By deviantony
Browser-based annotation tool that lets you add line-specific feedback to any file
npx claudepluginhub deviantony/claude-plugins --plugin canon
A browser-based annotation tool for Claude Code that lets you add
line-specific feedback to any file, with annotations flowing back
into your conversation as structured context.
AI Manifesto: Vibe-coding
This project is vibe-coded with AI. The associated code has undergone little to no review. It is recommended to fork this project if you would like to see it evolve.
Install the plugin from the claude-plugins marketplace:
claude plugin marketplace add deviantony/claude-plugins
claude plugin install canon@deviantony-plugins
Then in a Claude Code session, run /canon:setup to download the binary for your platform.
Supported platforms: Linux (x64, arm64), macOS (Apple Silicon), Windows (x64)
In a Claude Code session:
/canon:new
A browser window opens automatically at http://localhost:9847. Browse files, click lines to annotate, and submit to return feedback to Claude.
To update Canon, update the marketplace and plugin:
claude plugin marketplace update deviantony-plugins
claude plugin update canon@deviantony-plugins
Then in a Claude Code session, run /canon:setup to update the binary.
Restart Claude Code after updating to ensure changes take effect.
To install the binary to a custom location instead of ~/.local/bin:
export CANON_BIN_DIR=/usr/local/bin
Then run /canon:setup.
If running Claude Code in a container or over SSH:
export CANON_PORT=9000
export CANON_REMOTE=1
claude # then run /canon:new and open the URL manually
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Team-oriented workflow plugin with role agents, 27 specialist agents, ECC-inspired commands, layered rules, and hooks skeleton.
Comprehensive PR review agents specializing in comments, tests, error handling, type design, code quality, and code simplification
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
Comprehensive startup business analysis with market sizing (TAM/SAM/SOM), financial modeling, team planning, and strategic research
Automated code review for pull requests using multiple specialized agents with confidence-based scoring