SurfSense is an open-source desktop application that uses an AI agent to research, transform, and edit documents while keeping their index on the user's machine. It is intended for people working with documents they cannot upload, with a choice of local or remote models and no account required.
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 MODSetter/SurfSense --skill surfsense-htmlgit clone --depth 1 https://github.com/MODSetter/SurfSenseWrote 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/modsetter/surfsense/surfsense-html)<a href="https://agentmods.dev/skills/modsetter/surfsense/surfsense-html"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/surfsense-html/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/modsetter/surfsense/surfsense-html"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/surfsense-html.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 | $0.00089 | $0.02136 |
| Opus 5.5 | $0.00036 | $0.00854 |
| Sonnet 5.5 | $0.00018 | $0.00427 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
surfsense-html 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 today.
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.
Web pages
You write the page yourself, as one HTML file under outputs/, and keep it with surfsense_save_page. SurfSense stores it as a version in Studio, where the user opens it, and shows you screenshots of it. To change it later you edit the same file and save again, which makes the next version.
The files in this skill
| File | Read it |
|---|---|
design.md |
Always, before writing: how a page looks and moves. |
figures.md |
When the page explains a mechanism or a process with an isometric figure. |
isometric.md |
With figures.md: the drawing helper to copy into the page, and its rules. |
examples/spring-scale.md, examples/pin-tumbler-lock.md, examples/job-queue-conveyor.md |
The one closest to your mechanism: a complete, working figure page to start from. |
How to make a page
- Read the sources and decide what the reader most needs, and whether the page needs a figure of a mechanism (most pages do not; charts and type carry a report, a summary or a dashboard).
- Read
design.md. For a figure, readfigures.md,isometric.mdand the closest example too. - Plan in a few lines, then write a first, lean version: the structure, the main content, and for a figure its main parts working.
- Save it with
surfsense_save_pageand look at every screenshot. - Improve it with edits to the same file, a section or a group of parts at a time, saving and looking after each.
The contract
- One complete HTML document:
<!doctype html>,<html lang>,<head>with<meta charset="utf-8">,<meta name="viewport" content="width=device-width, initial-scale=1">and a<title>, then<body>. - Everything inline: CSS in
<style>, code in<script>, images asdata:URLs or inline SVG. - The page has no network. The viewer blocks every request: no CDN, no web font, no
fetch, no image from a URL, no form that submits. Use system fonts, draw charts as SVG, and write the data into the page. A save lists anything the page asks to load, so you can take it out. - No
evalornew Function; they are blocked too. - At most 5 MB. A page is usually 10 to 80 KB.
- Write it at
outputs/<short-name>.htmlwith your own file tools. It stays there for the next edit. - Keep the first write lean, about 300 lines at most, and grow the page with edits. One reply can only write so much: a page planned and written whole in one go can run out before it is saved. Plan in a few lines, then write.
- Only what the sources and the user support. Every figure, date and name on the page is one you found or were given.
What ships with it
6 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.
- today First seen · 115 lines · 89 tokens per session scan A f97cb2f38839
surfsense-html is a skill published in the GitHub repository MODSetter/SurfSense (16,603 stars, last pushed today), licensed Apache-2.0. It adds 89 tokens to every session and 2,136 once invoked, about $0.0004 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 2026-10-26.
Other skills, from other repositories
sage-review
Deep, platform-neutral code review for PRs and CRs in ONE thorough single pass — design reasoning (Problem Worth Solving & Solution Fit) as one dimension alongside the 9 code-level dimensions, with chain-of-consequences, self-critique, and draft-only comments. The single app-owned source of truth.
design-critique
Run a heuristic evaluation of a UI design (image, HTML, Figma, URL, or flow) the way an experienced designer would. Evaluates 4 categories (Visual & hierarchy, Usability & interaction, Accessibility, Content) using recognized frameworks, NN/g 0-4 severity, and evaluability-aware prioritization that never judges what…
living-ui
Use when building an animated or interactive widget, explainer or dashboard page: how motion feels, where the eye goes, where words sit, reduced motion, keyboard and screen readers. Style-neutral: it never picks colours, fonts or shapes. Pairs with the widgets skill.
dashboard-template
Kiro Crew repo only: load this when a task will author or change a dashboard page. A page never ships alone: the same PR carries its TypedDict contract, its provider, and a parity test that the two agree. Scaffold all four from one field list; read numbers from an existing fold, never type them.
theme-pack-authoring
Build, validate, and install Kiro Crew theme packs -- pack anatomy, the 56-variable palette, role-tagged fonts, the overrides.css allowlist (what installs vs what actually renders), and the install-verify cycle. Use when the user wants to create or edit a theme pack.
image-authoring
Author images and diagrams as code — SVG, Pillow, Excalidraw, mermaid. Load when asked to draw, illustrate, or make an image, icon, logo, poster, or diagram.