agentleFS
Sign inStart free
mrlong0129mrlong0129/wechat-article-fetcher/AGENTS.md

wechat-article-fetcher

AGENTS.md1 starsChanged 38 days agoMITView on GitHub

Instructions for coding agents (Claude Code, Cursor, Codex, etc.) that want to use this tool or work on this repo. Only uv is needed (curl -LsSf https://astral.sh/uv/install.sh | sh). No API keys or environment variables; defaults work as-is. Register the MCP server (Python 3.10+; the MCP SDK installs automatically): Cursor (~/.cursor/mcp.json or .cursor/mcp.json): MCP tools: fetch_wechat_article(url, format="markdown"|"text"|"both", max_chars=40000) and parse_wechat_html(html, url=None, format, max_chars). Install the skill (works even without the package):

  • Pipes a download into a shell
  • Installs packages
  • Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.

    Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.

  • In this repository2 other files it gives its agents.

The file

We split this AGENTS.md into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Only uv is needed (curl -LsSf https://astral.sh/uv/install.sh | sh).

    line 12
  2. Distinctive:

    Never add captcha solving or logged-in session reuse.

    line 51

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

AGENTS.md — wechat-article-fetcher

Instructions for coding agents (Claude Code, Cursor, Codex, etc.) that want to use this tool or work on this repo.

Use it in one step (no install, no config)

uvx --from git+https://github.com/mrlong0129/wechat-article-fetcher wxfetch <url>           # Markdown to stdout
uvx --from git+https://github.com/mrlong0129/wechat-article-fetcher wxfetch <url> -f json   # JSON

Only uv is needed (curl -LsSf https://astral.sh/uv/install.sh | sh). No API keys or environment variables; defaults work as-is.

Register the MCP server (Python 3.10+; the MCP SDK installs automatically):

claude mcp add wechat-article-fetcher -- uvx --from git+https://github.com/mrlong0129/wechat-article-fetcher wxfetch-mcp

Cursor (~/.cursor/mcp.json or .cursor/mcp.json):

{"mcpServers": {"wechat-article-fetcher": {"command": "uvx", "args": ["--from", "git+https://github.com/mrlong0129/wechat-article-fetcher", "wxfetch-mcp"]}}}

MCP tools: fetch_wechat_article(url, format="markdown"|"text"|"both", max_chars=40000) and parse_wechat_html(html, url=None, format, max_chars).

Install the skill (works even without the package):

mkdir -p ~/.claude/skills/wechat-article-fetcher && curl -fsSL https://raw.githubusercontent.com/mrlong0129/wechat-article-fetcher/main/skill/SKILL.md -o ~/.claude/skills/wechat-article-fetcher/SKILL.md

How to read results

  • CLI exit codes: 0 all ok, 1 at least one article failed (reason on stderr), 2 usage error.
  • MCP: ok: true → title, account_nickname, author, publish_time, content_markdown, images, extraction_method. ok: false → error is verification_required, article_unavailable (with reason), invalid_url or fetch_error.
  • On verification_required, do not retry in a loop or try to solve the captcha: tell the user, suggest opening the article in WeChat, or saving the page as HTML and using wxfetch --from-html page.html / parse_wechat_html.
  • For general (non-WeChat) web pages use the sibling project agent-web-fetch.

Work on this repo

uv venv && . .venv/bin/activate && uv pip install -e ".[dev]"
pytest              # offline, fast; must pass before committing
pytest -m live      # optional live smoke tests
  • Code: src/wxfetch/ — fetcher.py (UA fallback, retries), pagecheck.py (verification / deleted detection), extractor.py (candidates), render.py (HTML → Markdown), cli.py, mcp_server.py.
  • Fixtures must not contain third-party article text or real account IDs/tokens; use placeholders like the existing text_post_trimmed.html.
  • Never add captcha solving or logged-in session reuse.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free