prikotov/task-agents-playbook
AI-Assisted Development Playbook & Task-driven development methodology for AI-agents.
Implements a structured task-driven development methodology where standardized task templates serve as executable specifications for LLM agents, enforced through a central `AGENTS.md` constitution file. The system uses file-based task management in a `todo/` directory and role-based prompting—agents assume specialized personas (backend developer, DevOps engineer, code reviewer, etc.) with domain-specific instructions to guide autonomous development cycles. Integrates with CLI tools like Codex CLI and Kilo Code, automating self-validation loops through integrated test suites, static analysis (PHPMD, Deptrac, Psalm), and linting tools to ensure code quality before human review.
Stars
12
Forks
3
Language
PHP
License
MIT
Category
Last pushed
Feb 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/prikotov/task-agents-playbook"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
playbooks-ai/playbooks
▶📚 Playbooks is a semantic programming system for AI agents
JohnCrickett/ai-assisted-engineering
A Guide To AI-Assisted Software Engineering
lee-to/ai-factory
You want to build with AI, but setting up the right context, prompts, and workflows takes time....
InteractiveAgents/IAW
IAW is an Orleans-based multi-agent runtime for .NET. Build intelligent agents that collaborate,...
DUBSOpenHub/dark-factory
🏭 Agentic dark factory for AI building with sealed-envelope testing