Menú
Show the current ultragoal state — active goal, rubric progress, budget, memory health.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Ultragoal for Codex. Use when the user asks for ultragoal in Codex, a hook-backed or runner-backed Codex goal loop, a rubric-backed Codex /goal, durable goal execution, evidence-led completion, panel verification, or to turn a brain dump into a Codex-native goal. Do not use for trivial one-turn tasks unless explicitly invoked.
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. NOT for small contained tasks (a quick fix, a question, a tweak) — those are ordinary conversation, and a goal having run earlier in the session never makes later small asks goal work.
Initialize or reconfigure ultragoal in this project — scaffold .ultragoal/, choose preference knobs, wire the CLAUDE.md block. Runs automatically on first /ultragoal:goal.
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 the active ultragoal loop — archive the goal as abandoned (or paused) and release the gate.
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.
| name | status |
| description | Show the current ultragoal state — active goal, rubric progress, budget, memory health. |
Report the current ultragoal state for this project. Current data:
Active goals (one directory per goal; each shows its bound session):
out="$({ find "${CLAUDE_PROJECT_DIR:-.}/.ultragoal/goals/active" -maxdepth 2 -name goal.md 2>/dev/null; ls "${CLAUDE_PROJECT_DIR:-.}/.ultragoal/goals/active.md" 2>/dev/null; } | while read -r g; do echo "── $g"; grep -E '^(slug|status|kind|session|budget):' "$g"; t="$(dirname "$g")/.turns"; echo "turns: $(cat "$t" 2>/dev/null || echo 0)"; done)"; printf '%s\n' "${out:-(no active goals)}"
Sessions since last memory compaction: !cat "${CLAUDE_PROJECT_DIR:-.}/.ultragoal/memory/.sessions" 2>/dev/null || echo 0 · Archived goals: !ls "${CLAUDE_PROJECT_DIR:-.}/.ultragoal/goals/archive/" 2>/dev/null | wc -l | tr -d ' '
Goal history (stats.tsv, most recent last):
tail -10 "${CLAUDE_PROJECT_DIR:-.}/.ultragoal/stats.tsv" 2>/dev/null || echo "(no completed goals yet)"
Summarize for the user, leading with what matters. Note which goal (if any) belongs to THIS session — that's the one the gate is driving here; others run in their own sessions.
/ultragoal:stop.status: active resumes it./ultragoal:goal <brief> starts one.End with one dim line: preferences live in .ultragoal/config.md (hand-edit anytime) — re-run /ultragoal:setup to change them interactively.
Keep it short. Do not start working on the goal from this skill — it is a dashboard, not a trigger.