# robots.txt for Mission Green
# https://missiongreen.com.au

User-agent: *
Allow: /
# Internal blog tooling — not for indexing
Disallow: /blog-studio
Disallow: /blog-studio.html
Disallow: /blog-template
Disallow: /blog-template.html

# Internal design/dev labs — not for indexing
Disallow: /glass-lab
Disallow: /glass-lab.html
Disallow: /motion-lab
Disallow: /motion-lab.html

# ── AI / answer-engine crawlers: explicitly welcome ──────────────
# We want to be retrievable and citable in AI answers (Google AI Mode,
# ChatGPT, Claude, Perplexity, Copilot). Curated index: /llms.txt

User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: cohere-ai
Allow: /

# Sitemap
Sitemap: https://missiongreen.com.au/sitemap.xml
# The Energy Wire — RSS feed of dated, sourced rebate/price/policy changes — is
# deliberately NOT declared as a sitemap here, and must not be added back.
#
# Search engines do accept an RSS feed as a sitemap, which is why it was listed. The
# catch is what that means: every <link> in the feed becomes a URL Google is being
# asked to index. Every item in this feed links to an ANCHOR on one page
# (/news#vic-veu-ceiling-insulation-2026 and 144 others), so Google dutifully
# discovered 137 "pages" that are all the same page and correctly refused to index a
# single one of them. On 10 Sep 2026 that was 137 of the 138 URLs sitting in Search
# Console's "Discovered - currently not indexed" — a report that looked like 138
# missing pages and was actually one orphan plus a feed pointed at itself.
#
# The feed itself is fine and stays exactly as it is: unique guid, fragment link so a
# reader's client jumps to the item. It is a feed for readers, not a list of pages for
# a crawler. /news is in sitemap.xml and that is how it gets indexed.

# LLM-friendly index
# https://missiongreen.com.au/llms.txt