Borrowing it
Nothing to install: this file belongs to ccivlcid/VibeHarness. 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/ccivlcid/VibeHarness/main/.agent/skills/web-fetch/SKILL.mdgit clone --depth 1 https://github.com/ccivlcid/VibeHarnessWrote 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/ccivlcid/vibeharness/web-fetch)<a href="https://agentmods.dev/skills/ccivlcid/vibeharness/web-fetch"><img src="https://agentmods.dev/badge/skills/ccivlcid/vibeharness/web-fetch/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/ccivlcid/vibeharness/web-fetch"><img src="https://agentmods.dev/badge/skills/ccivlcid/vibeharness/web-fetch.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 | $0.00049 | $0.00381 |
| Opus 5.5 | $0.00020 | $0.00152 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
web-fetch 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 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.
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.
What it actually says
Web Fetch — Visit URLs Directly
Core principle: When a URL is given, visit it directly. Don't guess what's on the page.
When to Fetch
| Phase | Fetch When |
|---|---|
Planning (docs/biz/) |
Reference site shared, competitor analysis, API doc page |
| Development | Reading API docs, checking library pages, verifying service status |
| Communication | Non-developer asks "what does this site do?" or "make it like this" |
How to Fetch
Use the WebFetch MCP tool to retrieve page content from a URL.
- Extract URL from non-developer's message
- Fetch page content using
WebFetch - Analyze structure, features, layout, or content
- Summarize in simple terms for non-developers
Presenting Results
- In planning docs (
docs/biz/): layout patterns, feature lists, user flows observed - In technical docs (
docs/ai-dev/): API details, tech stack observations - For non-developers: simple language, focus on what the site does, not how
Limitations
- Login-required pages cannot be accessed
- JavaScript-heavy SPAs may return only initial HTML
- Some sites block automated access
When blocked, ask: "Could you take a screenshot and share it instead?"
vs Web Research
- Web Research: Don't know where to look →
WebSearch - Web Fetch: Have a specific URL →
WebFetch
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 · 48 lines · 49 tokens per session scan A 955433f8c0e4
web-fetch is a skill published in the GitHub repository ccivlcid/VibeHarness (4 stars, last pushed 6mo ago), licensed MIT. It adds 49 tokens to every session and 381 once invoked, about $0.0002 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
interactive-login
Log a CLI in with a browser/device-code flow (aws sso, gh, glab, gcloud, …) and save the result to the keychain so later commands can request it through execute.credentials.
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.
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
open-design-browser
Inspect and exercise local HTML design artifacts and library prototype previews with the existing agent-browser CLI, including screenshots, interaction checks, and rendered DOM snapshots. Use when rendered evidence helps author or review a design; excludes browser installation, remote services, and unrelated browser…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.