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 skills add acamolese/google-search-console-mcp --skill gsc-indexing-auditgit clone --depth 1 https://github.com/acamolese/google-search-console-mcpWrote 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/acamolese/google-search-console-mcp/gsc-indexing-audit)<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-indexing-audit"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-indexing-audit/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-indexing-audit"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-indexing-audit.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00064 | $0.00529 |
| Opus 5 | $0.00032 | $0.00264 |
| Sonnet 5 | $0.00013 | $0.00106 |
| Haiku 4.5 | $0.00006 | $0.00053 |
Grade A, and why
gsc-indexing-audit 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 12d ago.
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.
What it actually says
Indexing audit
1. Choose the URLs
Do not inspect the whole site. Start with the pages that matter:
gsc_query with dimensions="page", period="last_28_days", row_limit=20.
If the user names specific URLs, use theirs instead.
2. Inspect
gsc_indexing_issues with those URLs. Limits worth knowing:
- 100 URLs per call.
- The API allows 600 inspections per minute and 2,000 per day per property. On a large site that daily cap is the real constraint; say so before running a big batch.
Then gsc_sitemaps for the submitted sitemaps.
3. Group by cause, not by URL
The coverage_state is what matters, and each value needs a different fix:
- Duplicate, Google chose different canonical than user — Google disagrees
with the declared canonical. Check what it picked (
google_canonicalagainstuser_canonical) and whether the content is genuinely distinct. - Crawled - currently not indexed — Google saw it and passed. This is a content-quality signal, not a technical one. More internal links will not fix a thin page.
- Discovered - currently not indexed — Google knows the URL but has not fetched it. Usually crawl budget: too many low-value URLs competing for attention.
- Blocked by robots.txt / noindex — deliberate or a mistake. Confirm which before recommending anything.
- Page fetch failure / soft 404 — a server problem. Reproduce it before blaming Google.
4. Sitemaps
Report any sitemap with errors or warnings, and compare its submitted count against its indexed count. A wide gap usually means the sitemap lists URLs that redirect, 404 or carry noindex.
5. Deliver
A prioritised list: what is broken, how many pages it affects, what to change, and how to verify. Note that indexing changes take days to weeks to show, so a recheck belongs two to three weeks out, not tomorrow.
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.
- 12d ago First seen · 56 lines · 64 tokens per session scan A 2e8c9c2774b3
gsc-indexing-audit is a skill published in the GitHub repository acamolese/google-search-console-mcp (8 stars, last pushed 21d ago), licensed MIT. It adds 64 tokens to every session and 529 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 2026-08-31.
Other skills, from other repositories
uap-pulse
Search and map 350 official-government UAP/UFO records spanning 1944–2026: all four U.S. Pentagon PURSUE releases plus curated archives from 12 nations.
2ools
Use 2ools through its remote MCP server to turn chat-made HTML into a temporary public preview, or—after OAuth—to build, version, review, share, and export durable projects.
garmin
Unofficial Garmin Connect data for AI agents. Prefer MCP tools if connected; otherwise the package CLI. Use when the user wants Garmin data or actions through an agent.
uap-pulse
UAP Pulse. Prefer MCP tools if connected; otherwise the package CLI.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.