context-budgeting
sarielwang93 द्वारा
Coding Agents & IDEsसंक्षिप्त
Manage and optimize OpenClaw context window usage via partitioning, pre-compression checkpointing, and information.
विवरण
यह स्किल क्या करती है
A framework for managing context window usage in OpenClaw agents. It partitions context into defined zones (goals, history, decisions, background knowledge), checkpoints state before compaction, and runs a cleanup script to recover capacity without restarting the session.
Checkpointing to HOT_MEMORY.md before compaction preserves task state that standard compaction would otherwise discard, allowing the agent to resume accurately.
इसे कब इस्तेमाल करें
- Preventing memory loss during long multi-step coding sessions
- Recovering task state after automatic context compaction
- Reducing token costs on extended agent workflows
- Managing multi-megabyte JSON outputs without flooding the context
- Keeping long-running agents on track past the 80% context threshold
उदाहरण वर्कफ़्लो
User asks: Keep my refactoring task going after the context fills up
- 1
Check current context usage via /status
- 2
Confirm context exceeds 80% threshold
- 3
Update memory/hot/HOT_MEMORY.md with current status, key decisions made, and next step
- 4
Execute scripts/gc_and_checkpoint.sh to clear raw data and finalize compaction
- 5
Resume the task using the checkpoint as the new working context
Task continues from the last checkpoint without losing prior decisions or progress
इंस्टॉलेशन
clawhub install sarielwang93/context-budgetingCLI कमांड चलाएँ, या प्रॉम्प्ट को Claude Code, Cursor, Codex या जो भी कोडिंग एजेंट आप इस्तेमाल करते हैं उसमें पेस्ट करें।