Stats
Actions
Tags
From harness-engineering
Directory of specialized subagents for code analysis, development, refactoring, documentation generation, research, security audits, and performance optimization. Invoke @README to delegate category-specific tasks.
How this agent operates — its isolation, permissions, and tool access model
Agent reference
harness-engineering:agents/readmeThe summary Claude sees when deciding whether to delegate to this agent
This directory contains specialized AI agents organized by category. ``` agents/ ├── analysis/ # Code analysis and investigation agents ├── development/ # Code development and refactoring agents ├── documentation/ # Documentation generation agents ├── research/ # Research and information gathering agents ├── security/ # Security ana...
This directory contains specialized AI agents organized by category.
agents/
├── analysis/ # Code analysis and investigation agents
├── development/ # Code development and refactoring agents
├── documentation/ # Documentation generation agents
├── research/ # Research and information gathering agents
├── security/ # Security analysis agents
├── performance/ # Performance optimization agents
├── README.md # This file
└── guide.md # Comprehensive subagent guide
Agents for analyzing and understanding code:
codebase-locator.md - Find WHERE code lives in a codebasecodebase-analyzer.md - Understand HOW code workscode-synthesis-analyzer.md - Analyze recently implemented code changesAgents for code development tasks:
tdd-python.md - Test-Driven Development for Pythoncode-clarity-refactorer.md - Apply refactoring rules for claritybug-issue-creator.md - Analyze bugs and create GitHub issuesAgents for documentation tasks:
git-diff-documentation-agent.md - Document changes from git diffstech-docs-maintainer.md - Maintain technical documentationtechnical-docs-orchestrator.md - Multi-stage documentation creationprompt-engineer.md - Optimize and improve promptsAgents for research tasks:
web-docs-researcher.md - Search web for official documentationmulti-agent-synthesis-orchestrator.md - Orchestrate multiple research agentsAgents for security analysis:
security-orchestrator.md - Comprehensive security investigationsAgents for performance optimization:
memory-profiler.md - Identify memory leaks and optimization opportunitiesSee guide.md for detailed information about creating, configuring, and using subagents effectively.
npx claudepluginhub alchemiststudiosdotai/harness-engineeringMaintains technical documentation in @documentation (general) and .claude (dev/agent) directories. Audits codebase gaps with grep/gh CLI, updates after code/agent changes.
Creates, improves, and analyzes Claude Code agents following Anthropic best practices. Delegate for explicit requests like 'create agent', 'new agent', 'improve agent', 'fix agent trigger', or 'agent doesn't trigger'.
Audits code for bugs, security vulnerabilities, performance issues, best practices, and maintainability. Delegate comprehensive code reviews, issue detection, and refactoring suggestions.