Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add jianzhichun/permafrost/plugin install permafrostWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/jianzhichun/permafrost/benchmark)<a href="https://agentmods.dev/commands/jianzhichun/permafrost/benchmark"><img src="https://agentmods.dev/badge/commands/jianzhichun/permafrost/benchmark.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00015 | $0.00161 |
| Opus 5 | $0.00008 | $0.00081 |
| Sonnet 5 | $0.00003 | $0.00032 |
| Haiku 4.5 | $0.00002 | $0.00016 |
Grade A, and why
benchmark scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the offline DeepSeek cache benchmark and report the result.
!python3 "${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.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 12 lines · 15 tokens per session scan A ae49ba9f3976
benchmark is a command published in the GitHub repository jianzhichun/permafrost (21 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 161 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
help
Quick reference for all Attune commands.
spec
Spec-driven development — brainstorm, plan, review, and execute with quality gates and approval.
kill
Stop a running cli-dispatch worker session.
OPSX: Explore
Enter explore mode - think through ideas, investigate problems, clarify requirements.
OPSX: Archive
Archive a completed change in the experimental workflow.
doc-gen
Generate documentation from source code — docstrings, README sections, API references.