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 NachoLafuente/5050-gtm --skill gsc-lighthousegit clone --depth 1 https://github.com/NachoLafuente/5050-gtmWrote 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/nacholafuente/5050-gtm/gsc-lighthouse)<a href="https://agentmods.dev/skills/nacholafuente/5050-gtm/gsc-lighthouse"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/gsc-lighthouse/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/nacholafuente/5050-gtm/gsc-lighthouse"><img src="https://agentmods.dev/badge/skills/nacholafuente/5050-gtm/gsc-lighthouse.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 | $0.00112 | $0.01547 |
| Opus 5.5 | $0.00045 | $0.00619 |
| Sonnet 5.5 | $0.00022 | $0.00309 |
| Haiku 4.5 | $0.00011 | $0.00155 |
Grade C, and why
gsc-lighthouse scanned grade C with 2 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 2mo 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.
Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
Sign in with the Google Account that owns the GSC property. Credentials are saved to `~/.config/gcloud/application_default_credentials.json` and any Python script using `google.auth.default()` picks them up automatically Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **TBT spike > 300ms with stable LCP/FCP** → cold-start signature on serverless platforms (Cloud Run, Lambda@Edge). Warm with a curl loop, re-run. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSC + Lighthouse health check
Pulls Google Search Console (sitemap status, per-URL index coverage, 28-day search analytics) and runs Lighthouse via the PageSpeed Insights API on the top 10 pages by clicks. Produces a single report a non-technical person can read.
The point: most "SEO audit" tools throw a hundred warnings at you. This one tells you what's actually broken, calibrates against false positives, and groups fixes by theme so you can ship a single PR instead of a hundred.
Step 1: Ask the user 2 questions
-
What's your GSC property? (the verified site in Search Console)
sc-domain:example.com, Domain property (covers all subdomains and protocols)https://example.com/, URL-prefix property (one specific protocol + host)- If they don't know, link them to https://search.google.com/search-console and ask them to copy the property URL from the sidebar.
-
Do you have a
PAGESPEED_API_KEYconfigured? (.envor shell env)yes→ Lighthouse step runs.no / skip→ Lighthouse step is skipped, GSC report still ships. (SeeREADME.md"Setup: PSI API key" for the 3-command setup, ~30 seconds.)
That's it. No other config needed.
Step 2: Run the audit
cd skills/gsc-lighthouse
python audit.py --site "sc-domain:example.com"
Add --no-lighthouse to skip the PSI step. Add --top N to audit a different number of pages (default 10).
The script writes a JSON dump to ./out/audit-<date>.json and prints the structured report to stdout.
Step 3: Report
Read audit.py's stdout straight back to the user. Don't reformat unless they ask; the script's output is already structured for direct read.
If the user wants a TL;DR, summarize in this shape:
## GSC + Lighthouse: {today}
Sitemap: {N URLs, errors/warnings}
Indexing: {indexed} / {total}
Search (28d): {clicks}, {±%} vs prior 28d
Lighthouse: median perf {score}, median LCP {seconds}
Top 3 fixes (impact-ordered):
1. {theme}, {N pages affected}, est. {savings}
2. ...
3. ...
Bottom line: {one sentence}
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 127 lines · 112 tokens per session scan C 43046b20fabf
gsc-lighthouse is a skill published in the GitHub repository NachoLafuente/5050-gtm (3 stars, last pushed 4mo ago), licensed MIT. It adds 112 tokens to every session and 1,547 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 2 findings (reaches for credential files, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
gsc-lighthouse compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| gsc-lighthouseNachoLafuente/5050-gtm | Skill | 3 | 4mo ago | MIT | C | 112 | Claude Code, Codex |
| gt-email-infraGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 232 | Claude Code, Codex |
| gt-linkedin-contentGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 228 | Claude Code, Codex |
| gt-linkedin-outbounderGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 236 | Claude Code, Codex |
| email-infra-bounce-auditGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 157 | Claude Code |
| gt-cold-email-writerGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 181 | Claude Code, Codex |
| gt-gtm-strategy-advisorGrowth-Today/claude-skills | Skill | 6 | yesterday | MIT | A | 242 | Claude Code, Codex |