x-twitter

A skill for reading X, formerly called Twitter, through an authenticated browser session and its internal data interfaces. It supports inspecting profiles, posts, timelines, searches, likes, reposts, direct messages, and relationship data as permitted by the account.

In plain words
What is it for?
Use it to inspect an account, find posts, search X, see who liked or reposted content, review connections, or build a graph of people and posts.
Why use it?
It helps collect information from X when ordinary browsing or a public interface does not expose the needed account data. Some lists or protected content may remain unavailable.

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/agentproto/ts/x-twitter
Any agent
npx skills add agentproto/ts --skill x-twitter
Clone the repo
git clone --depth 1 https://github.com/agentproto/ts

Made for: Claude Code, Codex.

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,382 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00070 $0.01382
Opus 5 $0.00035 $0.00691
Sonnet 5 $0.00014 $0.00276
Haiku 4.5 $0.00007 $0.00138

Measured 2d ago against content hash 01cb4b302a49, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

x-twitter scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

const r = await fetch(URL, {
packages/skill-pack-bureau/src/skills/x-twitter/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

X / Twitter — recon plan

SHIPPED on the Camofox stealth session (X flags CDP-Chromium → use Camofox, not the local-browser chain). Helpers:

  • scripts/lib/camofox.ts (createCamofox) — Camofox-service REST client (tabs/navigate/click/type/evaluate + fetchInPage). baseUrl via CAMOFOX_URL (⚠️ use 127.0.0.1, not localhost — node/undici picks IPv6 ::1 and fails).
  • X adapterSOCIAL_PLATFORMS.x in @agstudio/browser-social (sites/x/adapter.ts): profile · authored · engagement-given/received · connections, as a SocialSourcePort. queryIds read live from X's JS bundle (drift-proof); features flags self-heal on 400s. The capture recipe lives in the registry, not a script-local helper.
  • Graph ingest: scripts/profile.ts x <handle> --graph-only [--depth quick] → registry capture → landFootprint graph sink (platform "x"): profile→SocialPerson, posts→AUTHORED, connections→FOLLOWS. Validated live: @romanbuildsaas → 73 records · 74 graph ops.
  • Login done via Camofox (cookie-banner dismissed via /evaluate JS, then username→password→Continue). ⚠️ Followers list often 404s for large/protected accounts; Favoriters/Retweeters load lazily → captureMore() after opening the likes/retweets modal. Gecko: no CDP, but /evaluate works (used for the API calls).

Legacy note: the local-browser cloned profile is NOT logged into X and X flags CDP anyway — the Camofox path above supersedes it.

Internal API: GraphQL at https://x.com/i/api/graphql/<queryId>/<OperationName> (+ some REST https://x.com/i/api/1.1/ and /2/). Same shape as Voyager: the web app calls its own GraphQL; we drive that in-page.

Auth (capture from any /i/api/graphql request header)

  • authorization: Bearer <web-app bearer> — a constant embedded in X's JS (same for all web users; long AAAA…). Capture once.
  • x-csrf-token: <ct0 cookie> — per-session; read from document.cookie (ct0).
  • cookies (auth_token, ct0) ride automatically (same-origin).
  • also: x-twitter-active-user: yes, x-twitter-auth-type: OAuth2Session, x-twitter-client-language: en.

Read the full file on GitHub · 117 lines

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 · 117 lines · 70 tokens per session scan A 01cb4b302a49

Subscribe to this mod's changes

x-twitter is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed 3d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,382 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

browser-qa

Validate web applications through the embedded browser with responsive, interaction, console, and screenshot checks.

metaspartan/cybara · 22 tokens

goplaces

Query Google Places API (New) via the goplaces CLI for text search, place details, resolve, and reviews. Use for human-friendly place lookup or JSON output for scripts.

metaspartan/cybara · 41 tokens

ai-browser-use

业务诊断助手适合市场营销、运营、产品、销售在用户提出“这件事该怎么做”这类问题,需要快速拆解目标、判断重点并形成可执行结果时使用,帮助基于输入材料生成摘要、诊断结论、行动建议和可复用交付物。.

skillsaiagent/aiskills · 71 tokens

pre-push

Runs the local equivalent of the CI merge gate before you push. Detects which areas (Python, TypeScript, docs) your changes touch, auto-fixes what it can, then runs only those checks. Use when the user asks to run pre-push checks, get push-ready, verify changes before pushing or opening a PR, "make sure CI will pass"…

strands-agents/harness-sdk · 85 tokens

docs-planner

Identify documentation gaps and prioritize the docs backlog. Use when planning a docs improvement sprint, after signals surface repeated friction, when new SDK features ship without docs, or for periodic health assessment. Also triggers on "plan docs work", "what docs need writing", "prioritize the backlog", "docs…

strands-agents/harness-sdk · 73 tokens

pr-feedback

Fetches PR review feedback and inline comments, categorizes them, and presents options to the user. Use when the user asks to get, read, address, or fix review comments on a pull request.

strands-agents/harness-sdk · 44 tokens