refactor(plugin): restructure plugin and improve skills to 95%+ #103
Conversation
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
- 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>
RichardHightower
changed the title
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>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary
Major restructure of the Agent Brain plugin to follow Claude Code plugin specification and improve skill grades to 95%+.
Changes
Plugin Structure
marketplace.jsonto project root.claude-plugin/directoryplugin.jsonmanifest inagent-brain-plugin/.claude-plugin/agent-brain-skill/directory (content consolidated into plugin)Skill Improvements
agent-brain-setupskill toconfiguring-agent-brain(action-focused naming)using-agent-brainskill from 82% to 99% grade:configuring-agent-brainskill to 95%+ grade:Command/Agent Updates
configuring-agent-brainsetup-assistantagent skill referenceDocumentation
docs/plans/agent-brain-plugin-cleanup-plan.mdTest plan
marketplace.jsonat project rootplugin.jsonin plugin directory🤖 Generated with Claude Code