agent-foreman
Task-driven coding harness with verification and progress tracking
All Skills in This Repository (5)
Pure Emerald Level Indicatorsfeature-run
Automate unattended batch processing of pending tasks with structured result parsing.
feature-next
Orchestrate a four-step feature workflow from next to done.
init-harness
Initialize agent-foreman project scaffolds with TDD mode and task-type scopes.
project-analyze
Generate ARCHITECTURE.md documentation from codebase analysis.
foreman-spec
Coordinate four AI agents to translate requirements into structured task breakdowns.
Frequently Asked Questions
FAQPage SchemaHow to install agent-foreman?▼
Run `npx skills add mylukin/agent-foreman --all -g -y` in your terminal to install all skills in this suite globally.
How to stop AI agents from half-finishing features?▼
agent-foreman forces a strict next, implement, check, done loop where every task must pass verification before it is marked complete.
How does agent-foreman track progress between sessions?▼
It stores tasks as Markdown files with an index and a progress log, so any new session can pick up exactly where the last one stopped.
Does agent-foreman support test-driven development?▼
Yes. You can enable strict TDD mode, which requires failing tests to be written before any implementation code.
Is agent-foreman still maintained?▼
No. The author deprecated it and recommends migrating to the simplified successor project called ralph-dev.
Related Repositories in Software Engineering
View All in Software Engineering→openclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core