A command reference for Xeepy, a command-line tool for working with X/Twitter accounts and posts. It covers login, session cookies, scraping, output formats, and shared command options.

Use it to check the exact command for logging in, checking account status, exporting sessions, or scraping replies from a post.

It puts the available commands and their options in one place, so you do not have to guess how to authenticate or run a task.

reference — Command by nirholas

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 commands/nirholas/xactions/reference

Clone the repo

git clone --depth 1 https://github.com/nirholas/XActions

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 2,543 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.02543
Opus 5	$0.00000	$0.01272
Sonnet 5	$0.00000	$0.00509
Haiku 4.5	$0.00000	$0.00254

Measured yesterday against content hash 467e42acaf9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reference 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 yesterday.

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.

python/docs/cli/commands/reference.md · 598 lines

How it starts

The opening of the file, as written. The whole thing — 598 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLI Command Reference

Complete reference for all Xeepy command-line commands.

Global Options

# All commands support these options
xeepy [OPTIONS] COMMAND [ARGS]

Options:
  --config PATH    Configuration file path
  --profile NAME   Profile to use (for multiple accounts)
  --verbose, -v    Enable verbose output
  --quiet, -q      Suppress non-essential output
  --json           Output in JSON format
  --help           Show help message

Authentication Commands

`auth login`

Authenticate with X/Twitter.

# Interactive browser login
xeepy auth login

# With specific profile
xeepy auth login --profile work

# Headless (cookie import)
xeepy auth login --cookies cookies.json

`auth logout`

Clear authentication.

xeepy auth logout
xeepy auth logout --profile work

`auth status`

Check authentication status.

xeepy auth status
# Output: ✓ Logged in as @username

`auth export`

Export session cookies.

xeepy auth export session.json
xeepy auth export --format netscape cookies.txt

Scraping Commands

`scrape replies`

Get replies to a tweet.

# Basic usage
xeepy scrape replies https://x.com/user/status/123

# With options
xeepy scrape replies https://x.com/user/status/123 \
  --limit 500 \
  --output replies.csv \
  --format csv

# Include nested replies
xeepy scrape replies https://x.com/user/status/123 --nested

Options:

Option	Description	Default
`--limit, -n`	Maximum replies	100
`--output, -o`	Output file	stdout
`--format, -f`	Output format (csv, json, table)	table
`--nested`	Include nested replies	false
`--since`	Only replies after date	-

`scrape profile`

Get user profile information.

xeepy scrape profile elonmusk
xeepy scrape profile elonmusk --json
xeepy scrape profile user1 user2 user3 --output profiles.csv

`scrape followers`

Get user's followers.

Read the full file on GitHub · 598 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.

yesterday First seen · 598 lines · 0 tokens per session scan A 467e42acaf9c

Subscribe to this mod's changes

reference is a command published in the GitHub repository nirholas/XActions (492 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,543 tokens. 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.

Browser automation Data and AI Writing and docs ai-agent automation claude gpt mass-unfollow mcp

reference