Skip to content

Conversation

@RichardHightower
Copy link
Contributor

Summary

This PR makes the Claude Code plugin the primary interface for Agent Brain across all documentation and updates model references to 2026 versions.

Documentation Overhaul

  • README.md: Complete rewrite with plugin-first approach - plugin installation and /agent-brain-setup as the primary getting started path
  • QUICK_START.md: Step-by-step guide using plugin commands (install → configure → init → start → index → search)
  • USER_GUIDE.md: Reorganized around plugin features (24 commands, 3 agents, 2 skills)
  • PLUGIN_GUIDE.md: Complete reference for all plugin components

Plugin Restructure

  • Restructured plugin directory with skills, commands, and agents
  • Improved skills to 95%+ grade using improving-skills rubric
  • Updated marketplace.json with correct paths

Model Updates (2026 versions)

  • Claude: claude-haiku-4-5-20251001, claude-sonnet-4-5-20250514
  • OpenAI: gpt-5, gpt-5-mini
  • Gemini: gemini-3-flash, gemini-3-pro
  • Grok: grok-4, grok-4-fast
  • Ollama: llama4:scout, mistral-small3.2, qwen3-coder

Wiki Sync

  • Synced 96 pages to GitHub Wiki including all commands, agents, and feature specs

Test plan

  • Verify plugin installation works: claude plugins install github:SpillwaveSolutions/agent-brain
  • Verify /agent-brain-setup wizard functions correctly
  • Verify all 24 slash commands are documented and accessible
  • Verify GitHub Wiki pages are accessible and properly linked

🤖 Generated with Claude Code

RichardHightower and others added 8 commits February 2, 2026 13:59
- Add current version reference (v2.0.0)
- Add package installation instructions (basic and with extras)
- Add quick start guide for using Agent Brain after install
- Update version examples to use 2.0.0
- Add pluggable providers to release notes template

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Move marketplace.json to project root .claude-plugin/
- Create plugin.json manifest in agent-brain-plugin/.claude-plugin/
- Rename agent-brain-setup skill to configuring-agent-brain
- Delete deprecated agent-brain-skill/ directory
- Move query_domain.py script to plugin before deletion
- Update all command and agent skill references
- Improve using-agent-brain skill from 82% to 99%:
  - Move license to top-level frontmatter
  - Add progress checklist for feedback loops
  - Streamline configuration reference section
- Improve configuring-agent-brain skill to 95%+:
  - Move license to top-level frontmatter
  - Add comprehensive trigger phrases
  - Add counter-examples and validation steps
- Add implementation plan to docs/plans/

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all model references to latest 2026 versions:

Anthropic:
- claude-3-5-haiku-20241022 → claude-haiku-4-5-20251001
- claude-sonnet-4 → claude-sonnet-4-5-20250514
- claude-opus-4 → claude-opus-4-5-20251101

OpenAI:
- gpt-4o → gpt-5
- gpt-4o-mini → gpt-5-mini

Google:
- gemini-1.5-flash → gemini-3-flash
- gemini-1.5-pro → gemini-3-pro

xAI:
- grok-beta → grok-4
- Added grok-4-fast variant

Ollama (local models):
- llama3.2 → llama4:scout
- llama3.1 → llama4:scout
- mistral → mistral-small3.2
- codellama → qwen3-coder
- Added gemma3 and deepseek-coder-v3

Updated files:
- Server provider implementations and config
- Plugin skills and commands documentation
- Test files with updated model assertions
- config.yaml.example
- Product roadmap

Sources:
- xAI Models and Pricing: https://docs.x.ai/docs/models

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Update all model references in .speckit/features/ to use current 2026 models:
- Claude: claude-haiku-4-5-20251001, claude-sonnet-4-5-20250514, claude-opus-4-5-20251101
- OpenAI: gpt-5, gpt-5-mini (from gpt-4o/gpt-4o-mini)
- Gemini: gemini-3-flash, gemini-3-pro (from gemini-1.5-*)
- Grok: grok-4, grok-4-fast (from grok-beta)
- Ollama: llama4:scout, mistral-small3.2, qwen3-coder, gemma3 (from llama3.2)

Files updated:
- 103-pluggable-providers/spec.md
- 103-pluggable-providers/quickstart.md
- 103-pluggable-providers/research.md
- 103-pluggable-providers/data-model.md
- 106-vertex-ai/spec.md

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- README.md: Rewrite with plugin-first approach, plugin as primary interface
- QUICK_START.md: Step-by-step plugin installation and setup guide
- USER_GUIDE.md: Plugin commands, agents, skills as primary interface
- PLUGIN_GUIDE.md: Complete reference for all 24 commands, 3 agents, 2 skills

The Claude Code plugin is now the recommended way to use Agent Brain.
CLI documentation moved to reference sections for advanced users.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Update hardcoded version in server source code (api/main.py, models/health.py)
- Update version assertions in server tests
- Update version assertions in CLI tests

All tests now pass with version 2.0.0.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
@RichardHightower RichardHightower merged commit 44cc8f1 into main Feb 2, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants