context-compactor
by emberdesire
CLI UtilitiesBrief
Token-based context compaction for local models (MLX, llama.cpp, Ollama) that don't report context limits.
Description
What This Skill Does
Client-side token estimation plugin for OpenClaw that proactively summarizes older messages before local models silently truncate or corrupt context. Works with MLX, llama.cpp, and Ollama, which don't report context overflow errors the way cloud APIs do. Configurable thresholds let you tune behavior per model size.
Built-in OpenClaw compaction only triggers when the model reports an overflow error, which local models rarely do, so this plugin catches the problem before it silently corrupts the session.
When to Use It
- Running long coding sessions with an 8K MLX model without losing conversation history
- Debugging why a local model started returning garbled responses mid-session
- Checking token usage before hitting a context limit with /context-stats
- Forcing a fresh summary cache when context feels stale
- Tuning compaction thresholds for a 4K vs 32K local model
Example Workflow
User sends a message in a long session using an MLX 8K model
- 1
before_agent_start hook fires and estimates total context tokens
- 2
Plugin counts ~6,800 tokens against the 8,000 maxTokens threshold
- 3
Splits messages into old (to summarize) and recent (to keep within keepRecentTokens)
- 4
Calls the session model to generate a summary of old messages and caches it
- 5
Injects the summary plus recent messages as the new context before the agent responds
Agent responds normally with full context awareness, without the model ever seeing a truncated or overflowed input
Installation
clawhub install emberdesire/context-compactorRun the CLI command, or paste the prompt into Claude Code, Cursor, Codex or whichever coding agent you use.