Multi-project execution, memory, and collaboration platform for humans and AI agents — REST + 50 MCP tools, Postgres + Memgraph, self-hosted deploy.
Skill Claude CodeCodex
Persist a substantive agent deliverable (audit report, analysis, design note, generated-asset reference, handoff) into RoadBoard as a memory entry via the MCP tools, with a standard envelope. Use whenever you produce an output worth keeping beyond the chat.
Skill Claude CodeCodex
Worker-prompt lifecycle and the Architect/Analyst review gates — prompt frontmatter (status, reviewround, outputstatus), the draft→in-review→approved loop, the append-only review logs, the output gate (review-output → promote), and the tasks/{todo,run,done} transitions. Use when drafting, reviewing, or executing a…
Skill Claude CodeCodex
Git commit format, branch model and safety rules for committing code in a project repo. Use whenever you are about to commit, branch, or run any git command in a cloned project repo.
Skill Claude CodeCodex
Onboard a code project into RoadBoard — analyze the cloned repo and populate RoadBoard (project, phase, tasks, memory and the architecture graph / Atlas) via the RoadBoard MCP tools, then render the per-repo CLAUDE.md. Use when the user asks to onboard a project, or when a project that has a repo is not yet onboarded…
Skill Claude CodeCodex
Navigate and edit code with Serena (LSP-backed semantic tools) instead of grep/ripgrep/Read. Use whenever you need to find a symbol definition, find usages/call sites, understand a file's structure, or make structured code edits in a repo.
Skill Claude CodeCodex
Checklist to close a wave/milestone before marking it complete in RoadBoard — verify prompts done, run the mandatory security review, update changelog/plan, and update the RoadBoard phase via MCP. Use when asked to close or complete a wave/milestone.