rore
UserLocal messaging and searchable session history for coding agents.
Categories
Indexed Skills (6)
agent-workflow
Use when starting, advancing, pausing, or resuming an engineering task. Maintains the Work Record, validates readiness gates between checkpoints, and routes risk classification to agent-redline (bundled, required by default).
agent-redline
Use when setting up agent governance for a repo, or when working in a repo that contains agent-redline-policy.yaml. Classifies structural risk and routes human attention to red-zone changes.
minimap-roadmap
Use when showing or updating roadmap state in a repo with the minimap roadmap convention (board.md, scope.md, features/, ideas/). Not for arbitrary spec review.
pallium-memory
Use Pallium Relay, Session History, or optional derived memory.
execution-loop
Use when tasks need 3+ steps, involve architecture/refactor seams, behavior-parity risk, or bug/test/CI failures. Skip for trivial one-liners, pure Q&A, or when the user explicitly asks to skip planning.
pallium-architect-review
Review and shape Pallium features, plans, implementations, and cross-thread work for product alignment, architectural fit, safety, and proportional design. Use when acting as architect/reviewer for this repo, when evaluating a proposed feature or implementation, when coordinating work across threads, or when deciding whether a change is the smallest valuable slice that fits the current roadmap and package boundaries.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.