A personal idea for a human agent workflow bundle where human and agents collaborate from the discovery through the implementation
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Research agent for adr-writing. Given a decision topic, returns the next ADR ID, related existing ADRs, and key context from relevant arc42 chapters. Invoke before drafting any ADR.
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Read-only PR review agent. Given a PR number and story/issue ID, reviews the pushed diff against the change's stated intent and the project's own documented conventions (discovered from CLAUDE.md and the docs it points to), applies a security lens when the change touches auth, posts a summary review comment plus…
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Research agent that reads glossary, context files, and relationships for one or more bounded contexts. Used by gherkin-story-authoring and plan-story before writing. Pass the context name(s) as input.
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Research agent for backlog-grooming. Reads the full project state and returns a compact snapshot covering story status by epic, context coverage, unimplemented relationships, and building blocks without stories.
maurizio100/human-agent-workflow-bundle
Agent Claude Code
Research agent for plan-story. Given a story ID, reads all relevant documentation and returns a structured context summary ready for plan writing. Invoke before writing any plan.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: