stop
Stop the active ultragoal loop — archive the goal as abandoned (or paused) and release the gate.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Stop the active ultragoal loop — archive the goal as abandoned (or paused) and release the gate.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | stop |
| description | Stop the active ultragoal loop — archive the goal as abandoned (or paused) and release the gate. |
| argument-hint | ["optional reason"] |
The user wants to stop the active goal loop. Reason given (may be empty):
$ARGUMENTS.ultragoal/goals/active/<slug>/goal.md whose session: matches the current session (or the legacy .ultragoal/goals/active.md). If more than one active goal exists across sessions, confirm which one to stop — default to this session's. If none, say so and stop.status: paused, leave the directory in place. The SessionStart banner surfaces it next time the bound session starts.status: abandoned, append the reason and the date to the Decision journal, move goal.md to .ultragoal/goals/archive/<slug>.md, remove the now-empty active/<slug>/ directory, and append a row to .ultragoal/stats.tsv (tab-separated; header date slug kind outcome turns verifier_fails budget if the file is new): date, slug, kind, abandoned, turns used (the goal dir's .turns), FAIL-verdict count in the goal file, budget.failures.md exists so the next attempt doesn't repeat them). If the user agrees, follow the ultragoal:remember protocol.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.
Show the current ultragoal state — active goal, rubric progress, budget, memory health.
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.