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 AgentComputerAI/torch --skill proxygit clone --depth 1 https://github.com/AgentComputerAI/torchWrote 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/agentcomputerai/torch/proxy)<a href="https://agentmods.dev/skills/agentcomputerai/torch/proxy"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/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/agentcomputerai/torch/proxy"><img src="https://agentmods.dev/badge/skills/agentcomputerai/torch/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 | $0.00083 | $0.02566 |
| Opus 5.5 | $0.00033 | $0.01026 |
| Sonnet 5.5 | $0.00017 | $0.00513 |
| Haiku 4.5 | $0.00008 | $0.00257 |
Grade A, and why
proxy 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Proxy integration
Proxies are anti-blocking Layer 7 — escalate to them when IP-based blocking is the problem (403/429 on your datacenter IP, rate limits hit fast, geo-blocked content). They don't help with browser fingerprinting or JavaScript challenges — combine with stealth mode (scrape anti-blocking) and CAPTCHA solvers (2captcha, capmonster) as needed.
When to use a proxy
| Symptom | Likely cause | Fix |
|---|---|---|
| 403 on first request | IP reputation (datacenter flagged) | Residential proxy |
| 429 after 5-20 requests | Rate limit per IP | Rotating residential, one IP per request |
| "Not available in your country" | Geo-block | Country-specific exit node |
| Instant Turnstile / JS challenge | Fingerprinting, NOT IP | Don't use proxy — use stealth + solver |
| CAPTCHA appears | Behavior detection | Solver, not proxy (see 2captcha) |
Residential proxies cost money — don't reach for them before trying headed stealth mode and cookie persistence.
Proxy types
| Type | Cost | Trust level | Use case |
|---|---|---|---|
| Datacenter | $0.50-$2/GB | Low (easy to flag) | Low-protection sites, high throughput |
| Residential | $4-$10/GB | High (real ISP IPs) | Protected sites, default choice |
| Mobile (4G/5G) | $10-$20/GB | Highest (shared carrier IPs) | Extreme protection, Instagram, TikTok |
| ISP / Static residential | $1-$3/IP/mo | High, sticky | Authenticated sessions |
Provider comparison (2026)
| Provider | Starting price | Network | Strengths |
|---|---|---|---|
| Smartproxy | $4.50/GB | Large | Best small-scale value, no minimum, simple API |
| Bright Data | $5.88/GB | 150M+ IPs | Largest network, ZIP-code targeting, enterprise compliance |
| Oxylabs | $6.98/GB | 175M+ IPs | Fastest (~0.4s response), 99.82% success rate, $300 minimum |
| IPRoyal | $1.75/GB | Smaller | Cheapest residential, pay-as-you-go |
| Decodo (ex-Smartproxy) | $3.50/GB | Mid | Best value for mid-scale |
Default recommendation for torch: Smartproxy (no minimum, Puppeteer-friendly) or IPRoyal (cheapest). Pick Bright Data only if you need enterprise features or ZIP-precise geo-targeting.
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.
- 1mo ago First seen · 294 lines · 83 tokens per session scan A 82e7524d0079
proxy is a skill published in the GitHub repository AgentComputerAI/torch (5 stars, last pushed 6mo ago), licensed MIT. It adds 83 tokens to every session and 2,566 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
chrome-extension
Use when building or shipping a Manifest V3 browser extension and hitting its quirks — service worker dying and losing state, permission warnings, a Chrome Web Store rejection, content-script/worker/popup messaging, or an MV2-to-V3 migration. NOT a generic web app (that is nextjs), NOT a desktop shell (that is…
data-scraper
Use when data lives on a website with no usable API — listings, prices, public records — and the scrape must stay legal and not get blocked: legal gate, extraction path, durable selectors, pacing, resilience. NOT parsing bytes you already hold into fields (that is structured-extraction), NOT a documented API or key…
nodejs
Use when building or operating a plain Node.js / Express 5 backend service: project layout, async correctness, central error middleware, fail-fast config, graceful shutdown on SIGTERM. NOT DI modules/providers/guards (that is nestjs), NOT the type system or tsconfig (that is typescript), NOT REST contract design (that…
checking-a-page
Check that a web page you wrote or changed actually works, by opening it in a browser and driving every control on it. Use after creating or editing an HTML page, or the JavaScript or CSS that a page loads.
browser-qa
Testing web apps through a real browser: reconnaissance before acting, selector discovery, state capture, console errors and screenshot evidence. Use on a web surface end to end, or to reproduce a front-end bug.
browser-automation
A browser-automation workflow that detects the terminal environment and chooses a browser control tool. It supports opening pages, taking snapshots, clicking, filling fields, and other checks.