Deevs' Agent System enables engineers to create multi-session workflow chains with terminal control and expert agents. It benefits operations teams by automating complex tasks and integrating with Claude Code. The system connects to GitHub for plugin management and supports shell-based workflows.
git clone https://github.com/DeevsDeevs/agent-system.gitDeevs' Agent System is a plugin marketplace for Claude Code that combines workflow chains, terminal control, and specialized expert agents. It allows engineers to maintain context across multiple sessions using the chain-system, invoke developer personas like architects and DevOps specialists for code review and debugging, and deploy hypothesis-driven research agents for financial analysis or systematic bug hunting. The system loads repo-scoped skills from .agents/skills directories and includes Codex multi-agent configurations for orchestrated workflows. Install globally or per-repository with flexible scripting options, supporting selective skill installation for Codex, Claude Code, or both platforms.
Install via Claude Code plugin marketplace or globally with bash installer script. Enable repo-scoped skills by symlinking to .agents/skills, then invoke personas with commands like $dev-experts <persona>, $chain-system link/load, or $bug-hunters <role>. Restart Codex after installation to reload skills.
Resume complex multi-session projects without losing technical context
Perform specialized code review using language-specific expert agents
Systematically hunt and validate bugs with adversarial testing
Orchestrate hypothesis-driven research workflows for financial analysis
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/DeevsDeevs/agent-systemCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
Create a multi-session workflow chain for [COMPANY] in the [INDUSTRY] sector. The workflow should automate [TASK] using terminal control and expert agents. Include steps for integrating with GitHub for plugin management and support shell-based workflows. Provide a detailed step-by-step guide.
# Multi-Session Workflow Chain for Automating Data Backup ## Workflow Overview This workflow automates the backup process for a cloud-based database system, ensuring data integrity and reducing manual intervention. ## Steps 1. **Initialize Workflow**: - Connect to the database server using SSH. - Verify the current database status and disk usage. 2. **Backup Execution**: - Run the backup script located at `/usr/local/bin/backup_script.sh`. - Monitor the backup process in real-time. 3. **Verification**: - Check the backup integrity using the `md5sum` command. - Compare the backup size with the original database size. 4. **GitHub Integration**: - Push the backup log files to the GitHub repository `company-repo/backup-logs`. - Update the README.md with the latest backup details. 5. **Completion**: - Send a notification email to the operations team. - Log the workflow completion time and status.
Cloud ETL platform for non-technical data integration
IronCalc is a spreadsheet engine and ecosystem
Get more done every day with Microsoft Teams – powered by AI
Customer feedback management made simple
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan