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.
npx skills add slicervm/agent-skills --skill use-slicer-proxygit clone --depth 1 https://github.com/slicervm/agent-skillsWrote 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/skills/slicervm/agent-skills/use-slicer-proxy)<a href="https://agentmods.dev/skills/slicervm/agent-skills/use-slicer-proxy"><img src="https://agentmods.dev/badge/skills/slicervm/agent-skills/use-slicer-proxy/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/skills/slicervm/agent-skills/use-slicer-proxy"><img src="https://agentmods.dev/badge/skills/slicervm/agent-skills/use-slicer-proxy.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 | $0.00068 | $0.04864 |
| Opus 5 | $0.00034 | $0.02432 |
| Sonnet 5 | $0.00014 | $0.00973 |
| Haiku 4.5 | $0.00007 | $0.00486 |
Grade B, and why
use-slicer-proxy scanned grade B with 3 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 9d 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.
Asks for rootlowPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo slicer ca init --hostgroup sbox Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Reset the CA: stop the daemons, `sudo rm -rf .slicer/ca/<hostgroup> proxy.crt proxy.key`, then re-run `slicer ca init`. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
sudo slicer vm exec sbox-1 -- curl -sS --max-time 3 https://wikipedia.org How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Slicer Proxy — filtered egress and secret injection for microVMs
Slicer Proxy is a daemon that runs alongside Slicer and becomes the only egress path for microVMs. Use it to:
- Audit and log every outbound HTTP(S) request from a VM
- Default-deny egress and allow only specific hosts / paths / methods / ports
- Inject credentials (Bearer, Basic, OAuth) so the VM never sees the real secret
- Expire rules automatically with a TTL
- Passthrough raw TCP (SSH, Postgres, cert-pinned clients) without TLS termination
This skill assumes a running Slicer daemon — see the use-slicer skill for connecting to one. Full docs: https://docs.slicervm.com/proxy/
Concepts
Slicer Proxy separates three nouns:
- client — a name plus a token. The VM authenticates to the proxy with that token (carried in
HTTPS_PROXY), which is how the proxy identifies it — no source-IP guessing. - secret — a named upstream credential (
bearer,basic, or anoauth-*type). The value lives on the proxy, never in the VM. - allow rule — owned by a client: a
hostplus optionalpaths/methods/ports/ttl, and optionally a referencedsecret.
Default deny. A client with no rules reaches nothing. An allow rule may be bare (just open a host) or reference a secret (inject a credential when it matches).
Ports and bind address
:3128— plaintext listener →HTTP_PROXY=http://:<token>@<ip>:3128:3129— TLS listener →HTTPS_PROXY=https://proxy:<token>@<ip>:3129- Proxy IP: Linux defaults to
192.168.222.1(set with--bind); macOS is192.168.64.1(the NAT gateway).
The :3129 outer certificate is signed by the host group CA, so a guest that already trusts the Slicer CA validates it with no extra flags.
Setup on Linux
Slicer Proxy only makes sense with isolated networking — the only mode where the proxy is the sole egress path. In bridge mode the VM has direct NAT'd Internet and bypasses the proxy entirely, so rules do nothing.
- Generate an isolated config that drops all egress except the proxy ports:
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.
- 9d ago First seen · 359 lines · 68 tokens per session scan B 369c44786ecf
use-slicer-proxy is a skill published in the GitHub repository slicervm/agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 68 tokens to every session and 4,864 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 3 findings (asks for root, recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…