Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/jianzhichun/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/wrap)<a href="https://agentmods.dev/commands/jianzhichun/permafrost/wrap"><img src="https://agentmods.dev/badge/commands/jianzhichun/permafrost/wrap/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/jianzhichun/permafrost/wrap"><img src="https://agentmods.dev/badge/commands/jianzhichun/permafrost/wrap.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00012 | $0.00253 |
| Opus 5.5 | $0.00005 | $0.00101 |
| Sonnet 5.5 | $0.00002 | $0.00051 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade B, and why
wrap scanned grade B with 1 finding 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 2mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
2. **Persistent** — copy the `env` block from `settings.example.json` into `~/.claude/settings.json`, set `ANTHROPIC_API_KEY` to their DeepSeek key, run `permafrost up`, then start `claude` normally. What it actually says
Explain to the user how to route Claude Code through Permafrost so DeepSeek's cache hits.
Key point first: ANTHROPIC_BASE_URL is read once when claude starts, so the current session cannot be re-routed — this takes effect on the next launch.
Give them the two options:
-
One-shot wrapper (nothing persisted):
permafrost wrap -- [any claude args]This starts the proxy if needed, sets
ANTHROPIC_BASE_URL+ENABLE_TOOL_SEARCH=truefor that child process only, and execsclaude. -
Persistent — copy the
envblock fromsettings.example.jsoninto~/.claude/settings.json, setANTHROPIC_API_KEYto their DeepSeek key, runpermafrost up, then startclaudenormally.
Remind them the upstream defaults to https://api.deepseek.com/anthropic and can be changed with PERMAFROST_UPSTREAM. Offer to write the settings block for them if they confirm the path.
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.
- 2mo ago First seen · 20 lines · 12 tokens per session scan B 0a15fc7ad30f
wrap is a command published in the GitHub repository jianzhichun/permafrost (25 stars, last pushed 4mo ago), licensed MIT. It adds 12 tokens to every session and 253 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
wrap compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| wrapjianzhichun/permafrost | Command | 25 | 4mo ago | MIT | B | 12 | Claude Code |
| helpSmart-AI-Memory/attune-ai | Command | 11 | yesterday | Apache-2.0 | A | 9 | Claude Code |
| doc-genSmart-AI-Memory/attune-ai | Command | 11 | yesterday | Apache-2.0 | A | 18 | Claude Code |
| refactorSmart-AI-Memory/attune-ai | Command | 11 | yesterday | Apache-2.0 | A | 12 | Claude Code |
| pm-competitiveVandanaAjayDubey111/great-pm | Command | 3 | 1mo ago | MIT | A | 31 | Claude Code |
| pm-pricingVandanaAjayDubey111/great-pm | Command | 3 | 1mo ago | MIT | A | 29 | Claude Code |
| pm-roadmapVandanaAjayDubey111/great-pm | Command | 3 | 1mo ago | MIT | A | 28 | Claude Code |