session-health-monitor
por assistantheinrich-prog
Coding Agents & IDEsResumo
Context window health monitoring for OpenClaw agents — threshold warnings via Telegram, pre-compaction snapshots.
Descrição
O que esta skill faz
Monitors context window usage in OpenClaw agent sessions and sends threshold-based warnings via Telegram. When usage is high or compaction is detected, the agent saves key facts and decisions to a daily memory file. Old memory files are archived automatically to prevent directory clutter.
Context compaction is silent by default; this surfaces usage and compaction events in real time and preserves key facts before they disappear from the agent's memory.
Quando usá-la
- Getting Telegram alerts when an agent context window hits 75%
- Saving decisions and changed files before a long session ends
- Detecting when context was silently compacted mid-task
- Auto-archiving old memory snapshots after a configurable number of days
- Tracking compaction count across a multi-hour automation run
Exemplo de fluxo de trabalho
User asks: check session health and send me a Telegram update
- 1
Runs
bash scripts/context-check.sh --jsonto get current usage percentage and compaction count - 2
Evaluates result: 63% used, 1 compaction detected, YELLOW threshold triggered
- 3
Extracts 3-5 key facts from the current session (decisions made, files changed, blockers)
- 4
Runs
bash scripts/snapshot.shto write facts to today's memory file - 5
Appends footer
📊 63% Context Window | 1x compactedto the outgoing Telegram message
Telegram message sent with context health footer; facts saved to memory/YYYY-MM-DD.md
Requisitos
- Telegram bot token (obtained from BotFather)
- Telegram chat ID for the target conversation
Instalação
clawhub install assistantheinrich-prog/session-health-monitorExecute o comando da CLI ou cole o prompt no Claude Code, Cursor, Codex ou no agente de código que você usa.