kiro-agent-team 1.0.0

package/.kiro/documentation/docs_cli_chat_model-selection.md

@@ -0,0 +1,153 @@
+# Model selection
+Kiro provides multiple powerful AI agent options to handle your development tasks: **Auto** , **Claude Sonnet 4.0** , **Claude Sonnet 4.5** , **Claude Haiku 4.5** , and **Claude Opus 4.5**. Each offers distinct advantages depending on your needs and usage patterns.
+## Available models[](https://kiro.dev/docs/cli/chat/model-selection/#available-models)
+### Auto (recommended)[](https://kiro.dev/docs/cli/chat/model-selection/#auto-recommended)
+Auto is Kiro's default intelligent model router that combines multiple frontier models with advanced optimization techniques.
+**Key benefits:**
+  * **Cost-effective** – Approximately 23% less expensive than direct Sonnet 4 usage
+  * **Smart routing** – Automatically chooses the optimal model for each task
+  * **Consistent quality** – Delivers Sonnet 4-level results across different task types
+  * **Plan efficiency** – Makes your usage limits go further
+
+
+#### What model does Auto use?[](https://kiro.dev/docs/cli/chat/model-selection/#what-model-does-auto-use)
+Auto uses best in class LLM models (Claude Sonnet 4 and alike) to provide you the best quality for the type of tasks assigned to the agent. We maintain a very high bar to ensure that the quality of what is offered under Auto compares to or exceeds the quality of separate models made available to our users.
+### Claude Sonnet 4.0[](https://kiro.dev/docs/cli/chat/model-selection/#claude-sonnet-40)
+Direct access to Anthropic's Claude Sonnet 4.0 model for users who prefer consistent model selection or have specific requirements for using this particular model.
+**Key benefits:**
+  * **Predictable behavior** – Same model for all interactions
+  * **Direct access** – No routing or optimization layers
+  * **Full control** – Complete transparency in model selection
+
+
+### Claude Sonnet 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#claude-sonnet-45)
+Anthropic's best model for complex agents and coding, with the highest intelligence across most tasks.
+**Key benefits:**
+  * **Coding excellence** – Advanced state-of-the-art on SWE-bench Verified
+  * **Agent capabilities** – Extended autonomous operation for hours with effective tool usage
+  * **Enhanced reasoning** – Improved planning, system design, and security engineering
+
+
+### Claude Opus 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#claude-opus-45)
+Anthropic's most intelligent model combining maximum capability with practical performance. Ideal for complex specialized tasks, professional software engineering, and advanced agents.
+**Key benefits:**
+  * **Maximum intelligence** – Step-change improvements in reasoning, coding, and problem-solving
+  * **Practical performance** – More accessible price point than previous Opus models
+  * **Complex reasoning** – Better balance of tradeoffs and ambiguity across multiple systems
+
+
+### Claude Haiku 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#claude-haiku-45)
+Anthropic's fastest and most intelligent Haiku model with near-frontier performance. Delivers intelligence matching Sonnet 4 at significantly lower cost and faster speed.
+**Key benefits:**
+  * **Near-frontier intelligence** – Matches Sonnet 4 performance across reasoning and coding
+  * **Blazing speed** – More than twice the speed of Sonnet 4
+  * **Cost-effective** – Near-frontier intelligence at one-third the cost
+  * **Extended thinking** – First Haiku model with advanced reasoning capabilities
+
+
+## Cost comparison[](https://kiro.dev/docs/cli/chat/model-selection/#cost-comparison)
+Understanding the credit consumption differences:
+Model | Credit Usage | Example Task Cost  
+---|---|---  
+**Claude Haiku 4.5** | 0.4x | 4 credits  
+**Auto** | 1.0x | 10 credits  
+**Claude Sonnet 4.0** | 1.3x | 13 credits  
+**Claude Sonnet 4.5** | 1.3x | 13 credits  
+**Claude Opus 4.5** | 2.2x | 22 credits  
+## Choosing the right model[](https://kiro.dev/docs/cli/chat/model-selection/#choosing-the-right-model)
+### Claude Haiku 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#claude-haiku-45-1)
+Consider using Haiku 4.5 when:
+  * **Speed is critical** – You need fast responses for interactive experiences
+  * **Cost efficiency matters** – Near-frontier intelligence at one-third the cost
+  * **High-volume processing** – Cost-effective intelligence for large-scale deployments
+  * **Real-time applications** – Fast turnaround for user-facing features
+
+
+### Auto[](https://kiro.dev/docs/cli/chat/model-selection/#auto)
+Consider using Auto when:
+  * **Cost efficiency matters** – You want to maximize your plan's value
+  * **General development work** – Most coding, debugging, and planning tasks
+  * **Variable task types** – Working on diverse projects with different requirements
+  * **Plan optimization** – You want your limits to stretch further
+
+
+### Sonnet 4.0 & Sonnet 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#sonnet-40--sonnet-45)
+Consider using Sonnet 4.0 or Sonnet 4.5 when:
+  * **Consistency is critical** – You need predictable model behavior
+  * **Specific requirements** – Your workflow depends on Sonnet 4's particular capabilities
+  * **Model transparency** – You prefer knowing exactly which model handles each request
+  * **Budget flexibility** – Higher costs aren't a primary concern
+
+
+### Claude Opus 4.5[](https://kiro.dev/docs/cli/chat/model-selection/#claude-opus-45-1)
+Consider using Opus 4.5 when:
+  * **Maximum intelligence needed** – Most complex specialized tasks requiring top-tier reasoning
+  * **Professional software engineering** – Sophisticated production development challenges
+  * **Advanced agents** – Long-running autonomous tasks with complex decision-making
+  * **Critical implementations** – High-stakes features where quality is paramount
+
+
+## How to switch models[](https://kiro.dev/docs/cli/chat/model-selection/#how-to-switch-models)
+### In the chat interface[](https://kiro.dev/docs/cli/chat/model-selection/#in-the-chat-interface)
+![/model command usage](https://kiro.dev/images/cli-model-selection.png?h=fa2bf44f)
+### Kiro CLI setting[](https://kiro.dev/docs/cli/chat/model-selection/#kiro-cli-setting)
+bash
+```
+
+kiro-cli settings chat.defaultModel claude-sonnet4
+
+
+```
+
+### Persisting your model selection[](https://kiro.dev/docs/cli/chat/model-selection/#persisting-your-model-selection)
+To save your current model as the default for all future sessions:
+bash
+```
+
+> /model set-current-as-default
+
+
+```
+
+This stores your preference in `~/.kiro/settings/cli.json`. New sessions will automatically use this model.
+## Best practices[](https://kiro.dev/docs/cli/chat/model-selection/#best-practices)
+### Maximizing efficiency[](https://kiro.dev/docs/cli/chat/model-selection/#maximizing-efficiency)
+  * **Start with Auto** – Use it as your default for most tasks
+  * **Use Haiku for speed** – Near-frontier intelligence with fast responses and lower cost
+  * **Use Sonnet for agents** – Best for complex coding and autonomous workflows
+  * **Reserve Opus for maximum intelligence** – Use for the most complex specialized tasks
+  * **Monitor usage** – Track how different models affect your plan consumption
+  * **Experiment** – Try different models for similar tasks to compare results
+
+
+### Cost management[](https://kiro.dev/docs/cli/chat/model-selection/#cost-management)
+  * **Plan accordingly** – Factor model choice into your tier selection
+  * **Track patterns** – Understand which tasks benefit most from each model
+  * **Optimize workflows** – Adjust development practices based on model strengths
+  * **Consider overages** – Enable if you need flexibility beyond plan limits
+
+
+Page updated: December 19, 2025
+[Chat](https://kiro.dev/docs/cli/chat/)
+[Subagents](https://kiro.dev/docs/cli/chat/subagents/)
+On this page
+  * [Available models](https://kiro.dev/docs/cli/chat/model-selection/#available-models)
+  * [Auto (recommended)](https://kiro.dev/docs/cli/chat/model-selection/#auto-recommended)
+  * [What model does Auto use?](https://kiro.dev/docs/cli/chat/model-selection/#what-model-does-auto-use)
+  * [Claude Sonnet 4.0](https://kiro.dev/docs/cli/chat/model-selection/#claude-sonnet-40)
+  * [Claude Sonnet 4.5](https://kiro.dev/docs/cli/chat/model-selection/#claude-sonnet-45)
+  * [Claude Opus 4.5](https://kiro.dev/docs/cli/chat/model-selection/#claude-opus-45)
+  * [Claude Haiku 4.5](https://kiro.dev/docs/cli/chat/model-selection/#claude-haiku-45)
+  * [Cost comparison](https://kiro.dev/docs/cli/chat/model-selection/#cost-comparison)
+  * [Choosing the right model](https://kiro.dev/docs/cli/chat/model-selection/#choosing-the-right-model)
+  * [Claude Haiku 4.5](https://kiro.dev/docs/cli/chat/model-selection/#claude-haiku-45-1)
+  * [Auto](https://kiro.dev/docs/cli/chat/model-selection/#auto)
+  * [Sonnet 4.0 & Sonnet 4.5](https://kiro.dev/docs/cli/chat/model-selection/#sonnet-40--sonnet-45)
+  * [Claude Opus 4.5](https://kiro.dev/docs/cli/chat/model-selection/#claude-opus-45-1)
+  * [How to switch models](https://kiro.dev/docs/cli/chat/model-selection/#how-to-switch-models)
+  * [In the chat interface](https://kiro.dev/docs/cli/chat/model-selection/#in-the-chat-interface)
+  * [Kiro CLI setting](https://kiro.dev/docs/cli/chat/model-selection/#kiro-cli-setting)
+  * [Persisting your model selection](https://kiro.dev/docs/cli/chat/model-selection/#persisting-your-model-selection)
+  * [Best practices](https://kiro.dev/docs/cli/chat/model-selection/#best-practices)
+  * [Maximizing efficiency](https://kiro.dev/docs/cli/chat/model-selection/#maximizing-efficiency)
+  * [Cost management](https://kiro.dev/docs/cli/chat/model-selection/#cost-management)

package/.kiro/documentation/docs_cli_chat_permissions.md

@@ -0,0 +1,68 @@
+# Managing tool permissions
+You can use the `/tools` command to manage permissions for tools that Kiro uses to perform actions on your system. This provides granular control over what actions Kiro can perform.
+Tools commands
+Command | Description  
+---|---  
+`help` | Shows help related to tools.  
+`trust` | Trusts a specific tool for the session.  
+`untrust` | Reverts a tool to per-request confirmation.  
+`trust-all` | Trusts all tools (equivalent to deprecated /acceptall).  
+`reset` | Resets all tools to default permission levels.  
+To view the current permission settings for all tools:
+```
+
+$ kiro-cli chat
+Kiro> /tools
+
+
+```
+
+This displays a list of all available tools and their current permission status (trusted or per-request).
+Tool permissions have two possible states:
+  * _Trusted_ : Kiro can use the tool without asking for confirmation each time.
+  * _Per-request_ : Kiro must ask for your confirmation each time before using the tool.
+
+
+To trust or untrust a specific tool for the current session:
+```
+
+Kiro> /tools trust read
+Kiro> /tools untrust shell
+
+
+```
+
+You can also trust all tools at once with `/tools trust-all`(equivalent to the deprecated `/acceptall` command):
+```
+
+Kiro> /tools trust-all
+
+
+```
+
+###### Warning[](https://kiro.dev/docs/cli/chat/permissions/#warning)
+Using `/tools trust-all` carries risks. For more information, see [Understanding security risks](https://kiro.dev/docs/cli/chat/permissions/command-line-chat-security.html#command-line-chat-security-risks "./command-line-chat-security.html#command-line-chat-security-risks") .
+The following image shows the status of the CLI tools when they are all in their default trust status.
+The following tools are natively available for Kiro to use:
+Available tools
+Tool | Description  
+---|---  
+`read` | Reads files and directories on your system.  
+`write` | Creates and modifies files on your system.  
+`shell` | Executes bash commands on your system.  
+`aws` | Makes AWS CLI calls to interact with AWS services.  
+`report` | Opens a browser to report an issue with the chat to AWS.  
+When Kiro attempts to use a tool that doesn't have explicit permission, it will ask for your approval before proceeding. You can choose to allow or deny the action, or trust the tool for the remainder of your session.
+Each tool has a default trust behavior. `read` is the only tool that is trusted by default.
+Here are some examples of when to use different permission levels:
+  * _Trust fs_read_ : When you want Kiro to read files without confirmation, such as when exploring a codebase.
+  * _Trust fs_write_ : When you're actively working on a project and want Kiro to help you create or modify files.
+  * _Untrust execute_bash_ : When working in sensitive environments where you want to review all commands before execution.
+  * _Untrust use_aws_ : When working with production AWS resources to prevent unintended changes.
+
+
+When Kiro uses a tool, it shows you the trust permission being used.
+You can also specify trust permissions as part of starting a `kiro-cli chat` session.
+Page updated: November 18, 2025
+[Responding to messages](https://kiro.dev/docs/cli/chat/responding/)
+[Working with Git](https://kiro.dev/docs/cli/chat/git-aware-selection/)

package/.kiro/documentation/docs_cli_chat_planning-agent.md

@@ -0,0 +1,230 @@
+# Plan agent
+The Plan agent is a specialized built-in agent that helps transform ideas into structured implementation plans. It guides you through requirements gathering, research, and creates detailed task breakdowns before switching to execution mode.
+## Getting started[](https://kiro.dev/docs/cli/chat/planning-agent/#getting-started)
+### Keyboard shortcut[](https://kiro.dev/docs/cli/chat/planning-agent/#keyboard-shortcut)
+Press `Shift + Tab` to toggle between plan and execution modes.
+### Slash command[](https://kiro.dev/docs/cli/chat/planning-agent/#slash-command)
+bash
+```
+
+> /plan
+
+Switched to the Kiro [plan] agent. Transform any idea into fully working code.
+What do you want to build today?
+
+[plan] >
+
+
+```
+
+### With immediate prompt[](https://kiro.dev/docs/cli/chat/planning-agent/#with-immediate-prompt)
+bash
+```
+
+> /plan Build a REST API for user authentication
+
+
+```
+
+When active, you'll see:
+  * `[plan]` indicator in your prompt
+  * Welcome message when switching modes
+
+
+## Plan workflow[](https://kiro.dev/docs/cli/chat/planning-agent/#plan-workflow)
+### 1. Requirements gathering[](https://kiro.dev/docs/cli/chat/planning-agent/#1-requirements-gathering)
+The planner guides you through structured questions to refine your initial idea.
+bash
+```
+
+[plan] > I want to build a todo app
+
+I understand you want to build a todo app. Let me help you plan this
+implementation.
+
+**My Understanding:** You want to create a todo application for managing tasks.
+
+Let me gather some requirements to create a detailed plan:
+
+[1]: What platform should this todo app target?
+a. **Web Application** - Browser-based with HTML/CSS/JavaScript
+b. **Mobile App** - Native iOS/Android or cross-platform
+c. **Desktop App** - Electron, Tauri, or native desktop
+d. **CLI Tool** - Command-line interface
+e. **Other** - Provide your own answer
+
+[2]: What's the primary use case for this todo app?
+a. **Personal Task Management** - Individual productivity
+b. **Team Collaboration** - Shared tasks and assignments
+c. **Project Management** - Complex workflows with dependencies
+d. **Other** - Describe your specific needs
+
+(Use the chat to answer any subset: eg., "1=a, 2=b" or provide your own answers)
+
+
+```
+
+Feature | Description  
+---|---  
+Structured questions | Clear, numbered questions with multiple choice options  
+Flexible responses | Answer individual questions or provide custom responses  
+Iterative process | Builds understanding through multiple rounds of questions  
+Context awareness | Adapts follow-up questions based on your answers  
+### 2. Research and analysis[](https://kiro.dev/docs/cli/chat/planning-agent/#2-research-and-analysis)
+The planner explores your codebase and researches relevant technologies.
+Capability | Description  
+---|---  
+Code exploration | Uses code, grep, and glob tools to understand existing code  
+Technology research | Identifies relevant frameworks, libraries, and patterns  
+Architecture analysis | Reviews existing project structure and conventions  
+### 3. Implementation plan[](https://kiro.dev/docs/cli/chat/planning-agent/#3-implementation-plan)
+Creates a detailed, step-by-step implementation plan with clear objectives.
+bash
+```
+
+**Implementation Plan - Todo CLI Command**
+
+**Problem Statement:** Add todo management to existing Kiro CLI for task tracking.
+
+**Requirements:**
+- CLI commands for CRUD operations
+- Local SQLite storage
+- Priority and due date support
+
+**Task Breakdown:**
+
+Task 1: Create database schema and models
+- Define Todo struct with required fields
+- Create database migration for todos table
+- Demo: Can create and query todos in database
+
+Task 2: Implement CLI command structure
+- Add todo subcommand with add/list/complete operations
+- Demo: CLI accepts todo commands and shows help
+
+Task 3: Add advanced features
+- Implement due dates and priority sorting
+- Demo: Complete todo system with all features
+
+
+```
+
+Each task includes:
+  * **Clear objectives** - Specific, measurable goals
+  * **Implementation guidance** - General approach and key considerations
+  * **Demo description** - Working functionality that can be demonstrated
+
+
+### 4. Plan approval and handoff[](https://kiro.dev/docs/cli/chat/planning-agent/#4-plan-approval-and-handoff)
+Before switching to execution, the planner seeks your approval.
+bash
+```
+
+[plan] > Does this plan look good, or would you like me to adjust anything?
+
+> The plan looks great! Let's implement it.
+
+*Planning complete!* Ready to exit [plan] agent to start your implementation? [y/n]:
+
+> y
+
+
+```
+
+The handoff process:
+  1. You approve the implementation plan
+  2. Interactive prompt confirms switching to execution
+  3. Automatically transitions back to previous agent
+  4. Complete plan is passed to the execution agent
+
+
+## Read-only design[](https://kiro.dev/docs/cli/chat/planning-agent/#read-only-design)
+The Plan agent operates in read-only mode to keep focus on planning.
+Operation | Status  
+---|---  
+File reading | ✓ Full access to explore codebase  
+Code intelligence | ✓ LSP operations for understanding code structure  
+Search (grep, glob) | ✓ Code exploration  
+Web search | ✓ Documentation and research access  
+File writing | ✗ Cannot create or modify files  
+Command execution | ✗ Limited to read-only bash commands  
+MCP tools | ✗ Cannot use MCP tools  
+## Best practices[](https://kiro.dev/docs/cli/chat/planning-agent/#best-practices)
+  1. **Use for complex tasks** - Most valuable for multi-step implementations
+  2. **Engage with questions** - Answer structured questions thoughtfully
+  3. **Let it explore** - Allow planner to analyze your existing codebase
+  4. **Review plans** - Ensure plan matches expectations before handoff
+  5. **Iterate as needed** - Continue refining until plan is clear
+
+
+## Troubleshooting[](https://kiro.dev/docs/cli/chat/planning-agent/#troubleshooting)
+Issue | Solution  
+---|---  
+How to exit plan agent? | Use `Shift + Tab` to return to your previous agent.  
+Planning session interrupted | Use `/plan` to re-enter planning and continue where you left off.  
+Plan not transferring to execution agent | Make sure to respond "y" when prompted with "Ready to exit [plan] agent to start your implementation? [y/n]".  
+## Example workflow[](https://kiro.dev/docs/cli/chat/planning-agent/#example-workflow)
+bash
+```
+
+> /plan Add user authentication to my web app
+
+[plan] > I understand you want to add user authentication to your web application.
+
+**My Understanding:** You want to implement user authentication functionality
+for an existing web application.
+
+[1]: What authentication method do you prefer?
+a. **Email/Password** - Traditional username and password
+b. **OAuth** - Google, GitHub, or other OAuth providers
+c. **Magic Links** - Passwordless email-based authentication
+d. **Multi-factor** - Combination of methods with 2FA
+
+> 1=a
+
+[plan] > Great! Email/password authentication it is.
+
+[2]: What's your current tech stack?
+a. **React + Node.js** - JavaScript full-stack
+b. **Next.js** - React with server-side rendering
+c. **Django/Flask** - Python web framework
+d. **Other** - Please specify
+
+> 2=d, I'm using Rust with Axum framework
+
+[plan] > Perfect! Rust with Axum is an excellent choice for secure authentication.
+
+*Researching Axum authentication patterns...*
+*Exploring your existing codebase structure...*
+
+**Implementation Plan - User Authentication System**
+[Detailed plan follows...]
+
+Does this plan look good, or would you like me to adjust anything?
+
+> Looks perfect!
+
+Ready to exit [plan] agent to start your implementation? [y/n]: y
+
+[default] > Implement this plan: [Plan content transferred to execution agent]
+
+
+```
+
+Page updated: December 19, 2025
+[Subagents](https://kiro.dev/docs/cli/chat/subagents/)
+[Prompts](https://kiro.dev/docs/cli/chat/manage-prompts/)
+On this page
+  * [Getting started](https://kiro.dev/docs/cli/chat/planning-agent/#getting-started)
+  * [Keyboard shortcut](https://kiro.dev/docs/cli/chat/planning-agent/#keyboard-shortcut)
+  * [Slash command](https://kiro.dev/docs/cli/chat/planning-agent/#slash-command)
+  * [With immediate prompt](https://kiro.dev/docs/cli/chat/planning-agent/#with-immediate-prompt)
+  * [Plan workflow](https://kiro.dev/docs/cli/chat/planning-agent/#plan-workflow)
+  * [1. Requirements gathering](https://kiro.dev/docs/cli/chat/planning-agent/#1-requirements-gathering)
+  * [2. Research and analysis](https://kiro.dev/docs/cli/chat/planning-agent/#2-research-and-analysis)
+  * [3. Implementation plan](https://kiro.dev/docs/cli/chat/planning-agent/#3-implementation-plan)
+  * [4. Plan approval and handoff](https://kiro.dev/docs/cli/chat/planning-agent/#4-plan-approval-and-handoff)
+  * [Read-only design](https://kiro.dev/docs/cli/chat/planning-agent/#read-only-design)
+  * [Best practices](https://kiro.dev/docs/cli/chat/planning-agent/#best-practices)
+  * [Troubleshooting](https://kiro.dev/docs/cli/chat/planning-agent/#troubleshooting)
+  * [Example workflow](https://kiro.dev/docs/cli/chat/planning-agent/#example-workflow)

package/.kiro/documentation/docs_cli_chat_responding.md

@@ -0,0 +1,123 @@
+# Responding to messages
+## Overview[](https://kiro.dev/docs/cli/chat/responding/#overview)
+Kiro CLI provides a convenient way to respond to specific parts of Kiro's previous message through the `/reply` command. It opens an editor with Kiro's last response quoted with > prefixes, allowing you to easily address individual points or provide structured feedback. The command uses your system's default editor, and falls back to `vi` if no editor is configured
+### How it works[](https://kiro.dev/docs/cli/chat/responding/#how-it-works)
+  * **Retrieves last response** : Finds the most recent assistant message from the conversation
+  * **Formats with quotes** : Each line is prefixed with > for clear attribution
+  * **Opens editor** : Your default editor opens with the quoted content
+  * **Edit and respond** : Add your responses below or interspersed with the quoted text
+  * **Submit** : When you save and close the editor, your response is submitted
+
+
+### Editor behavior[](https://kiro.dev/docs/cli/chat/responding/#editor-behavior)
+  * Pre-populated content: Editor opens with Kiro's response already quoted
+  * Quote format: Each line prefixed with > for clear visual distinction
+  * Flexible editing: Add content anywhere - below quotes, between lines, or interspersed
+  * Auto-submission: Content is automatically submitted when editor closes successfully
+
+
+### Use cases[](https://kiro.dev/docs/cli/chat/responding/#use-cases)
+#### Responding to multiple questions[](https://kiro.dev/docs/cli/chat/responding/#responding-to-multiple-questions)
+When Kiro asks several clarifying questions, use `/reply` to address each one:
+```
+
+> What programming language are you using?
+Python
+
+> What framework are you working with?
+Django
+
+> What specific error are you encountering?
+I'm getting a 404 error when trying to access my API endpoints.
+
+
+
+```
+
+#### Addressing specific points[](https://kiro.dev/docs/cli/chat/responding/#addressing-specific-points)
+When Kiro provides a detailed explanation, respond to specific parts:
+```
+
+> Here are three approaches you could take:
+> 1. Use a database migration
+> 2. Update the model directly
+> 3. Create a custom management command
+
+I'd like to go with option 1. Can you show me how to create the migration?
+
+> Make sure to backup your data first.
+Already done - I have a full backup from this morning.
+
+
+```
+
+#### Providing structured feedback[](https://kiro.dev/docs/cli/chat/responding/#providing-structured-feedback)
+When Kiro suggests multiple changes, organize your responses clearly:
+```
+
+> I recommend these improvements:
+> - Add error handling for network requests
+> - Implement input validation
+> - Add logging for debugging
+
+Agreed on all points. For the error handling:
+- Should I use try/catch blocks or a decorator pattern?
+
+For logging:
+- What level of detail do you recommend?
+
+
+```
+
+### Status messages[](https://kiro.dev/docs/cli/chat/responding/#status-messages)
+The command provides clear feedback about its operation:
+  * Success: "Content loaded from editor. Submitting prompt..."
+  * No changes: "No changes made in editor, not submitting."
+  * No message: "No assistant message found to reply to."
+  * Editor error: "Error opening editor: [specific error details]"
+
+
+### Error handling[](https://kiro.dev/docs/cli/chat/responding/#error-handling)
+  * No assistant message: Shows warning if no previous Kiro response is found
+  * Editor failures: Reports editor process failures with specific error details
+  * Empty content: Detects when no changes are made and skips submission
+  * Unchanged content: Compares with initial text to avoid submitting unmodified quotes
+
+
+### Best practices[](https://kiro.dev/docs/cli/chat/responding/#best-practices)
+  * Use `/reply` when Kiro's response contains multiple points that need individual attention
+  * Keep your responses clear and organized when addressing quoted sections
+  * Focus on sections that need clarification rather than responding to every quoted line
+  * Use the quote structure to maintain context in longer conversations
+
+
+**Tip**
+  1. You can delete quote lines you don't need to respond to
+  2. Add blank lines between your responses for better readability
+  3. Use the quoted structure to break down complex topics into manageable parts
+  4. The command works best when Q Developer's previous response was substantial and detailed
+
+
+View related pages
+## Next steps[](https://kiro.dev/docs/cli/chat/responding/#next-steps)
+  * Learn about [Context Management](https://kiro.dev/docs/cli/chat/context) for better responses
+  * Explore [Slash Commands](https://kiro.dev/docs/cli/reference/slash-commands) for quick actions
+  * Check [Conversations](https://kiro.dev/docs/cli/chat/conversations) to save and manage chats
+  * Review [Prompts](https://kiro.dev/docs/cli/chat/manage-prompts) for effective questioning
+
+
+Page updated: November 18, 2025
+[Context management](https://kiro.dev/docs/cli/chat/context/)
+[Permissions](https://kiro.dev/docs/cli/chat/permissions/)
+On this page
+  * [Overview](https://kiro.dev/docs/cli/chat/responding/#overview)
+  * [How it works](https://kiro.dev/docs/cli/chat/responding/#how-it-works)
+  * [Editor behavior](https://kiro.dev/docs/cli/chat/responding/#editor-behavior)
+  * [Use cases](https://kiro.dev/docs/cli/chat/responding/#use-cases)
+  * [Responding to multiple questions](https://kiro.dev/docs/cli/chat/responding/#responding-to-multiple-questions)
+  * [Addressing specific points](https://kiro.dev/docs/cli/chat/responding/#addressing-specific-points)
+  * [Providing structured feedback](https://kiro.dev/docs/cli/chat/responding/#providing-structured-feedback)
+  * [Status messages](https://kiro.dev/docs/cli/chat/responding/#status-messages)
+  * [Error handling](https://kiro.dev/docs/cli/chat/responding/#error-handling)
+  * [Best practices](https://kiro.dev/docs/cli/chat/responding/#best-practices)
+  * [Next steps](https://kiro.dev/docs/cli/chat/responding/#next-steps)

package/.kiro/documentation/docs_cli_chat_security.md

@@ -0,0 +1,87 @@
+# Security considerations
+Kiro provides powerful capabilities that can modify your system and AWS resources. Understanding security implications and following best practices helps you use these capabilities safely.
+## Understanding security risks[](https://kiro.dev/docs/cli/chat/security/#understanding-security-risks)
+When using Kiro, be aware of the following potential security risks:
+  * Unintended system changes: Kiro may interpret your requests in unexpected ways, leading to unintended modifications
+  * AWS resource modifications: Resources could be created, modified, or deleted, potentially affecting production environments or incurring costs
+  * Data loss: Commands that delete or overwrite files could result in data loss
+  * Security vulnerabilities: Commands might compromise system security if not properly reviewed
+
+
+These risks are significantly increased when using /tools trust-all or /acceptall, which bypass confirmation prompts.
+Specific examples of risks include:
+  * A request to "clean up old files" might delete important configuration files
+  * A request to "optimize my EC2 instances" might terminate running instances
+  * A request to "fix security issues" might modify permissions in ways that expose sensitive data
+
+
+**Warning**
+Don't use `/tools trust-all` or `/acceptall` mode in production environments or when working with sensitive data or resources. You are responsible for all actions performed by Kiro.
+## General security best practices[](https://kiro.dev/docs/cli/chat/security/#general-security-best-practices)
+When using Kiro in any environment, especially those with sensitive files, private keys, tokens, or other confidential information, consider implementing these security measures:
+### Restricting file access[](https://kiro.dev/docs/cli/chat/security/#restricting-file-access)
+By default, Kiro can read files without asking for permission each time (Read is trusted by default). For sensitive environments, you can restrict this behavior:
+bash
+```
+
+/tools untrust read
+
+
+```
+
+With this setting, Kiro will ask for your explicit permission before reading any file. This gives you granular control over which files Kiro can access during your session.
+You can also make this setting persistent by adding it to your shell startup script:
+bash
+```
+
+echo 'alias kiro-cli="kiro-cli --untrust-fs-read"' >> ~/.bashrc
+
+
+```
+
+This ensures that every new Kiro session starts with Read untrusted, requiring explicit permission for file access.
+### Additional security measures[](https://kiro.dev/docs/cli/chat/security/#additional-security-measures)
+For environments with highly sensitive information, consider these additional measures:
+  * Use in a dedicated development environment that doesn't contain sensitive credentials or data
+  * Store sensitive files outside your project directories or in locations with restricted permissions
+  * Use environment variables for sensitive values instead of hardcoding them in files
+  * Consider using `/tools untrust aws` to require explicit permission before making AWS API calls
+  * Use steering to define security guidelines and restrictions
+
+
+### Using /tools trust-all safely[](https://kiro.dev/docs/cli/chat/security/#using-tools-trust-all-safely)
+If you must use `/tools trustall` or `/acceptall` for specific workflows, follow these safety practices to minimize risks:
+  * Only use in development or testing environments, never in production
+  * Enable `/tools trust-all` only for specific tasks, then immediately disable it using `/tools reset` to return to default permissions
+  * Back up important data before enabling `/tools trust-all`
+  * Use AWS credentials with minimal permissions when `/tools trust-all` is enabled
+  * Carefully monitor all actions Kiro agent takes while `/tools trust-all` is enabled
+
+
+To return to the default permission settings after using /tools trust-all, use the reset command:
+bash
+```
+
+/tools reset
+
+
+```
+
+This reverts all tools to their default permission levels, with only Read trusted by default.
+## Related documentation[](https://kiro.dev/docs/cli/chat/security/#related-documentation)
+  * [Permissions](https://kiro.dev/docs/cli/chat/permissions) - Managing access controls
+  * [Context Management](https://kiro.dev/docs/cli/chat/context) - Controlling what data is shared
+  * [Authentication](https://kiro.dev/docs/cli/authentication) - Secure login methods
+  * [Privacy and Security](https://kiro.dev/docs/cli/privacy-and-security) - Overall security practices
+
+
+Page updated: November 18, 2025
+[Images](https://kiro.dev/docs/cli/chat/images/)
+[Configuration](https://kiro.dev/docs/cli/chat/configuration/)
+On this page
+  * [Understanding security risks](https://kiro.dev/docs/cli/chat/security/#understanding-security-risks)
+  * [General security best practices](https://kiro.dev/docs/cli/chat/security/#general-security-best-practices)
+  * [Restricting file access](https://kiro.dev/docs/cli/chat/security/#restricting-file-access)
+  * [Additional security measures](https://kiro.dev/docs/cli/chat/security/#additional-security-measures)
+  * [Using /tools trust-all safely](https://kiro.dev/docs/cli/chat/security/#using-tools-trust-all-safely)
+  * [Related documentation](https://kiro.dev/docs/cli/chat/security/#related-documentation)