Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/oyusypenko/creonpx agentmods add skills/oyusypenko/creo/creo-gscWrote 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/oyusypenko/creo/creo-gsc)<a href="https://agentmods.dev/skills/oyusypenko/creo/creo-gsc"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-gsc/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/oyusypenko/creo/creo-gsc"><img src="https://agentmods.dev/badge/skills/oyusypenko/creo/creo-gsc.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 | $0.00108 | $0.02000 |
| Opus 5 | $0.00054 | $0.01000 |
| Sonnet 5 | $0.00022 | $0.00400 |
| Haiku 4.5 | $0.00011 | $0.00200 |
Grade A, and why
creo-gsc 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.
How it starts
The opening of the file, as written. The whole thing — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creo GSC - Google Search Console & SEO Analysis
Commands
| Command | Description |
|---|---|
/creo gsc list-sites |
List all Search Console properties |
/creo gsc inspect <url> |
Inspect a URL's indexation status |
/creo gsc analytics |
Get search analytics (clicks, impressions, CTR) |
/creo gsc security <url> |
Analyze HTTP security headers |
/creo gsc onpage <url> |
On-page SEO analysis (title, meta, headings, images) |
/creo gsc schema <url> |
Validate structured data (JSON-LD) |
/creo gsc hreflang <url> |
Validate hreflang implementation |
/creo gsc full-seo <url> |
Run all 9 page analyzers on a URL |
/creo gsc site-audit <url> |
Crawl and audit entire website |
/creo gsc ui-export |
Export Page Indexing drilldown CSVs via Playwright (UI-only data the API cannot enumerate) |
/creo gsc validate-fix |
Click GSC's "Validate Fix" button via Playwright (no API exists for it) |
/creo gsc open [<surface>] |
Open a Search Console report in the user's browser (overview, performance, indexing, sitemaps, settings, inspect ) and read/operate it together |
Browser-first operation
The API is preferred for data it can serve, but this skill is NOT API-only. With browser tools available, open Search Console directly in the user's signed-in Chrome — navigate to the exact report via the deep-link map in the agent doc, read it, click drilldowns, export CSVs, and perform configuration (submit sitemaps, manage users) together with the user. The user must already be signed in; never attempt a scripted Google login; confirm before any destructive click. Use the UI as ground truth whenever API results look wrong.
Running gsc_toolkit CLI Commands
The toolkit is a Python package. All commands are executed via:
# Find the installed toolkit
GSC_DIR="${HOME}/.claude/skills/creo-gsc"
# Activate the virtual environment (if installed with venv)
source "${GSC_DIR}/.venv/bin/activate" 2>/dev/null || true
# Run commands
python -m gsc_toolkit <command> [options]
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 · 175 lines · 108 tokens per session scan A 496862956945
creo-gsc is a skill published in the GitHub repository oyusypenko/creo (4 stars, last pushed 2d ago), licensed MIT. It adds 108 tokens to every session and 2,000 once invoked, about $0.0005 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
agent-loop-ext
Crash-resilient external agent loop with state persistence and CI/CD integration.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
ci-all
Full CI pipeline: run local tests, type check, push branch, and return the pipeline URL. The only command you need before opening a PR.
ci-pipeline
Push current branch and return the pipeline tracking URL (GitLab or GitHub Actions).
ci-status
Show current pipeline status for the active branch (GitLab CI or GitHub Actions).
devops
DevOps patterns: containerization, CI/CD, deployment strategies, monitoring. Use when containerizing apps, setting up pipelines, or deploying services.