Borrowing it
Nothing to install: this file belongs to GabrielOnDelphi/Claude-Tools-for-Delphi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/GabrielOnDelphi/Claude-Tools-for-Delphi/main/.claude/skills/light-web-UncensoredFetch/SKILL.mdgit clone --depth 1 https://github.com/GabrielOnDelphi/Claude-Tools-for-DelphiWrote 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/gabrielondelphi/claude-tools-for-delphi/light-web-uncensoredfetch)<a href="https://agentmods.dev/skills/gabrielondelphi/claude-tools-for-delphi/light-web-uncensoredfetch"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-uncensoredfetch/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/gabrielondelphi/claude-tools-for-delphi/light-web-uncensoredfetch"><img src="https://agentmods.dev/badge/skills/gabrielondelphi/claude-tools-for-delphi/light-web-uncensoredfetch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00134 | $0.02174 |
| Opus 5 | $0.00067 | $0.01087 |
| Sonnet 5 | $0.00027 | $0.00435 |
| Haiku 4.5 | $0.00013 | $0.00217 |
Grade A, and why
light-web-UncensoredFetch 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 3d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
light-web-UncensoredFetch — read a page WebFetch won't
UncensoredClaude.exe drives a real WebView2 browser on this PC, renders one URL, and writes the page's
visible text to a file. It runs OUTSIDE Claude Code's network, so WebFetch's host denylist never applies.
Exe: UncensoredClaude.exe (Win64). It is a small Delphi WebView2 host, not published — build your own
or point this skill at any equivalent tool that takes a URL and writes the rendered text to a file.
Set its full path in the commands below before using the skill.
READ THIS FIRST — the one reason it "doesn't work"
The exe is a GUI-subsystem app. That changes how you must launch it:
- Bash tool (recommended): a direct call BLOCKS until the exe exits. This is the reliable way.
- PowerShell tool: a direct call
& exe ...returns INSTANTLY, before the page is fetched. If you then Read the file you get "file not found" or stale content and conclude it failed. It did not — you read too early. In PowerShell you MUST useStart-Process -Wait.
Verified 2026-07-24: in PowerShell the output file did not exist until ~4 s after & returned.
The command (use the Bash tool)
Quote BOTH paths — the exe path and the output path contain spaces. Use forward slashes or escaped backslashes; an unquoted path with a space is parsed as extra arguments and fails with exit 1.
"<path to your UncensoredClaude.exe>" "<url>" "C:/AI/ClaudeCode-Temp/page.txt"
echo "exit=$?"
Then Read C:\AI\ClaudeCode-Temp\page.txt.
Smoke test it first if unsure it is built/working:
"<path to your UncensoredClaude.exe>" "https://example.com" "C:/AI/ClaudeCode-Temp/smoke.txt"; echo "exit=$?"
Expect exit=0 and a file containing "Example Domain".
PowerShell variant (only if you cannot use Bash)
$exe='<path to your UncensoredClaude.exe>'
$p=Start-Process $exe -ArgumentList '"<url>"','"C:\AI\ClaudeCode-Temp\page.txt"' -Wait -PassThru
"exit=$($p.ExitCode)"
Did it work?
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.
- 3d ago Changed · +20 lines 7c2a81b07061
- 6d ago Changed · +1 lines 51d9839f8aa5
- 7d ago Changed · +2 lines d96cef52f8b7
- 11d ago First seen · 92 lines · 134 tokens per session scan A 71ad5647424e
light-web-UncensoredFetch is a skill published in the GitHub repository GabrielOnDelphi/Claude-Tools-for-Delphi (18 stars, last pushed 3d ago), licensed MPL-2.0. It adds 134 tokens to every session and 2,174 once invoked, about $0.0007 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
interactive-login
How to complete browser/interactive logins (aws / gh / glab / gcloud). The platform backgrounds the login poller so it survives the human's browser round-trip — and when that does NOT work.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
azure-messaging-webpubsub-java
Build real-time web applications with Azure Web PubSub SDK for Java. Use when implementing WebSocket-based messaging, live updates, chat applications, or server-to-client push notifications.
google-safe-browsing
Prevent and fix Google Safe Browsing "Dangerous site" flags. Use when launching a public web app, buying/picking a domain, building a login or signup page, or when any site shows a red "Dangerous site" / "Deceptive site" warning in Chrome, Brave, Safari, Firefox, or Edge. Triggers on "dangerous site", "deceptive…