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-weekly-reportgit 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-weekly-report)<a href="https://agentmods.dev/skills/acamolese/google-search-console-mcp/gsc-weekly-report"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-weekly-report/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-weekly-report"><img src="https://agentmods.dev/badge/skills/acamolese/google-search-console-mcp/gsc-weekly-report.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 | $0.00058 | $0.00553 |
| Opus 5 | $0.00029 | $0.00277 |
| Sonnet 5 | $0.00012 | $0.00111 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
gsc-weekly-report 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 11d 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
Weekly Search Console review
1. Pick the property
If the user did not name one, call gsc_sites and ask which property they mean.
Property strings are exact: sc-domain:example.com for a domain property,
https://example.com/ with the trailing slash for a URL-prefix one.
If several properties are in play, gsc_portfolio ranks them worst first in one
call; start with whatever it flags critical.
2. Gather
Run these, in order:
gsc_performance_overview—period="last_7_days",compare_previous=truegsc_alerts—window_days=7gsc_traffic_drops—period="last_7_days"gsc_quick_wins—period="last_28_days"
Use 28 days for the quick wins even in a weekly review: a single week rarely holds enough impressions to size an opportunity.
3. Write it
- Headline: clicks, impressions, CTR and average position, each with its
change. Copy the numbers from the tool output; do not recompute them. A
negative
position_deltais an improvement. - What moved: worst first. Use the
diagnosiscolumn to say whether it was a ranking loss, falling demand, a collapsed CTR or a page dropping out. These need different fixes. If the diagnosis ismixed, say the data does not separate the causes rather than picking one. - What to do: the two or three opportunities worth this week's effort, each with the uplift the tool estimated.
Never attribute a drop to a core update, a competitor or a site change unless the user brought that context. Search Console shows what happened, not why.
If nothing crossed the thresholds, say the week was quiet and stop. The meta line of each response names the thresholds that were applied; quote them if the user asks why something is missing.
Caveats worth stating
data_state=allincludes today's partial data, matching the Search Console UI. The last day of any range is usually incomplete.- Search Console keeps 16 months. Anything older is not available at any price.
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.
- 11d ago First seen · 53 lines · 58 tokens per session scan A 9ebf71f34dfc
gsc-weekly-report is a skill published in the GitHub repository acamolese/google-search-console-mcp (8 stars, last pushed 20d ago), licensed MIT. It adds 58 tokens to every session and 553 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.