All notable changes to Agent OS will be documented in this file.
The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.
Fixed bugs in the project installation scripts (project-install.sh, project-update.sh, and common-functions.sh) that caused installations to fail in certain bash environments. These issues were triggered by stricter bash implementations and configurations, particularly when set -e (exit on error) was enabled.
Agent OS 2.0 is a major new release that brings several core architectural changes and improvements.
The big headline here is the dual mode architecture for supporting both multi-agent tools (Claude Code) and single-agent tools (every other tool).
this page documents:
- The new features in Agent OS 2.0
- Architectural changes in 2.0
- What changed from 1.x
- Updating guide
The Agent OS docs also received a complete overhaul and expansion. It's now broken out into multiple pages that document every detail of how to install, use and customize Agent OS.
1.4.2 - 2025-08-24
- Updated
instructions/core/execute-tasks.mdto strictly require all three phases (pre-execution, execution loop, post-execution) and to invokeinstructions/core/post-execution-tasks.mdafter task completion.
- Renamed
instructions/core/complete-tasks.mdtoinstructions/core/post-execution-tasks.md. - Improved the post-execution workflow by adding clarity and removing bloat in instructions.
1.4.1 - 2025-08-18
Earlier versions added a decisions.md inside a project's .agent-os/product/. In practice, this was rarely used and didn't help future development.
It's been replaced with a new system for creating "Recaps"—short summaries of what was built—after every feature spec's implementation has been completed. Similar to a changelog, but more descriptive and context-focused. These recaps are easy to reference by both humans and AI agents.
Recaps are automatically generated via the new complete-tasks.md process.
A goal of this update was to tighten up the processes for creating specs and executing tasks, ensuring these processes are executed reliably. Sounds like the job for a "project manager".
This update introduces a new subagent (for Claude Code) called project-manager which handles all task completion, status updates, and reporting progress back to you.
Several changes to the instructions, processes, and executions, all aimed at helping agents follow the process steps consistently.
- Consolidated task execution instructions with clear step-by-step processes
- Added post-flight verification rules to ensure instruction compliance
- Improved subagent delegation tracking and reporting
- Standardized test suite verification and git workflow integration
- Enhanced task completion criteria validation and status management
1.4.0 - 2025-08-17
BIG updates in this one! Thanks for all the feedback, requests and support 🙏
The way Agent OS gets installed is structured differently from prior versions. The new system works as follows:
There are 2 installation processes:
- Your "Base installation" (now optional, but still recommended!)
- Your "Project installation"
"Base installation"
- Installs all of the Agent OS files to a location of your choosing on your system where they can be customized (especially your standards) and maintained.
- Project installations copy files from your base installation, so they can be customized and self-contained within each individual project.
- Your base installation now has a config.yml
To install the Agent OS base installation,
-
cd to a location of your choice (your system's home folder is a good choice).
-
Run one of these commands:
- Agent OS with Claude Code support:
curl -sSL https://raw.githubusercontent.com/buildermethods/agent-os/main/setup/base.sh | bash -s -- --claude-code - Agent OS with Cursor support:
curl -sSL https://raw.githubusercontent.com/buildermethods/agent-os/main/setup/base.sh | bash -s -- --cursor - Agent OS with Claude Code & Cursor support:
curl -sSL https://raw.githubusercontent.com/buildermethods/agent-os/main/setup/base.sh | bash -s -- --claude-code --cursor
- Customize your /standards (just like earlier versions)
Project installation
- Now each project codebase gets it's own self-contained installation of Agent OS. It no longer references instructions or standards that reside elsewhere on your system. These all get installed directly into your project's .agent-os folder, which brings several benefits:
- No external references = more reliable Agent OS commands & workflows.
- You can commit your instructions, standards, Claude Code commands and agents to your project's github repo for team access.
- You can customize standards differently per project than what's in your base installation.
Your project installation command will be based on where you installed the Agent OS base installation.
- If you've installed it to your system's home folder, then your project installation command will be
~/.agent-os/setup/project.sh. - If you've installed it elsewhere, your command will be
/path/to/agent-os/setup/project.sh(after your base installation, it will show you your project installation command. It's a good idea to save it or make an alias if you work on many projects.)
If (for whatever reason) you didn't install the base installation, you can still install Agent OS directly into a project, by pulling it directly off of the public github repo using the following command.
- Note: This means your standards folder won't inherit your defaults from a base installation. You'd need to customize the files in the standards folder for this project.
curl -sSL https://raw.githubusercontent.com/buildermethods/agent-os/main/setup/project.sh | bash -s -- --no-base --claude-code --cursor
When you install the Agent OS base installation, that now includes a config.yml file. Currently this file is used for:
- Tracking the Agent OS version you have installed
- Which coding agents (Claude Code, Cursor) you're using
- Project Types (new! read on...)
If you work on different types of projects, you can define different sets of standards, code style, and instructions for each!
- By default, a new installation of Agent OS into a project will copy its instructions and standards from your base installation's /instructions and /standards.
- You can define additional project types by doing the following:
- Setup a folder (typically inside your base installation's .agent-os folder, but it can be anywhere on your system) which contains /instructions and /standards folders (copy these from your base install, then customize).
- Define the project type's folder location on your system in your base install's config.yml
- Using project types:
- If you've named a project type, 'ruby-on-rails', when running your project install command, add the flag --project-type=ruby-on-rails.
- To make a project type your default for new projects, set it's name as the value for default_project_type in config.yml
This update does away with the old installation script files:
- setup.sh (replaced by /setup/base.sh and /setup/project.sh)
- setup-claude-code.sh (now you add --claude-code flag to the install commands or enable it in your Agent OS config.yml)
- setup-cursor.sh (now you add --cursor flag to the install commands or enable it in your Agent OS config.yml)
Claude Code Agent OS commands now should not be installed in the ~/.agent-os/.claude/commands folder. Now, these are copied from ~/.agent-os/commands into each project's ~/.claude/commands folder (this prevents duplicate commands showing in in Claude Code's commands list). The same approach applies to Claude Code subagents files.
Follow these steps to update a previous version to 1.4.0:
-
If you've customized any files in /instructions, back those up now. They will be overwritten.
-
Navigate to your home directory (or whichever location you want to have your Agent OS base installation)
-
Run the following to command, which includes flags to overwrite your /instructions (remove the --cursor flag if not using Cursor):
curl -sSL https://raw.githubusercontent.com/buildermethods/agent-os/main/setup/base.sh | bash -s -- --overwrite-instructions --claude-code --cursor -
If your ~/.claude/commands contain Agent OS commands, remove those and copy the versions that are now in your base installation's commands folder into your project's
.claude/commandsfolder. -
Navigate to your project. Run your project installation command to install Agent OS instructions and standards into your project's installation. If your Agent OS base installation is in your system's home folder (like previous versions), then your project installation will be:
~/.agent-os/setup/project.sh
1.3.1 - 2025-08-02
- Date-Checker Subagent - New specialized Claude Code subagent for accurate date determination using file system timestamps
- Uses temporary file creation to extract current date in YYYY-MM-DD format
- Includes context checking to avoid duplication
- Provides clear validation and error handling
- Create-Spec Instructions - Updated
instructions/core/create-spec.mdto use the new date-checker subagent- Replaced complex inline date determination logic with simple subagent delegation
- Simplified step 4 (date_determination) by removing 45 lines of validation and fallback code
- Cleaner instruction flow with specialized agent handling date logic
- Code Maintainability - Date determination logic centralized in reusable subagent
- Instruction Clarity - Simplified create-spec workflow with cleaner delegation pattern
- Error Handling - More robust date determination with dedicated validation rules
1.3.0 - 2025-08-01
- Pre-flight Check System - New
meta/pre-flight.mdinstruction for centralized agent detection and initialization - Proactive Agent Usage - Updated agent descriptions to encourage proactive use when appropriate
- Structured Instruction Organization - New folder structure with
core/andmeta/subdirectories
- Instruction File Structure - Reorganized all instruction files into subdirectories:
- Core instructions moved to
instructions/core/(plan-product, create-spec, execute-tasks, execute-task, analyze-product) - Meta instructions in
instructions/meta/(pre-flight, more to come)
- Core instructions moved to
- Simplified XML Metadata - Removed verbose
<ai_meta>and<step_metadata>blocks for cleaner, more readable instructions - Subagent Integration - Replaced manual agent detection with centralized pre-flight check across all instruction files to enforce delegation and preserve main agent's context.
- Step Definitions - Added
subagentattribute to steps for clearer delegation of work to help enforce delegation and preserve main agent's context. - Setup Script - Updated to create subdirectories and download files to new locations
- Code Clarity - Removed redundant XML instructions in favor of descriptive step purposes
- Agent Efficiency - Centralized agent detection reduces repeated checks throughout workflows
- Maintainability - Cleaner instruction format with less XML boilerplate
- User Experience - Clearer indication of when specialized agents will be used proactively
- CLAUDE.md - Removed deprecated Claude Code configuration file (functionality moved to pre-flight system, preventing over-reading instructions into context)
- Redundant Instructions - Eliminated verbose ACTION/MODIFY/VERIFY instruction blocks
1.2.0 - 2025-07-29
- Claude Code Specialized Subagents - New agents to offload specific tasks for improved efficiency:
test-runner.md- Handles test execution and failure analysis with minimal toolsetcontext-fetcher.md- Retrieves information from files while checking context to avoid duplicationgit-workflow.md- Manages git operations, branches, commits, and PR creationfile-creator.md- Creates files, directories, and applies consistent templates
- Agent Detection Pattern - Single check at process start with boolean flags for efficiency
- Subagent Integration across all instruction files with automatic fallback for non-Claude Code users
- Instruction Files - All updated to support conditional agent usage:
execute-tasks.md- Uses git-workflow (branch management, PR creation), test-runner (full suite), and context-fetcher (loading lite files)execute-task.md- Uses context-fetcher (best practices, code style) and test-runner (task-specific tests)plan-product.md- Uses file-creator (directory creation) and context-fetcher (tech stack defaults)create-spec.md- Uses file-creator (spec folder) and context-fetcher (mission/roadmap checks)
- Standards Files - Updated for conditional agent usage:
code-style.md- Uses context-fetcher for loading language-specific style guides
- Setup Scripts - Enhanced to install Claude Code agents:
setup-claude-code.sh- Downloads all agents to~/.claude/agents/directory
- Context Efficiency - Specialized agents use minimal context for their specific tasks
- Code Organization - Complex operations delegated to focused agents with clear responsibilities
- Error Handling - Agents provide targeted error analysis and recovery strategies
- Maintainability - Cleaner main agent code with operations abstracted to subagents
- Performance - Reduced context checks through one-time agent detection pattern
- Each agent uses only necessary tools (e.g., test-runner uses only Bash, Read, Grep, Glob)
- Automatic fallback ensures compatibility for users without Claude Code
- Consistent
IF has_[agent_name]:pattern reduces code complexity - All agents follow Agent OS conventions (branch naming, commit messages, file templates)
1.1.0 - 2025-07-29
- New
mission-lite.mdfile generation in product initialization for efficient AI context usage - New
spec-lite.mdfile generation in spec creation for condensed spec summaries - New
execute-task.mdinstruction file for individual task execution with TDD workflow - Task execution loop in
execute-tasks.mdthat callsexecute-task.mdfor each parent task - Language-specific code style guides:
standards/code-style/css-style.mdfor CSS and TailwindCSSstandards/code-style/html-style.mdfor HTML markupstandards/code-style/javascript-style.mdfor JavaScript
- Conditional loading blocks in
best-practices.mdandcode-style.mdto prevent duplicate context loading - Context-aware file loading throughout all instruction files
- Optimized
plan-product.mdto generate condensed versions of documents - Enhanced
create-spec.mdwith conditional context loading for mission-lite and tech-stack files - Simplified technical specification structure by removing multiple approach options
- Made external dependencies section conditional in technical specifications
- Updated
execute-tasks.mdto use minimal context loading strategy - Improved
execute-task.mdwith selective reading of relevant documentation sections - Modified roadmap progress check to be conditional and context-aware
- Updated decision documentation to avoid loading decisions.md and use conditional checks
- Restructured task execution to follow typical TDD pattern (tests first, implementation, verification)
- Context efficiency by 60-80% through conditional loading and lite file versions
- Reduced duplication when files are referenced multiple times in a workflow
- Clearer separation between task-specific and full test suite execution
- More intelligent file loading that checks current context before reading
- Better organization of code style rules with language-specific files
- Duplicate content loading when instruction files are called in loops
- Unnecessary loading of full documentation files when condensed versions suffice
- Redundant test suite runs between individual task execution and overall workflow
1.0.0 - 2025-07-21
- Initial release of Agent OS framework
- Core instruction files:
plan-product.mdfor product initializationcreate-spec.mdfor feature specificationexecute-tasks.mdfor task executionanalyze-product.mdfor existing codebase analysis
- Standard files:
tech-stack.mdfor technology choicescode-style.mdfor formatting rulesbest-practices.mdfor development guidelines
- Product documentation structure:
mission.mdfor product visionroadmap.mdfor development phasesdecisions.mdfor decision loggingtech-stack.mdfor technical architecture
- Setup scripts for easy installation
- Integration with AI coding assistants (Claude Code, Cursor)
- Task management with TDD workflow
- Spec creation and organization system