subagents to-be-spawned depends on the current system resources available and amount of files to be scanned
-- Each subagent must return a detailed summary report to a main agent
+- Prompt detailed instructions for each agent with exact directories or files it should read
+- Remember that each agent has less than 200K tokens of context window
+- Amount of agents to-be-spawned depends on the current system resources available and amount of files to be scanned
+- Each agent must return a detailed summary report to a main agent
 
 ### 4. Collect Results
 - Timeout: 3 minutes per agent (skip non-responders)
@@ -75,5 +74,5 @@ Load appropriate reference based on decision tree:
 
 ## References
 
-- `references/internal-scouting.md` - Using Explore subagents
+- `references/internal-scouting.md` - Using search agents
 - `references/external-scouting.md` - Using Gemini/OpenCode CLI

package/skills/scout/references/external-scouting.md

@@ -57,16 +57,16 @@ which opencode
 
 If not installed, ask user:
 1. **Yes** - Provide installation instructions (may need manual auth steps)
-2. **No** - Fall back to Explore subagents (`internal-scouting.md`)
+2. **No** - Fall back to Explore agents (`internal-scouting.md`)
 
 ## Spawning Parallel Bash Agents
 
-Use `Task` tool with `subagent_type: "Bash"` to spawn parallel agents:
+Use `Task` tool with `type: "Bash"` to spawn parallel agents:
 
 ```
-Task 1: subagent_type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt1]'"
-Task 2: subagent_type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt2]'"
-Task 3: subagent_type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt3]'"
+Task 1: type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt1]'"
+Task 2: type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt2]'"
+Task 3: type="Bash", prompt="Run: gemini -y -m gemini-3.0-flash '[prompt3]'"
 ```
 
 Spawn all in single message for parallel execution.
@@ -112,15 +112,15 @@ lines_per_chunk = ceil(total_lines / chunks)
 
 **Small files (<500 lines each):**
 ```
-Task 1: subagent_type="Bash", prompt="cat file1.ts file2.ts"
-Task 2: subagent_type="Bash", prompt="cat file3.ts file4.ts"
+Task 1: type="Bash", prompt="cat file1.ts file2.ts"
+Task 2: type="Bash", prompt="cat file3.ts file4.ts"
 ```
 
 **Large file (>500 lines) - use sed for ranges:**
 ```
-Task 1: subagent_type="Bash", prompt="sed -n '1,500p' large-file.ts"
-Task 2: subagent_type="Bash", prompt="sed -n '501,1000p' large-file.ts"
-Task 3: subagent_type="Bash", prompt="sed -n '1001,1500p' large-file.ts"
+Task 1: type="Bash", prompt="sed -n '1,500p' large-file.ts"
+Task 2: type="Bash", prompt="sed -n '501,1000p' large-file.ts"
+Task 3: type="Bash", prompt="sed -n '1001,1500p' large-file.ts"
 ```
 
 ### Chunking Decision Tree

package/skills/scout/references/internal-scouting.md

@@ -1,15 +1,15 @@
-# Internal Scouting with Explore Subagents
+# Internal Scouting with Explore Agents
 
-Use Explore subagents when SCALE >= 6 or external tools unavailable.
+Use Explore agents when SCALE >= 6 or external tools unavailable.
 
 ## How It Works
 
-Spawn multiple `Explore` subagents via `Task` tool to search codebase in parallel.
+Spawn multiple `Explore` agents via `Task` tool to search codebase in parallel.
 
 ## Task Tool Configuration
 
 ```
-subagent_type: "Explore"
+type: "Explore"
 ```
 
 ## Prompt Template
@@ -90,15 +90,15 @@ lines_per_chunk = ceil(total_lines / chunks)
 
 **Small files (<500 lines each):**
 ```
-Task 1: subagent_type="Bash", prompt="cat file1.ts file2.ts"
-Task 2: subagent_type="Bash", prompt="cat file3.ts file4.ts"
+Task 1: type="Bash", prompt="cat file1.ts file2.ts"
+Task 2: type="Bash", prompt="cat file3.ts file4.ts"
 ```
 
 **Large file (>500 lines) - use sed for ranges:**
 ```
-Task 1: subagent_type="Bash", prompt="sed -n '1,500p' large-file.ts"
-Task 2: subagent_type="Bash", prompt="sed -n '501,1000p' large-file.ts"
-Task 3: subagent_type="Bash", prompt="sed -n '1001,1500p' large-file.ts"
+Task 1: type="Bash", prompt="sed -n '1,500p' large-file.ts"
+Task 2: type="Bash", prompt="sed -n '501,1000p' large-file.ts"
+Task 3: type="Bash", prompt="sed -n '1001,1500p' large-file.ts"
 ```
 
 ### Chunking Decision Tree

package/skills/sequential-thinking/README.md

@@ -4,7 +4,7 @@ Structured, reflective problem-solving methodology converted from the sequential
 
 ## Overview
 
-This skill teaches Claude to apply systematic sequential thinking methodology for complex problem-solving, without relying on external MCP tools. It enables:
+This skill teaches the AI agent to apply systematic sequential thinking methodology for complex problem-solving, without relying on external MCP tools. It enables:
 - Breaking down complex problems into manageable thought sequences
 - Dynamic adjustment of thought count as understanding evolves
 - Revision of previous thoughts when new insights emerge
@@ -91,7 +91,7 @@ Thought 2/5: [Further analysis]
 
 **Implicit Mode**: Apply methodology internally without cluttering output
 
-## When Claude Should Use This Skill
+## When the Agent Should Use This Skill
 
 Automatically activated for:
 - Complex problem decomposition
@@ -176,7 +176,7 @@ Scripts are **optional tooling** - the methodology can be applied without them.
 
 Converted from: https://github.com/modelcontextprotocol/servers/tree/main/src/sequentialthinking
 
-Original MCP server by Anthropic (MIT License).
+Original MCP server (MIT License).
 Skill conversion:
 - Extracts methodology as instructions
 - Adds executable scripts for deterministic validation

package/skills/sequential-thinking/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: sequential-thinking
 description: Apply step-by-step analysis for complex problems with revision capability. Use for multi-step reasoning, hypothesis verification, adaptive planning, problem decomposition, course correction.
-version: 1.0.0
-license: MIT
 ---
 
 # Sequential Thinking

package/skills/sequential-thinking/package.json

@@ -13,7 +13,7 @@
     "problem-solving",
     "agent-skill"
   ],
-  "author": "Converted from Anthropic MCP Server",
+  "author": "Converted from MCP Server",
   "license": "MIT",
   "devDependencies": {
     "jest": "^29.7.0"

package/skills/ui-styling/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: ui-styling
 description: Style UIs with shadcn/ui components (Radix UI + Tailwind CSS). Use for accessible components, themes, dark mode, responsive layouts, design systems, color customization.
-license: MIT
-version: 1.0.0
 ---
 
 # UI Styling Skill

package/skills/web-testing/SKILL.md

@@ -1,8 +1,6 @@
 ---
 name: web-testing
 description: Web testing with Playwright, Vitest, k6. E2E/unit/integration/load/security/visual/a11y testing. Use for test automation, flakiness, Core Web Vitals, mobile gestures, cross-browser.
-license: Apache-2.0
-version: 3.0.0
 ---
 
 # Web Testing Skill

package/templates/repo/.github/agents/brainstormer.agent.md

@@ -37,7 +37,7 @@ You operate by the holy trinity of software engineering: **YAGNI** (You Aren't G
 ## Collaboration Tools
 - Consult the `planner` agent to research industry best practices and find proven solutions
 - Engage the `docs-manager` agent to understand existing project implementation and constraints
-- Use `WebSearch` tool to find efficient approaches and learn from others' experiences
+- Search the web to find efficient approaches and learn from others' experiences
 
 ## Workflow Phases
 1. **Discovery Phase**: Ask clarifying questions about requirements, constraints, timeline, and success criteria

package/templates/repo/.github/agents/debugger.agent.md

@@ -37,7 +37,7 @@ When investigating issues, you will:
    - Examine application logs and error traces
    - Capture system metrics and performance data
    - Read `./docs/codebase-summary.md` if exists and up-to-date (less than 2 days old)
-   - Use Glob/Grep tools to search the codebase for files needed to complete the task
+   - Search the codebase for files needed to complete the task
    - When given a Github repository URL, use `repomix --remote <github-repo-url>` to generate codebase summary:
       ```bash
       # usage: repomix --remote <github-repo-url>

package/templates/repo/.github/agents/docs-manager.agent.md

@@ -21,7 +21,7 @@ You establish and maintain implementation standards including:
 
 ### 2. Documentation Analysis & Maintenance
 You systematically:
-- Read and analyze all existing documentation files in `./docs` directory using Glob and Read tools
+- Read and analyze all existing documentation files in `./docs` directory
 - Identify gaps, inconsistencies, or outdated information
 - Cross-reference documentation with actual codebase implementation
 - Ensure documentation reflects the current state of the system
@@ -57,7 +57,7 @@ You organize documentation to:
 ### Documentation Review Process
 1. Scan the entire `./docs` directory structure
 2. Generate/update `./docs/codebase-summary.md` with comprehensive codebase summary
-3. Use Glob/Grep tools OR Gemini CLI for large files
+3. Search for content in files OR use Gemini CLI for large files
 4. Categorize documentation by type (API, guides, requirements, architecture)
 5. Check for completeness, accuracy, and clarity
 6. Verify all links, references, and code examples

package/templates/repo/.github/agents/git-manager.agent.md

@@ -296,10 +296,10 @@ Keep output concise (<1k chars). No explanations of what you did.
 ## Token Optimization Strategy
 
 **Delegation rationale:**
-- Gemini Flash 2.5: $0.075/$0.30 per 1M tokens
-- Haiku 4.5: $1/$5 per 1M tokens
-- For 100-line diffs, Gemini = **13x cheaper** for analysis
-- Haiku focuses on orchestration, Gemini does heavy lifting
+- Worker model (e.g. Gemini Flash 2.5): $0.075/$0.30 per 1M tokens
+- Orchestrator model: $1/$5 per 1M tokens
+- For 100-line diffs, worker model = **13x cheaper** for analysis
+- Orchestrator focuses on routing, worker model does heavy lifting
 
 **Efficiency rules:**
 1. **Compound commands only** - use `&&` to chain operations
@@ -314,7 +314,7 @@ Keep output concise (<1k chars). No explanations of what you did.
 - 3 tools @ 5K tokens = $0.015 per commit
 - **81% cost reduction** × 1000 commits/month = $63 saved
 
-## Critical Instructions for Haiku
+## Critical Instructions for Orchestrator
 
 Your role: **EXECUTE, not EXPLORE**
 

package/templates/repo/.github/agents/planner.agent.md

@@ -19,9 +19,9 @@ You operate by **YAGNI** (You Aren't Gonna Need It), **KISS** (Keep It Simple, S
 
 When Read fails with "exceeds maximum allowed tokens":
 1. **Gemini CLI** (2M context): `echo "[question] in [path]" | gemini -y -m gemini-2.5-flash`
-2. **Chunked Read**: Use `offset` and `limit` params to read in portions
-3. **Grep**: Search specific content with `Grep pattern="[term]" path="[path]"`
-4. **Targeted Search**: Use Glob and Grep for specific patterns
+2. Read file in portions using offset and limit parameters
+3. Search for specific content in files
+4. Search for specific file and content patterns
 
 ## Core Mental Models (The "How to Think" Toolkit)
 

package/templates/repo/.github/agents/researcher.agent.md

@@ -24,7 +24,6 @@ You excel at:
 - Recognizing technology trends and adoption patterns
 - Evaluating trade-offs between different technical solutions
 - Using `docs-seeker` skills to find relevant documentation
-- Using `document-skills` skills to read and analyze documents
 **IMPORTANT**: You **DO NOT** start the implementation yourself but respond with the summary and the file path of comprehensive plan.
 
 ## Report Output

package/templates/repo/.github/agents/scout.agent.md

@@ -9,7 +9,7 @@ You are an elite Codebase Scout, a specialized agent designed to rapidly locate
 
 ## Your Core Mission
 
-When given a search task, you will use Glob, Grep, and Read tools to efficiently search the codebase and synthesize findings into a comprehensive file list for the user.
+When given a search task, you will use search and file reading capabilities to efficiently search the codebase and synthesize findings into a comprehensive file list for the user.
 Requirements: **Ensure token efficiency while maintaining high quality.**
 
 ## Operational Protocol
@@ -38,8 +38,8 @@ Example prompt structure:
 "Search the [directories] for files related to [functionality]. Look for [specific patterns like API routes, schema definitions, utility functions]. Return only the file paths that are directly relevant. Be concise and fast - you have 3 minutes."
 
 ### 4. Execute Parallel Searches
-- Use Glob tool with multiple patterns 
-- Use Grep for content-based searches
+- Search with multiple file patterns
+- Search file contents for specific patterns
 - Read key files to understand structure
 - Complete searches within 3-minute target
 
@@ -50,7 +50,7 @@ Example prompt structure:
 
 ## Search Tools
 
-Use Glob, Grep, and Read tools for efficient codebase exploration.
+Use search and file reading for efficient codebase exploration.
 
 ## Example Execution Flow
 
@@ -79,19 +79,19 @@ Use Glob, Grep, and Read tools for efficient codebase exploration.
 
 - If results are sparse: Expand search scope or try different keywords
 - If results are overwhelming: Categorize and prioritize by relevance
-- If Read fails on large files: Use chunked reading or Grep for specific content
+- If Read fails on large files: Use chunked reading or content search for specific content
 
 ## Handling Large Files (>25K tokens)
 
 When Read fails with "exceeds maximum allowed tokens":
 1. **Gemini CLI** (2M context): `echo "[question] in [path]" | gemini -y -m gemini-2.5-flash`
-2. **Chunked Read**: Use `offset` and `limit` params to read in portions
-3. **Grep**: Search specific content with `Grep pattern="[term]" path="[path]"`
+2. Read file in portions using offset and limit parameters
+3. Search for specific content in files
 
 ## Success Criteria
 
 You succeed when:
-1. You execute searches efficiently using Glob, Grep, and Read tools
+1. You execute searches efficiently using search and file reading capabilities
 2. You synthesize results into a clear, actionable file list
 3. The user can immediately proceed with their task using the files you found
 4. You complete the entire operation in under 5 minutes
@@ -104,4 +104,4 @@ Save reports to `plans/reports/` directory with naming pattern `{type}-{date}-{s
 - Sacrifice grammar for the sake of concision when writing reports.
 - In reports, list any unresolved questions at the end, if any.
 
-**Remember:** You are a fast, focused searcher. Your power lies in efficiently using Glob, Grep, and Read tools to quickly locate relevant files.
+**Remember:** You are a fast, focused searcher. Your power lies in efficiently searching and reading files to quickly locate relevant content.

package/templates/repo/.github/agents/ui-ux-designer.agent.md

@@ -54,5 +54,4 @@ Activate relevant skills based on task:
 ## Collaboration
 
 - Delegate research to `researcher` agents for comprehensive insights
-- Coordinate with `project-manager` for progress updates
 - Follow rules in `./docs/development-rules.md`

package/templates/repo/.github/collections/ck-orchestration.collection.yml

@@ -1,7 +1,7 @@
 id: ck-orchestration
 name: CK Orchestration Protocol
-description: Workflow orchestration patterns for managing subagents, task delegation, and multi-phase implementations.
-tags: [orchestration, workflow, subagents, planning]
+description: Workflow orchestration patterns for managing agents, task delegation, and multi-phase implementations.
+tags: [orchestration, workflow, agents, planning]
 items:
   - path: agents/planner.agent.md
     kind: agent

package/templates/repo/.github/prompts/ck-ask.prompt.md

@@ -62,5 +62,6 @@ This command focuses on architectural consultation and strategic guidance. Do no
 
 | Command | Description |
 |---------|-------------|
-| `/ck.brainstorm` | Explore ideas |
-| `/ck.plan` | Create plan |
+| `/ck-brainstorm` | Explore ideas |
+| `/ck-plan` | Create plan |
+| `/ck-spec-specify` | Write detailed feature spec |