/benchmark
Run the Permafrost cache benchmark (offline emulator, no API key)
> /plugin marketplace add jianzhichun/permafrost > /plugin install permafrost@permafrost
How it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/benchmark
Context preview
What this command does when you run it.
Run the Permafrost cache benchmark (offline emulator, no API key)
Command definition
benchmark.mddescription: Run the Permafrost cache benchmark (offline emulator, no API key) argument-hint: "[turns]" allowed-tools: Bash(python3:*)
Run the offline DeepSeek cache benchmark and report the result.
!`python3 "${CLAUDE_PLUGIN_ROOT}/benchmarks/bench.py" --turns ${ARGUMENTS:-12}`
Present the table to the user and call out the headline: in the realistic "both" scenario, how the hit rate and cost change between `off` and `aggressive` mode, and how many anchor resets each mode incurs. Note that this uses a faithful emulator of DeepSeek's prefix cache — to measure the live API instead, add `--real` with a `DEEPSEEK_API_KEY` set.
Freeze Claude Code's prompt prefix so DeepSeek's automatic cache always hits — alignment proxy + coalescing + keepalive, installable as a CC plugin. Measured 64% cheaper on real Claude Code traffic.

