on-keyday
UserParallel Claude Code harness — dispatch tasks to multiple agents across repos/hosts, attach interactively, and let agents message each other over a per-task broker. Toy/dogfood scope.
Categories
Indexed Skills (4)
harness-cli
Use when sending messages to other agents on the agentboard or managing topic subscriptions. Reply delivery is asynchronous via the inbox hook — `send` and end the turn; replies arrive on a later turn. Provides reference for the `harness-cli agent` subcommands available inside this task.
implementation-pitfalls
Use BEFORE dispatching implementer/reviewer subagents (superpowers:subagent-driven-development) or BEFORE extending a layer in this repo. Catalog of concrete past failure modes specific to this project — subagent dispatch checklists + sibling-code grep obligations + spec problem-statement enforcement.
landing-to-main
Use when landing / pushing / merging a harness task-branch's work to a repo's trunk, AND at the start of a RESUMED session before new work. Covers both local-trunk-authoritative (FF-mirror) repos and PR-based repos. Universal rule — NEVER cherry-pick to the remote (it manufactures dup-SHA divergence) and rebase the task branch onto the current trunk first. Determine each repo's landing policy once and record it in memory.
independent-review
Use when you want a second opinion that does not inherit your framing — adversarial review of a diff or design, catching plausible-but-wrong work, or questioning whether the whole approach is right. Explains when a built-in subagent suffices vs. when to spawn a truly independent agent. For the harness-cli commands themselves, see the harness-cli skill.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.