dev-toolkit

Sample command demonstrating dev-toolkit command structure

Review test code for resource cleanup, mock hygiene, and best practices in Bun/Node.js projects. Use after writing tests or when debugging flaky tests.

Use this agent when implementing TypeScript code, MCP servers, or plugin features in the SideQuest marketplace. PROACTIVELY launch this agent after planning work that involves writing code, creating new features, fixing bugs, or adding tests. This agent knows core utilities, test patterns, validation tools, and testing best practices. Examples: <example> Context: User asks to implement a new MCP tool for a plugin. user: "Add a new tool to the kit plugin that lists all TypeScript files in a directory" assistant: "I'll use the code-monkey agent to implement this new MCP tool." <commentary> Since the user is asking to implement new TypeScript code for an MCP server, use the Task tool to launch the code-monkey agent which specializes in SideQuest plugin implementation. </commentary> </example> <example> Context: User asks to write tests for existing functionality. user: "Write tests for the spawnAndCollect function in core/spawn" assistant: "Let me launch the code-monkey agent to write those tests following our testing best practices." <commentary> The user is asking to write tests. Use the code-monkey agent which has comprehensive knowledge of testing patterns, mock hygiene, and resource cleanup. </commentary> </example> <example> Context: User has just finished discussing a feature design and is ready to implement. user: "That design looks good, let's build it" assistant: "I'll hand this off to the code-monkey agent to implement the feature we discussed." <commentary> The user has approved a plan and is ready for implementation. Proactively launch the code-monkey agent to write the code. </commentary> </example> <example> Context: User reports a bug that needs fixing. user: "The glob function isn't matching hidden files correctly" assistant: "I'll use the code-monkey agent to explore the issue, write a failing test, and fix the bug." <commentary> Bug fixes involve writing code and tests. Launch the code-monkey agent to follow the TDD approach: explore, write failing test, implement fix, validate. </commentary> </example> <example> Context: After planning phase is complete. assistant: "Here's the plan for implementing the new validation hook: [plan details]" user: "Looks good, go ahead" assistant: "Now I'll use the code-monkey agent to implement this plan." <commentary> After presenting a plan and receiving approval, proactively launch the code-monkey agent to execute the implementation. </commentary> </example>

Build production-grade CLI tools with Bun. Reference implementation covering argument parsing patterns (--flag value, --flag=value, --flag), dual markdown/JSON output, error handling, subcommands, and testing. Use when building CLIs, designing argument parsing, implementing command structures, reviewing CLI quality, or learning Bun CLI best practices.

Pure Bun-native filesystem utilities from @side-quest/core/fs. Use when you need command-injection-safe filesystem operations, prefer Bun over node:fs, or want token-efficient fs helpers. All functions use Bun.spawn, Bun.file(), or Bun.write() - no node:fs dependencies.

Master Bun runtime workflows for full-stack development. Monorepos, bunx, lockfiles, performance optimization, and integration patterns.

Development skills for Bun CLI, runtime workflows, and developer experience patterns

Design developer experiences that people love. Feedback loops, cognitive load, flow state, and ADHD-friendly patterns for tools and workflows.

Expert guidance for building and maintaining the Para Obsidian inbox processing system - a security-hardened automation framework for processing PDFs and attachments with AI-powered metadata extraction. Use when building inbox processors, implementing security patterns (TOCTOU, command injection prevention, atomic writes), designing interactive CLIs with suggestion workflows, integrating LLM detection, implementing idempotency with SHA256 registries, or working with the para-obsidian inbox codebase. Covers engine/interface separation, suggestion-based architecture, confidence scoring, error taxonomy, structured logging, and testing patterns. Useful when user mentions inbox automation, PDF processing, document classification, security-hardened file processing, or interactive CLI design.

Build production-grade MCP (Model Context Protocol) servers with observability, correlation ID tracing, and dual logging. Use when creating new MCP servers, adding tools to existing servers, implementing file logging, debugging MCP issues, wrapping CLI tools with spawnSyncCollect, or following Side Quest marketplace patterns. Covers @side-quest/core/mcp declarative API, @side-quest/core/spawn CLI wrapper patterns, Zod schemas, Bun runtime, and 9 gold standard patterns validated across Kit plugin (18 tools). Includes error handling, response format switching, MCP annotations, and graceful degradation.

Best practices for structured logging, correlation IDs, performance metrics, and debugging in Bun applications using @side-quest/core/logging and LogTape. Use when implementing logging, setting up observability, debugging production issues, tracking performance metrics, adding correlation IDs, configuring subsystem loggers, or working with JSONL log analysis. Covers plugin logger factory, hierarchical categories, log levels, metrics collection, and operational debugging workflows.