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.
npx agentmods add skills/nirholas/three.ws/xeepy-python-twitter-guidenpx skills add nirholas/three.ws --skill xeepy-python-twitter-guidegit clone --depth 1 https://github.com/nirholas/three.wsWrote 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/nirholas/three.ws/xeepy-python-twitter-guide)<a href="https://agentmods.dev/skills/nirholas/three.ws/xeepy-python-twitter-guide"><img src="https://agentmods.dev/badge/skills/nirholas/three.ws/xeepy-python-twitter-guide.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00067 | $0.01425 |
| Opus 5 | $0.00034 | $0.00713 |
| Sonnet 5 | $0.00013 | $0.00285 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
xeepy-python-twitter-guide 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.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
xeepy — Python X/Twitter Library Guide
xeepy is the most comprehensive Python library for X (Twitter) with 154 files and 44,000+ lines of code. Full API v2 coverage, Spaces, Communities, async support, and Grok integration.
Why xeepy?
| Feature | xeepy | tweepy | snscrape |
|---|---|---|---|
| API v2 | ✅ Full | Partial | ❌ |
| Spaces | ✅ | ❌ | ❌ |
| Communities | ✅ | ❌ | ❌ |
| Grok | ✅ | ❌ | ❌ |
| Polls | ✅ | Partial | ❌ |
| Lists | ✅ | Partial | ❌ |
| Async | ✅ | ❌ | ❌ |
| Scraping | ✅ | ❌ | ✅ |
| MCP Server | ✅ | ❌ | ❌ |
Quick Start
pip install xeepy
from xeepy import XClient
client = XClient(
api_key='your-api-key',
api_secret='your-api-secret',
access_token='your-access-token',
access_secret='your-access-secret'
)
Tweets
Post
# Simple tweet
tweet = await client.tweet("Sperax USDs auto-yield is like free money 💰")
# With media
tweet = await client.tweet(
"Check out this chart!",
media=["chart.png"],
alt_text="SPA price chart"
)
# Thread
await client.thread([
"Understanding impermanent loss 🧵",
"1/ IL happens when token prices in your LP change...",
"2/ The greater the divergence, the more IL...",
"3/ Fees can offset IL if the pool is active enough"
])
# Quote tweet
await client.quote(original_tweet_id, "This is huge for DeFi!")
# Reply
await client.reply(tweet_id, "Great point about USDs yield!")
Search
# Basic search
tweets = await client.search("sperax USDs", limit=100)
# Advanced search
tweets = await client.search(
query="$SPA OR $USDs",
start_time="2024-01-01T00:00:00Z",
end_time="2024-12-31T23:59:59Z",
tweet_fields=["public_metrics", "created_at", "author_id"],
sort_order="relevancy",
max_results=100
)
# Filtered stream
rules = [
{"value": "sperax OR USDs OR SPA -is:retweet", "tag": "sperax"},
{"value": "defi yield arbitrum -is:retweet", "tag": "defi"},
]
async for tweet in client.stream(rules):
print(f"[{tweet.tag}] {tweet.text}")
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 · 233 lines · 67 tokens per session scan A 2169cc2383eb
xeepy-python-twitter-guide is a skill published in the GitHub repository nirholas/three.ws (110 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 1,425 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
cadquery
Use when scripting parametric 3D CAD models in Python — programmatic part generation, parametric design optimization, STEP export. CadQuery: Python-based parametric CAD built on OCCT kernel with a fluent API.
freecad
Use when doing parametric 3D CAD modeling, BIM/architectural design, FEM simulation, CAM toolpath generation, or robot simulation with Python scripting. FreeCAD: the leading open-source parametric 3D CAD with Sketcher, Part, PartDesign, Arch, CAM, and FEM workbenches.
workflow-automation
Automate complex workflows and repetitive tasks using AI agents and tool integration. Use when user wants to create automated pipelines, integrate multiple services, or build task-specific agents.
doc-generator
Auto-generate API reference documentation from Python code.
security-linting
Automated security scanning for Python code using Bandit.
test-generator
A high-impact skill that automatically scaffolds pytest test files based on your Python source code. It parses your code structure (classes and functions) and generates corresponding test functions.