x-tweet-fetcher

What the source does

• FilesystemNone observedNo reads or writes in the source
• NetworkDeclared6 observations
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: no behavioural pass.

1. **No more hardcoded public Nitter default for browser mode.** v1 defaulted `--nitter` to `nitter.tiekoetter.com`, which contradicted the README's own advice. v2 defaults to your `XTF_NITTER` config

export XTF_NITTER=http://127.0.0.1:8788

| `XTF_NITTER` | `http://127.0.0.1:8788` | Comma-separated Nitter instances, tried in order with failover |

export XTF_NITTER=http://127.0.0.1:8788

export XTF_NITTER=http://127.0.0.1:8788,https://your-backup-instance.example

<div class="show-more"><a href="?cursor=DAAKCgABHMetRvu__qkLAAIAAAGcRW1QQzZ3QUFBZlEvZ0dKTjB2R3AvQUFBQUNRY3NaU3BSWmNBWFJwcE1Ya1JHNUVuSEQ5Z3QvcFdZTW9ZazNYMWhCYlJFaHg3SFg3YjJxRmdIRDdtRnkrYk1XTUo0TGxVeWhT

Audit 0.4.1 · source sha bf9a3c9c4f4b · 21 Oct 2026Report an issue or request a re-scan

• Publisherythx-101 GitHub userOwner of the repository this skill is read from
• Source folderythx-101/x-tweet-fetcherThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictbf9a3c9c4f4bA new audit runs when the source changes
• Repository statusNot archivedLast push 6 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Fetch tweets, replies, timelines, search results, X Lists, and X Articles from X/Twitter without login or API keys. Single tweets: zero dependencies (FxTwitter). Timelines/search/replies: a Nitter instance (XTF_NITTER).…

---
name: x-tweet-fetcher
description: >
  Fetch tweets, replies, timelines, search results, X Lists, and X Articles
  from X/Twitter without login or API keys. Single tweets: zero dependencies
  (FxTwitter). Timelines/search/replies: a Nitter instance (XTF_NITTER).
  Lists/Articles: a browser driver (Camofox or Playwright). Unified JSON
  schema across all backends; machine-readable error_code for agent branching.
  Field reports and agent-use questions: Agent Waystation #22 Teahouse:
  https://github.com/ythx-101/openclaw-qa/discussions/22
---

# X Tweet Fetcher

Fetch tweets from X/Twitter without authentication. For agent-use stories, failures, and field reports, start from **[#22 Teahouse / 茶座](https://github.com/ythx-101/openclaw-qa/discussions/22)**.

## Feature Overview

| Feature | Command | Dependencies |
|---------|---------|-------------|
| Single tweet | `xtf --url <tweet_url>` | None (zero deps) |
| Reply threads | `xtf --url <tweet_url> --replies` | Nitter or browser |
| User timeline | `xtf --user <username> --limit 50` | Nitter or browser |
| Search | `xtf --search "<query>"` | Nitter |
| User profile | `xtf --user-info <username>` | None (zero deps) |
| X List | `xtf --list <list_url_or_id>` | Browser (Camofox/Playwright) |
| X Article | `xtf --article <url_or_id>` | Browser (Camofox/Playwright) |
| Mentions monitor | `xtf --monitor @<username>` | Nitter or browser |

`python3 scripts/fetch_tweet.py` accepts the same flags (v1-compatible entry point).

## Basic Usage (Zero Dependencies)

```bash
# JSON output (default)
xtf --url https://x.com/user/status/1234567890

# Human-readable
xtf --url https://x.com/user/status/1234567890 --text-only

# Output covers: text, author, stats (likes/retweets/views), media URLs,
# quoted tweets, and full article text for tweet-embedded articles.
```

## Timeline / Search / Replies (Nitter)

```bash
export XTF_NITTER=http://127.0.0.1:8788   # your instance; comma-separate for failover
xtf --user elonmusk --limit 20
xtf --search "openclaw" --limit 10
xtf --url https://x.com/user/status/123 --replies
```

Backend selection: `--backend auto` (default, Nitter first then browser), `--backend nitter`, `--backend browser`.

## Lists & Articles (Browser)

```bash
# Camofox running on localhost:9377 (default), or:
export XTF_BROWSER=playwright

xtf --list https://x.com/i/lists/1455045069516357634 --limit 30
xtf --article https://x.com/i/article/2011779830157557760
```

Note: full X Article text requires X login; without it you get title + public preview (`is_partial: true`).

## Mentions Monitor (cron-friendly)

```bash
xtf --monitor @yourhandle
# exit 0 = no new mentions, 1 = new mentions found, 2 = setup error
# First run builds a baseline silently; later runs report only new URLs.
```

## Error Handling for Agents

Every error result includes `error` (message) and `error_code`:
`invalid_input` · `not_found` · `rate_limited` · `upstream_down` · `backend_unavailable` · `all_backends_failed` (with per-backend `error_causes`).

## Python API

```python
from xtf import Router
router = Router()
tweets = router.fetch_timeline("elonmusk", limit=20)  # list[Tweet]
print(tweets[0].to_dict())
```

## Directory Structure

```
src/xtf/
├── backends/   # fxtwitter.py, nitter.py, browser.py
├── parsers/    # pure parsing functions, fixture-tested
├── router.py   # auto-fallback
├── monitor.py  # mentions monitor
└── cli.py      # the `xtf` command
scripts/fetch_tweet.py  # v1-compatible shim
```

Looking for Chinese-platform fetching (Weibo/Bilibili/WeChat) or tweet growth tracking? Those moved out of this repo in v2 — see MIGRATION.md.

Excerpt, first 3,633 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

1. 2026-10-21
   ✓SAFE B 89 / 100

   first audit · source bf9a3c9c4f4b

Questions about x-tweet-fetcher

• github.com/ythx-101/x-tweet-fetcher — the audited source at commit bf9a3c9c4f4b and every finding aboveObserved · 21 Oct 2026

Spotted something wrong? Report a correction · Methodology