メニュー
Keep Claude working across long/autonomous sessions without stopping early due to context budget. Use for long-horizon agent loops, multi-context-window work, or tasks that should run to completion.
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
Make Claude default to implementing changes rather than just suggesting them. Use when the model keeps proposing edits instead of applying them, or when you want a bias toward action in an agentic coding context.
Raise recall in code review — get Claude to report every bug it finds, including low-confidence ones. Use for code review harnesses, security audits, or any workflow where missing a real bug is worse than a few false positives.
Stop Claude from leaving behind temporary scripts, scratch files, and iteration helpers after a task. Use when you want a clean workspace — no extra files beyond the requested deliverables.
Make Claude's responses shorter and more focused. Use when the model is over-explaining, adding non-essential context, or producing verbose answers for simple lookups.
Make Claude ask before taking destructive or hard-to-reverse actions (rm, force-push, dropping tables, posting publicly). Use in autonomous agents that touch shared systems or in any context where the blast radius of a wrong action is high.
Structured, hypothesis-driven research across large corpora. Use for complex research tasks, literature reviews, competitive analysis, or anywhere Claude needs to synthesize information from many sources with tracked confidence.
| name | vojta-persist |
| description | Keep Claude working across long/autonomous sessions without stopping early due to context budget. Use for long-horizon agent loops, multi-context-window work, or tasks that should run to completion. |
Claude 4.5/4.6 have context awareness and may naturally wrap up work as they approach the budget. If your harness compacts or checkpoints, tell the model.
Your context window will be automatically compacted as it approaches its limit, allowing you to continue working indefinitely from where you left off. Therefore, do not stop tasks early due to token budget concerns. As you approach your token budget limit, save your current progress and state to memory before the context window refreshes. Always be as persistent and autonomous as possible and complete tasks fully, even if the end of your budget is approaching. Never artificially stop any task early regardless of the context remaining.
This is a very long task, so it may be beneficial to plan out your work clearly. It's encouraged to spend your entire output context working on the task - just make sure you don't run out of context with significant uncommitted work. Continue working systematically until you have completed this task.
Pair with durable state files so a fresh context can pick up:
tests.json — structured test statusprogress.txt — freeform notesinit.sh — environment setup scriptTell the next context window: pwd; review progress.txt, tests.json, and git log; run the integration test before implementing anything new.