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 ajmaluk/site-mirror-skill --skill opencode-site-mirrorgit clone --depth 1 https://github.com/ajmaluk/site-mirror-skillWrote 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/ajmaluk/site-mirror-skill/opencode-site-mirror)<a href="https://agentmods.dev/skills/ajmaluk/site-mirror-skill/opencode-site-mirror"><img src="https://agentmods.dev/badge/skills/ajmaluk/site-mirror-skill/opencode-site-mirror.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 | $0.00069 | $0.00735 |
| Opus 5 | $0.00034 | $0.00367 |
| Sonnet 5 | $0.00014 | $0.00147 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
site-mirror scanned grade A 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Supports static mirroring via `wget`, dynamic mirroring for single pages, How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
- Capture websites for offline viewing by downloading all page resources.
- Provide three modes:
- static: fast mirroring using
wget. - dynamic single‑page: renders a single page with Playwright to capture assets loaded after JavaScript execution.
- dynamic multi‑page: crawls internal links up to a configurable depth and saves each page into a path that mirrors its URL structure.
- static: fast mirroring using
- Save the mirrored site into a specified output directory with a report.
When to use me
Use this skill when you need to create a local copy of a website for archiving, analysis or offline development. Choose static mode for server‑rendered or simple sites. Choose dynamic single‑page mode for SPAs or pages that load content via JavaScript. Choose dynamic multi‑page mode when you need to follow internal links and capture a small site or section in its entirety.
How to run
-
Select a mode. If the site is mostly static (e.g., basic HTML/CSS), run:
python3 mirror.py <URL> -o <output_dir>Replace
<URL>with the site to mirror and<output_dir>with a destination folder (for example,example-site). -
Dynamic single‑page mode. For JavaScript‑heavy sites, run:
python3 mirror_dynamic.py <URL> -o <output_dir> -
Dynamic multi‑page mode. To follow internal links within the same domain, run:
python3 mirror_dynamic_multi.py <URL> -o <output_dir> --depth <N> --concurrency 3 --max-pages 50Replace
<N>with the maximum number of link levels to follow (e.g., 1). Use optional--concurrencyto set how many pages are processed in parallel and--max-pagesto cap the total number of pages captured. Use caution: higher values can lead to large downloads on complex sites. -
Wait for the command to complete. It writes one or more
index.htmlfiles (mirroring the site structure) and areport.jsonsummarizing downloaded assets.
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.
- 7d ago First seen · 81 lines · 69 tokens per session scan A 7e2745e6127a
site-mirror is a skill published in the GitHub repository ajmaluk/site-mirror-skill (2 stars, last pushed 2mo ago), licensed MIT. It adds 69 tokens to every session and 735 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (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
scrapling-official
Scrape web pages using Scrapling with anti-bot bypass (like Cloudflare Turnstile), stealth headless browsing, spiders framework, adaptive scraping, and JavaScript rendering. Use when asked to scrape, crawl, or extract data from websites; webfetch fails; the site has anti-bot protections; write Python code to…
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…
e2e-automator
Build robust end-to-end test suites with Playwright or Cypress. Covers page objects, fixtures, visual testing, and CI integration.
playwright-cli
Automate browser interactions, test web pages and work with Playwright tests.
playwright-component-testing
Set up component testing with Playwright using a story gallery — scaffold stories and a gallery dev page driven by the built-in mount fixture, no dedicated component-testing runtime. Use when asked to test React or Vue components in isolation with Playwright, or to migrate off @playwright/experimental-ct-react / -vue.
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.