Uh oh!
There was an error while loading. Please reload this page.
Amplifier CLI - #17
Closed
Marc Goodner (robotdad) wants to merge 10 commits into
Closed
Conversation
Major features: - Complete CLI implementation with init, install, list, remove, update, config, and worktree commands - GitHub resource management from microsoft/amplifier repository - Git worktree support for parallel development branches - Rich terminal output with progress indicators Key improvements: - Fixed worktree creation on repos with no commits (uses --allow-empty) - Added raw.githubusercontent.com support to avoid GitHub API rate limits - Simplified network layer removing unnecessary complexity - Simplified decorator abstractions for cleaner code - Added UTF-8 encoding to all file operations for cross-platform support Architecture: - Resources always go to .claude/ directory (never .amplifier/resources/) - Metadata and manifests in .amplifier/ - Modular design with clear separation of concerns - Extensive test suite included This implementation follows the project's ruthless simplicity philosophy while providing a robust CLI for managing Amplifier resources. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Add --merge flag to intelligently merge Amplifier content into existing files - Fix initialization check to use manifest.json instead of .claude/ directory - Report skipped files and suggest --merge when files exist - Prevent duplicate content when merging multiple times - Support merging for CLAUDE.md, AGENTS.md, and other root files This allows projects with existing Claude Code assets to adopt Amplifier without overwriting their custom configurations. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Fix executable permissions for .claude/tools files - Copy actual files from repo instead of creating templates - Remove duplicated amplifier/data directory to prevent drift - Ensure settings.json gets full hooks configuration - Update tests to match new implementation Files in .claude/tools/ now automatically get executable permissions, and the init command uses files directly from the repository rather than maintaining duplicate copies that could drift out of sync. 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Included both pydantic (>=2.0.0) and pydantic-ai (>=1.0.10) dependencies - Regenerated uv.lock with updated dependencies - Brought in all upstream changes from main branch
Marc Goodner (robotdad)force-pushed
the
cli-v3
branch
from
September 23, 2025 16:56
08fc23f to
38e3632Compare- Copy actual .mcp.json config instead of creating stub during init - Fix on_code_change_hook.sh to work properly in other repos - Removed amplifier-specific logic that caused errors - Exit gracefully when no project root or Makefile found - Simplified directory detection to be more generic 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
- Create .ai/ directory for AI context and documentation - Create .data/ directory with subdirectories for application data: - cache, indexes, knowledge, memories, state, transcripts, subagents-logs - Create .vscode/ directory (empty for user customization) - Update repair mode to check and create these directories - Update success message to reflect new directory structure 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
Michael J. Jabbour (michaeljabbour) added a commit
to michaeljabbour/amplifier
that referenced
this pull request
Sep 30, 2025
Complete comprehensive technical specification library with all 44 principles: **People (6 specs)** - #1 Small AI-first working groups - #2 Strategic human touchpoints only - #3 Prompt engineering as core skill - microsoft#4 Test-based verification over code review - microsoft#5 Conversation-driven development - microsoft#6 Human escape hatches always available **Process (13 specs)** - microsoft#7 Regenerate, don't edit - microsoft#8 Contract-first everything - microsoft#9 Tests as the quality gate - microsoft#10 Git as safety net - microsoft#11 Continuous validation with fast feedback - microsoft#12 Incremental processing as default - microsoft#13 Parallel exploration by default - microsoft#14 Context management as discipline - microsoft#15 Git-based everything - microsoft#16 Docs define, not describe - microsoft#17 Prompt versioning and testing - microsoft#18 Contract evolution with migration paths - microsoft#19 Cost and token budgeting **Technology (18 specs)** - microsoft#20 Self-modifying AI-first codebase - microsoft#21 Limited and domain-specific by design - microsoft#22 Layered virtualization - microsoft#23 Protected self-healing kernel - microsoft#24 Long-running agent processes - microsoft#25 Simple interfaces by design - microsoft#26 Stateless by default - microsoft#27 Disposable components everywhere - microsoft#28 CLI-first design - microsoft#29 Tool ecosystems as extensions - microsoft#30 Observability baked in - microsoft#31 Idempotency by design (reference) - microsoft#32 Error recovery patterns built in - microsoft#33 Graceful degradation by design - microsoft#34 Feature flags as deployment strategy - microsoft#35 Least-privilege automation - microsoft#36 Dependency pinning and security scanning - microsoft#37 Declarative over imperative **Governance (7 specs)** - microsoft#38 Access control and compliance - microsoft#39 Metrics and evaluation everywhere - microsoft#40 Knowledge stewardship and institutional memory - microsoft#41 Adaptive sandboxing with explicit approvals - microsoft#42 Data governance and privacy controls - microsoft#43 Model lifecycle management - microsoft#44 Self-serve recovery with known-good snapshots Each specification includes: - Plain-language definition - AI-first development rationale - 4-6 implementation approaches - 5 good/bad example pairs with working code - 6 related principles with relationships - 7 common pitfalls with examples - Tools organized by category - 12 actionable checklist items Statistics: - 44 specifications totaling ~10,000+ lines - 220+ good/bad code example pairs - 240+ implementation approaches - 300+ documented anti-patterns - 500+ tools and frameworks - 250+ cross-principle relationships Created through parallel AI agent execution demonstrating Principle microsoft#13 (Parallel Exploration by Default). 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
Marc Goodner (robotdad)
commented
Oct 1, 2025
MemberAuthor
This is obsolete from more recent developements. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Iniital PR for discussion. There are some outstanding issues, in particular making sure the proper content of the root files for agents and claude md are used what is there now is too basic. The .ai folder may also need to be included. I also just realized the knowledge commands were fogotten... d'oh!
Amplifier CLI provides development tools and resource management for AI-assisted projects.
Install specialized agents, tools, and commands to enhance your development workflow.
Installation
uvx --from git+https://github.com/microsoft/amplifier.git amplifierFeatures
Commands
amplifier initInitialize Amplifier in your project.
amplifier installInstall resources (agents, tools, commands, MCP servers).
amplifier listList available and installed resources.
amplifier removeRemove installed resources.
amplifier updateUpdate installed resources.
amplifier worktreeManage git worktrees for parallel development.