4chan-reader

Browse 4chan boards and extract thread discussions into structured text files. Use when you need to fetch catalog information or specific thread content (including post text and file metadata) from 4chan boards like /a/, /vg/, /v/, etc.

Security Scan

The skill and its single script are coherent with the stated purpose (fetching 4chan catalogs and threads) and do not request unrelated credentials or perform unexpected network exfiltration.

Purpose & Capability

The name/description match the included script: the Python script fetches 4chan board catalog and thread HTML and extracts post text and file metadata. No unrelated services, binaries, or credentials are requested.

Instruction Scope

SKILL.md instructs only running the provided script. The script performs outbound HTTP requests to boards.4chan.org, extracts content, prints it, and optionally writes .txt files to a user-specified output directory. It does not read environment variables, system config, or other files beyond the optional output path.

Install Mechanism

No install spec — instruction-only plus a bundled script. Nothing is downloaded or installed from external URLs during setup.

Credentials

No environment variables, credentials, or config paths are required. The script only uses standard library modules and optional user-supplied output directory; there are no unexpected secret accesses.

Persistence & Privilege

always is false and the skill does not modify agent/system-wide config. The only persistence is optional writing of scraped thread text to a user-provided directory (expected for this tool).

Assessment

This skill appears to do exactly what it says: fetch 4chan pages and save extracted text. Before installing or running it, consider: (1) Source provenance — the package author is unknown; review the script (already included) and run it in a sandbox or container if you don't trust it. (2) Content risks — 4chan content can be NSFW, abusive, or illegal; avoid indexing or storing content that violates policy or law. (3) File write safety — when supplying output_root, don't point it at sensitive system directories; run as a non-privileged user. (4) Network policy — the script makes outbound HTTP requests to boards.4chan.org; ensure this is allowed on your network. The code does not access other credentials or exfiltrate files beyond what it fetches from 4chan.

This skill allows you to catalog and extract threads from 4chan boards into structured text.

Workflows

1. View Board Catalog

To see active threads and their reply counts on a board:

python3 scripts/chan_extractor.py catalog <board>

Output format: ThreadID|PostCount|TeaserText

2. Extract Thread Content

To read a specific thread and optionally save it:

python3 scripts/chan_extractor.py thread <board> <thread_id> [output_root_dir] [word_limit]

• output_root_dir (optional): If provided, saves content to <output_root_dir>/<board>_<timestamp>/<thread_id>.txt.
• word_limit (optional): Limits each line of post text to the specified number of words.

Details

• Scripts: Uses chan_extractor.py for all operations.