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 oaustegard/claude-skills --skill marking-up-pagesgit clone --depth 1 https://github.com/oaustegard/claude-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/oaustegard/claude-skills/marking-up-pages)<a href="https://agentmods.dev/skills/oaustegard/claude-skills/marking-up-pages"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/marking-up-pages/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/oaustegard/claude-skills/marking-up-pages"><img src="https://agentmods.dev/badge/skills/oaustegard/claude-skills/marking-up-pages.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 | $0.00126 | $0.01950 |
| Opus 5.5 | $0.00050 | $0.00780 |
| Sonnet 5.5 | $0.00025 | $0.00390 |
| Haiku 4.5 | $0.00013 | $0.00195 |
Grade A, and why
marking-up-pages 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 yesterday.
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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marking up pages
The user draws on the page and notes what is wrong; you get each mark tied to the real DOM element and, on dev builds, its component and source file. The marks are the bug report: read them before answering and don't ask the user to re-describe what they already marked.
Needs the Claude in Chrome tools (javascript_tool, computer, tabs_context_mcp). Load them in one ToolSearch call if they are deferred. The JavaScript tool runs in the page's own world and ignores the page's CSP, which is what makes this work.
1. Open the overlay
Use the user's tab (find it with tabs_context_mcp). Run the loader first; it is one line and costs nothing:
window.__scrawl ? (__scrawl.show(), __scrawl.status()) : (c => c && JSON.parse(c).version === '0.2.0' ? (0, eval)(JSON.parse(c).src) : 'NO_CACHE')(localStorage.getItem('page-scrawl:src'))
If it returns NO_CACHE, read scripts/overlay.js and pass the whole file as the text of javascript_tool. The overlay caches itself in that origin's localStorage, so after a reload the loader is enough. (Keep the version in the loader equal to VERSION in overlay.js.)
Then tell the user, briefly: draw on the page; after each mark a note box opens — type or dictate what's wrong, Enter saves; ⌥⇧S toggles drawing so they can click around in between; press Done and tell you when finished. Then stop and wait. Don't poll.
If the user opened it themselves with the bookmarklet, skip to step 2. If they instead paste copied marks or attach a *.scrawl.json file (the toolbar's Copy and Save buttons, for use without Claude in Chrome), read that: the file's summary field is the same text as summary(), and the rest is export({ points: true }). You can't screenshot or focus marks from a file, so lean on the selectors, text and source locations.
2. Read the marks
__scrawl.summary()
[page-scrawl · 3 marks · “Settings” · http://localhost:5173/settings · 1440×900 @2x]
- #1 underline over “setings” → `h1` “Notification setings” ‹SettingsForm› src/pages/Settings.tsx:23 — “typo: settings”
style: font 22px/normal 700 Inter · color rgb(17, 17, 17) · display block · margin 14.7px 0px
- #2 arrow → `button[data-testid="save"]` “Save changes” ‹SaveButton › SettingsForm› src/components/SaveButton.tsx:14 — “hugs the divider”
- #3 circle over “Recieve email updates” → `div.row:nth-of-type(1) > label` ‹Toggle› src/components/Toggle.tsx:9
Failed requests since page load:
· 404 fetch http://localhost:5173/api/prefs
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 87 lines · 126 tokens per session scan A 7e8e79eade99
marking-up-pages is a skill published in the GitHub repository oaustegard/claude-skills (154 stars, last pushed yesterday), licensed MIT. It adds 126 tokens to every session and 1,950 once invoked, about $0.0005 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 2026-10-21.
Other skills, from other repositories
safari-mcp-workflow
Inspect a scoped live site in Safari through Safari Technology Preview's local MCP server. Use for Safari-specific DOM, console, network, screenshot, accessibility, performance, interaction, responsive, or print-media evidence.
browser-testing-with-devtools
Verify web apps with browser DevTools—DOM, console, network, performance, and accessibility at runtime. Use with Chrome DevTools MCP or headless browser tools.
chrome-devtools-axi
Use the chrome-devtools-axi CLI to operate Chrome or investigate live page behavior. Default for ad hoc browsing, forms, rendered extraction, screenshots, DOM/CSS, console/network failures, responsive behavior, and performance or memory questions. Excludes static-only fetching, direct-MCP-only requests, explicitly…
chrome-devtools
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.
download-xhs-videos
A process for downloading a Xiaohongshu creator’s videos to a local folder. Xiaohongshu, also called RedNote, is a Chinese social-media platform.
dbr-logs
This skill should be used when the user asks to fetch, search, or analyze Databricks job logs. Trigger phrases include "job logs", "databricks logs", "executor logs", "driver logs", "spark job failed", "check logs for", "why did my job fail", "OOM error in job", "check run logs", or requests to debug a Databricks job…