morphaxl
UserTell Claude Code what you want once. It works until the job is verifiably done — and gets smarter every time. Self-correcting goal loops with independent verification and growing memory.
Categories
Indexed Skills (8)
goal
Turn a messy brain dump (raw voice transcript welcome) into a verifiable goal with a checkable rubric, then work autonomously until it is verified and lessons are saved. Use for substantial end-to-end work — build, fix, migrate, investigate — AND for follow-up rounds on a finished or paused goal ("next round", "improve on this"); re-invoke it rather than arming from memory of a previous round.
remember
Distill lessons from the current session or a finished goal into the project memory (.ultragoal/memory/). Used directly, as the final step of a goal loop, and immediately whenever the user corrects you.
stop
Stop the active ultragoal loop — archive the goal as abandoned (or paused) and release the gate.
verify
Independent audit of a goal — the active one or a named archived goal. A fresh-context verifier re-runs every rubric check and tries to refute the work. Use after completion for extra assurance, or anytime you doubt the claims.
ultragoal-goal
Codex-native Ultragoal bridge. Use when the user asks for ultragoal in Codex, a rubric-backed Codex /goal, durable goal execution, evidence-led completion, or to turn a brain dump into Codex native Goal mode. Do not use for trivial one-turn tasks unless explicitly invoked.
compact
Lint and compact the ultragoal project memory — find contradictions and stale claims, merge duplicates, refresh the index. Run every ~10 sessions (the session banner nudges when due).
setup
Initialize or reconfigure ultragoal in this project — scaffold .ultragoal/, choose preference knobs, wire the CLAUDE.md block. Runs automatically on first /ultragoal:goal.
status
Show the current ultragoal state — active goal, rubric progress, budget, memory health.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.