community-notes

A browser script for viewing and contributing to Community Notes on X/Twitter. Community Notes are user-written fact checks or context attached to posts.

In plain words
What is it for?
Use it to view notes on posts, browse posts that have notes, write a note for a specific post, or rate existing notes when your X account is enrolled.
Why use it?
Relevant context can be hard to find while browsing, and adding or evaluating notes requires several actions in X. The script puts viewing, writing, rating, and browsing into one workflow.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/nirholas/xactions/community-notes
Any agent
npx skills add nirholas/XActions --skill community-notes
Clone the repo
git clone --depth 1 https://github.com/nirholas/XActions

Made for: Claude Code, Codex.

Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 514 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00047 $0.00514
Opus 5 $0.00023 $0.00257
Sonnet 5 $0.00009 $0.00103
Haiku 4.5 $0.00005 $0.00051

Measured 2d ago against content hash c33c3751bdd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

community-notes 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 2d 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.

skills/community-notes/SKILL.md · 66 lines

What it actually says

Community Notes

Browser console script for interacting with X's Community Notes fact-checking system.

Script Selection

Goal File Navigate to
View, write, rate, or browse Community Notes src/communityNotes.js x.com/home or tweet page

Quick Start

  1. Navigate to a tweet page or x.com/home
  2. Open DevTools (F12) → Console
  3. Edit CONFIG.action to choose what to do
  4. Paste src/communityNotes.js → Enter

Actions

const CONFIG = {
  action: 'view',   // 'view' | 'write' | 'rate' | 'browse'

  // For 'write':
  tweetUrl: 'https://x.com/user/status/123',  // Tweet to annotate
  noteText: 'Context: this claim is missing...',

  // For 'rate':
  // Script finds existing notes and presents rating options
};
Action Description
view View Community Notes on currently visible tweets
write Write a note on a specific tweet (requires tweetUrl + noteText)
rate Rate existing notes as helpful or not helpful
browse Browse tweets on your timeline that have Community Notes

Prerequisites

  • Writing and rating notes requires enrollment at x.com/i/communitynotes
  • Enrollment is open to all users but requires a verified phone number
  • New contributors are in "Needs More Ratings" status until they establish a track record

Notes

  • Community Notes are surfaced by X's algorithm based on rater agreement
  • Notes only appear publicly when enough raters from diverse viewpoints agree
  • Script uses DOM automation on x.com — no API key required
  • content-posting — Post tweets and threads
  • discovery-explore — Find trending topics that may have Community Notes
  • analytics-insights — Analyze tweet performance and sentiment
Changes

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.

  1. 2d ago First seen · 66 lines · 47 tokens per session scan A c33c3751bdd0

Subscribe to this mod's changes

community-notes is a skill published in the GitHub repository nirholas/XActions (496 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 514 once invoked, about $0.0002 per session on Opus 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.

Related

Other skills, from other repositories

browser-test

Validate a feature works by driving a real browser with Playwright MCP. No test files — just interactive verification.

langwatch/langwatch · 25 tokens

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

the-open-agent/openagent · 22 tokens

browser-pair

Collaborative headed browser session for UI work. Launch Playwright Chromium visible to the user, handle auth, then interactively drive the browser while the user watches and gives real-time visual feedback. Edit code and refresh to verify fixes live. Use when the user says 'browser pair', 'paired browser', 'let's…

langwatch/langwatch · 87 tokens

debug-frontend-with-browser

Frontend diagnosis extension for the acceptance skill. Use for intermittent rendering, ordering, stale-state, navigation, virtual-list, React/Zustand, optimistic-update, refresh-dependent, or browser-only failures where the first broken boundary may be DOM, component input, derived state, client cache, network data…

lobehub/lobehub · 118 tokens

design-prototype

Produce an interactive single-file HTML design prototype using the REAL LobeHub design system (@lobehub/ui + antd + antd-style tokens) with production-style React — no build step, opens directly in a browser. Use when asked for a design prototype / interactive mockup / 交互原型 / 出个原型 / 设计稿 HTML for a page or flow, or to…

lobehub/lobehub · 92 tokens

share

Use when a user needs a browser-accessible link to preview, present, or send Agent-generated workspace files, an entire project, or the current topic outside Super Magic—especially rendered output such as HTML that messaging or file-viewing channels cannot display directly—or when they need to find, reuse, change, or…

dtyq/magic · 69 tokens