Does a STOP watermark mean the post is false or malicious?

It is a personal browsing aid, not a fact-checker or moderation system. It flags suspected spam, engagement bait, reposts, and ads so you notice them faster, and you should tune the threshold to your own tolerance.

How does it separate low-quality posts from real platform ads?

Low-quality probability comes from Jev answering whether the post merits a timeline warning plus a content-type question. Platform ads come from post metadata such as Promoted or Sponsored markers, not from body text mentioning ads.

What setup is needed before watermarks appear?

Load the project root containing manifest.json as an unpacked extension, open the toolbar popup, paste a TypeSafe key, save, and refresh X. Defaults scan automatically at 75% with normal-post labels off.

What data leaves my browser when it scans the timeline?

Post text and limited public metadata go to TypeSafe for scoring over POST to the SystemOne endpoint with limited retries on rate limits and server errors. Images, video, and direct messages are not used as inputs in the current version.

What is the default threshold and can I change it?

The default flags a post when the low-quality probability reaches 75%. Settings saved in chrome.storage.local also cover auto-judging and whether normal posts show a green label.

How does it avoid rescanning the same post?

A post is not requested twice in the current page session, and as you scroll or the page structure changes newly appearing posts are still processed, with the number of concurrent requests capped.

Is there an open-source license?

No license is specified in the repository yet. The README says to add a suitable LICENSE file before publishing it publicly.

CommunityJev Tools & CLIs

Twitter Jev Guard

Chrome and Edge extension that scores X posts with Jev and overlays STOP watermarks on likely low-quality posts and AD marks on promoted posts.

See highlights

Open github.com

Stars: 9
Language: JavaScript
Published by: Community
Author: qs-lll
Last verified: Oct 2026

qs-lll/twitter-jev-guard

User repository on GitHub

View on GitHub

使用 TypeSafe Jev 在 X/Twitter 时间线上识别低质量、垃圾和广告帖子，并在文字区域显示醒目的半透明水印。

Forks: 2
Last pushed: Updated Sep 2026

Repo stats from the GitHub API, cached Oct 2026.

Tagscommunity awesomejev catalog-import

Works forJev for Classification

Used inJev for Software & DevTools

Languages: JavaScript

Highlights

Background service worker calls TypeSafe Jev directly with no local proxy to run.
Default 75% low-quality threshold with red STOP overlay inside the post text container.
Amber AD overlay driven by promoted metadata; body text alone does not mark an ad.
Auto-scans new timeline posts with capped concurrency on x.com and twitter.com.

Watch out

Judgments are probabilistic and text-only, depend on page structure and language, and the key sits in extension local storage rather than a hardened server. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

jev-reviewer

Browser app for systematic-review extraction that opens a trial report with supplements and returns verbatim quotes with file and place, stored locally as projects holding studies.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

choxos/jev-reviewerJavaScript

jev-gmail-ai-spam-filter-and-labeling

Self-hosted Google Apps Script that classifies Gmail by meaning with Jev Choice over your own dozen-label taxonomy, checking metadata first and full content only when confidence demands it.

Jev Tools & CLIs#community#jevbest#catalog-import

Community

ilyamk/jev-gmail-ai-spam-filter-and-labelingJavaScript

hearth-jev-rental-search

Rental search agent that drives a real Chrome across Craigslist, Facebook Marketplace, Redfin, and Zillow and returns one shortlist with photos and links.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

Nancy-Chauhan/hearth-jev-rental-searchJavaScript

jev-minesweeper

Browser Minesweeper demo that asks one Noul mine question per frontier cell in a single Jev request, decides opens and flags from probabilities, and falls back to an exact solver.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

comoc/jev-minesweeperJavaScript

llm-to-jev

Static web tool that finds bounded decisions in GPT, Claude, or Gemini prompts and proposes Jev Choice, Score, and Noul questions with SDK exports.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

alexwestco/llm-to-jevJavaScript

jev-helper

Chrome and Edge Manifest V3 extension that takes over a running browser real-time strategy game, with Jev cloud, a locally served Laya model, or any OpenAI-compatible endpoint as the decision source.

Jev Tools & CLIs#community#awesomejev#catalog-import

Community

ra2web/jev-helperJavaScript

From the Jev guides

Original write-ups on what this entry is for.

Jev on the Gateways: Vercel, Workers AI, and OpenRouter

Oct 12, 2026

The request shape barely changes across surfaces; the surrounding contract does. When to call the API directly and when a gateway, a Worker binding, or a router entry earns its extra hop.

Jev Tools & CLIs#gateway#vercel#cloudflare

Read article

Exporting Decision Models: GGUF, ONNX, and Device Runtimes

Oct 10, 2026

Taking a decision checkpoint out of Python: what the GGUF and browser WebGPU exports preserve, what they change, and the parity evidence the model cards publish.

Jev Tools & CLIs#open-models#local#onnx

Read article

Records at Rest: Documents, Inboxes, and Risk Queues

Sep 28, 2026

Jev labels a record that already exists. Code moves, flags, or holds it. How the document, mail, and transfer tools keep the action out of the model.

Jev Tools & CLIs#classification#email#security

Read article

Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai