Use this agent when you need to brainstorm software solutions, evaluate architectural approaches, or debate technical decisions before implementation. Examples include adding new features, major refactoring decisions, or complex technical problems requiring multi-approach analysis.
Review code for quality, security, and performance issues. Use after implementing features, before PRs, or for quality audits.
Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise.
Investigate bugs, analyze logs, diagnose performance issues, and trace root causes. Use when something is broken or behaving unexpectedly.
Update project documentation after implementation changes. Analyzes code changes and updates relevant docs. Use after features are implemented.
Answer technical and architectural questions with expert consultation.
Bootstrap new projects with research, tech stack, design, planning, and implementation. Modes: deep (interactive), auto (default), fast (skip research), parallel (multi-agent).
Brainstorm solutions with trade-off analysis, research delegation, and structured debate. Use for ideation, architecture decisions, technical debates, feature exploration, feasibility assessment.
Debug systematically with root cause analysis before fixes. Use for bugs, test failures, unexpected behavior, performance issues.
Search library/framework documentation via llms.txt (context7.com). Use for API docs, technical documentation lookup, latest library features.
Executes bash commands
Hook triggers when Bash tool is used
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
Uses power tools
Uses Bash, Write, or Edit tools
Uses power tools
Uses Bash, Write, or Edit tools
Solon v0.5.0 — A Rust CLI tool and workflow engine for precise, hash-validated file editing with semantic code search, language server protocol support, and full development workflow orchestration across 3 plugins (24 skills).
# Clone and build
git clone https://github.com/yourusername/solon.git
cd solon
cargo install --path .
# Verify installation
sl --version
# Read entire file
sl read src/main.rs
# Read specific lines
sl read src/main.rs --lines 10:20
# Read in chunks (useful for large files)
sl read data.json --chunk-size 50
# Edit by line hash reference
sl edit src/main.rs 5#MQ 10#HW "fn new_function() {}"
# Append content after a line
sl edit src/main.rs 15#AQ "" "println!(\"new line\");" --after
# Delete lines
sl edit src/main.rs 20#XY 25#ZZ --delete
# Read from stdin
echo "new code" | sl edit src/main.rs 5#MQ --stdin
# Search for functions in Rust
sl ast search "fn \$NAME(\$\$\$ARGS)" --lang rust
# Search in specific directory
sl ast search "function \$NAME()" --lang typescript --path src/
# Replace (preview only)
sl ast replace "fn main() {}" "fn main() -> Result<()> {}" --lang rust
# Get diagnostics
sl lsp diagnostics src/main.rs
# Goto definition
sl lsp goto-def src/main.rs 25 10
# Find references
sl lsp references src/main.rs 15 5
# Hover information
sl lsp hover src/main.rs 20 0
# Plan management (via hooks)
sl plan resolve
# Task management (via hooks)
sl task hydrate plans/YYMMDD-my-feature
# Workflow status (via hooks)
sl workflow status plans/YYMMDD-my-feature
Full documentation is available in /docs:
Solon is a Cargo workspace with a unified Rust binary and 3 Claude Code plugins:
Binary (sl): Rust command-line tool with 4 subsystems:
sg binary)Plugins: Three Claude Code plugins registered in marketplace
sg binary (auto-downloaded on first use)Licensed under the Apache License, Version 2.0. See LICENSE file for details.
For issues, questions, or feature requests, please check FAQ & Troubleshooting or open an issue on GitHub.
npx claudepluginhub huynhhoangphuc/solon --plugin solon-coreHashline read/edit, AST-grep, LSP tools for Claude Code
Fast and token-friendly code reading for AI coding agents. Symbol-aware MCP tools that replace cat/grep with ~85% fewer tokens, sub-millisecond search, and a raw fallback that preserves cat/grep parity byte-for-byte.
Structural codebase indexing for efficient navigation. Reduces token consumption by 60-80% through targeted line-range reads instead of full file scans.
AST-aware code search, symbol navigation, and dependency graph analysis
Corca Workflow Framework — consolidated hooks and skill orchestration for structured development sessions
Hand off context to any AI coding agent. Creates comprehensive handoff documents that capture the current task, progress, modified files, and all relevant context needed to seamlessly continue work in any AI assistant (Claude Code, Cursor, Copilot, Aider, etc.).
Semantic code intelligence -- symbol navigation, cross-reference analysis, and structural code understanding powered by tree-sitter