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
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/MODSetter/SurfSensenpx agentmods add skills/modsetter/surfsense/videoWrote 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/video)<a href="https://agentmods.dev/skills/modsetter/surfsense/video"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/video/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/video"><img src="https://agentmods.dev/badge/skills/modsetter/surfsense/video.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 | $0.00015 | $0.01084 |
| Opus 5.5 | $0.00006 | $0.00434 |
| Sonnet 5.5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
video 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Video
Create one narrated 1920×1080 MP4 at 30 fps in /workspace. Use the baked
/opt/remotion harness and dependencies. Never install or download anything.
The sandbox has no network.
Plan before rendering
Draft the complete deck specification first. For every slide include its
on-screen text and narration line. Keep this specification unchanged: pass its
narration lines to synthesize_narration, and later use the full specification
as markdown_representation. It is the durable accessible and editable source;
scene files and props.json are ephemeral.
Refuse requests above the 12-scene product limit rather than silently shortening them. The selected composition must also be at most 180 seconds.
Composition rules
- Give each slide one clear purpose. Keep safe outer margins, readable body contrast, restrained motion, and every shape on the 1920×1080 canvas.
- The harness supplies sequencing, narration audio, and the SurfSense watermark. Do not add another watermark or audio element.
- Use only these system-installed font families:
Interfor normal text,Lorafor editorial titles or quotes, andJetBrains Monofor code and figures. No other family is available reliably offline. Do not useloadFont,@font-face, or@remotion/google-fonts. - Write one complete, self-contained TSX module per slide. Each module must
import every dependency it uses and have a default component export. The
harness writes the module verbatim: it does not inject globals, strip imports,
or rewrite exports. Dependencies must already exist in baked
node_modules.
Use this exact module shape:
import type React from "react";
import {AbsoluteFill, useCurrentFrame, useVideoConfig} from "remotion";
import {stagger} from "../../stagger";
const Scene: React.FC = () => {
const frame = useCurrentFrame();
const {fps} = useVideoConfig();
const entrance = stagger(frame, fps, 0, 1);
return (
<AbsoluteFill
style={{
alignItems: "center",
backgroundColor: "#101828",
color: "white",
fontFamily: "Inter",
justifyContent: "center",
}}
>
<h1 style={{fontSize: 96, ...entrance}}>A clear opening</h1>
</AbsoluteFill>
);
};
export default Scene;
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.
- 1mo ago Changed c3d0fc392a63
- 1mo ago First seen · 107 lines · 15 tokens per session scan A 6de24979d780
video is a skill published in the GitHub repository MODSetter/SurfSense (16,585 stars, last pushed today), licensed Apache-2.0. It adds 15 tokens to every session and 1,084 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
first-reader
Beta readers for any draft, run by simulating how a real reader experiences it, moment by moment. A skim gate, a no-lookahead timed read producing an attention transcript with quit points, a recall test of what a reader remembers the next day, and a trust ledger of the implied author. Use when the user asks for a beta…
mcp-apps-builder
MANDATORY for ALL MCP server work - mcp-use framework best practices and patterns. READ THIS FIRST before any MCP server work, including: Creating new MCP servers Modifying existing MCP servers (adding/updating tools, resources, prompts, widgets) Debugging MCP server issues or errors Reviewing MCP server code for…
project-graveyard
Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…
commit-archaeologist
Reconstructs why code exists from local git history, including the introducing commit, later changes, current authors, repeated companion files, and likely intent. Use when the user asks "why does this code exist", "who wrote this function and why", or to "explain the history of this function" before a rewrite…
dependency-doctor
Checks requirements.txt, pyproject.toml, and package.json dependency manifests for surface-level direct-dependency footguns: standard-library shadowing pins, abandoned backports, unpinned dependencies, and obvious intra-manifest conflicts, plus opt-in PyPI yanked releases. Use when the user asks to check a manifest…
scope-creep-detector
Analyzes git diffs against a stated intent to detect scope creep, unrelated files, broad pull requests, changes that grew beyond a fix, dependency additions, public API renames, config or CI edits, oversized hunks, and formatting-only files. Use when the user asks whether a change grew beyond the fix, a PR is too…