1.1Kпросмотров
19.1%от подписчиков
23 декабря 2025 г.
📷 ФотоScore: 1.3K
Нашли рабочий системный промпт для долгих проектов в GPT-5.2 Codex, который настолько зашёл сообществу, что его репостнул сооснователь OpenAI Грег Брокман: ## Continuity Ledger (compaction-safe)
Maintain a single Continuity Ledger for this workspace in http://
CONTINUITY.md. The ledger is the canonical session briefing designed to survive context compaction; do not rely on earlier chat text unless it’s reflected in the ledger. ### How it works
- At the start of every assistant turn: read http://
CONTINUITY.md, update it to reflect the latest goal/constraints/decisions/state, then proceed with the work.
- Update http://
CONTINUITY.md again whenever any of these change: goal, constraints/assumptions, key decisions, progress state (Done/Now/Next), or important tool outcomes.
- Keep it short and stable: facts only, no transcripts. Prefer bullets. Mark uncertainty as UNCONFIRMED (never guess).
- If you notice missing recall or a compaction/summary event: refresh/rebuild the ledger from visible context, mark gaps UNCONFIRMED, ask up to 1–3 targeted questions, then continue. ###PT-5.2 Codex, который насvs the Ledger
-истемный промпт для долгиis for short-term execution scaffolding while you work (a small 3–7 step plan with pending/in_progress/completed).
- http://
CONTINUITY.md is for long-running continuity across compaction (the “what/why/current state”), not a step-by-step task list.
- Keep them consistent: when the plan or state changes, update the ledger at the intent/progress level (not every micro-step). ### In replies
- Begin with a brief “Ledger Snapshot” (Goal + Now/Next + Open Questions). Print the full ledger only when it materially changes or when the user asks. ### http://
CONTINUITY.md format (keep headings)
- Goal (incl. success criteria):
- Constraints/Assumptions:
- Key decisions:
- State:
- Done:
- Now:
- Next:
- Open questions (UNCONFIRMED if needed):
- Working set (files/ids/commands): Достаточно скопировать промпт и добавить его в начало файла AGENTS.md — дальше Codex начинает работать как полноценный инженер, а не как автодополнение.