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 OpenClaudia/openclaudia-skills --skill gsc-portfolio-auditgit clone --depth 1 https://github.com/OpenClaudia/openclaudia-skillsWrote 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/openclaudia/openclaudia-skills/gsc-portfolio-audit)<a href="https://agentmods.dev/skills/openclaudia/openclaudia-skills/gsc-portfolio-audit"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/gsc-portfolio-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/openclaudia/openclaudia-skills/gsc-portfolio-audit"><img src="https://agentmods.dev/badge/skills/openclaudia/openclaudia-skills/gsc-portfolio-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00158 | $0.00951 |
| Opus 5 | $0.00079 | $0.00476 |
| Sonnet 5 | $0.00032 | $0.00190 |
| Haiku 4.5 | $0.00016 | $0.00095 |
Grade A, and why
gsc-portfolio-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 13d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GSC Portfolio Audit
Answers "how is everything doing?" across every property on a Search Console account, which is the question the per-site tooling can't answer without dozens of manual exports.
Setup
Requires an OAuth refresh token with https://www.googleapis.com/auth/webmasters.readonly:
export GOOGLE_GSC_CLIENT_ID=... # or GOOGLE_CLIENT_ID
export GOOGLE_GSC_CLIENT_SECRET=... # or GOOGLE_CLIENT_SECRET
export GOOGLE_REFRESH_TOKEN=...
export GSC_EXCLUDE="olddomain.com" # optional, comma-separated
pip install requests
The most common setup failure is unauthorized_client on token refresh. It means the refresh token was issued for a different OAuth client than the id/secret you paired with it. Accounts that have added Google integrations over time usually have several clients; match the pair that minted the token.
Run it
python3 scripts/audit_gsc.py # full: ranking + keyword diff for the top 12
python3 scripts/audit_gsc.py portfolio # just the ranked table
python3 scripts/audit_gsc.py queries --site sc-domain:example.com
python3 scripts/audit_gsc.py --days 90 # quarter over quarter
Flags: --days (window, compared against the window immediately before it), --site (repeatable), --top, --limit, --min-clicks.
Sections and what they mean
| Section | Read it as |
|---|---|
| NEW | queries with zero clicks last period. Where growth is actually coming from. |
| RISING | up ≥50%. Check whether position moved too — if it didn't, demand rose, not your ranking. |
| DROPPING | down ≥40% off a real base. Position tells you which kind: rank fell = ranking loss; rank held but clicks collapsed = something took the clicks above you (AI Overview, a new SERP feature, or the query changed shape). |
| LOST | ranked before, no data now. |
| CTR GAP | ≥1,500 impressions, top 10, under 2% CTR. Title and description rewrites, the cheapest wins available. |
Interpreting
- Report clicks first, impressions second. One large property can swing portfolio impressions enough to mask that everything else grew.
- Separate brand from non-brand. A site whose entire keyword set is its own name (or misspellings of a competitor's) has no acquisition engine, however good the click count looks. Say so plainly in the report.
- A whole-site collapse on its own head term is usually not SEO. Check ownership before diagnosing rankings:
whois <domain> | grep -i "registrar\|updated date"plus whether it still resolves. Expired, transferred, or disputed domains produce a textbook ranking cliff that no amount of SEO work will fix. - "new" in the portfolio table means zero clicks in the prior window, which for a recently launched site is a launch, not a data gap.
- Don't skip queries in languages you can't read. On multi-market sites the growth is usually in non-English long tail; translate the interesting ones rather than filtering them out.
- A property returning 403 is verified for listing but not for search analytics. The script reports it instead of hiding it.
What ships with it
1 file 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.
- 13d ago First seen · 68 lines · 158 tokens per session scan A 02ea91177783
gsc-portfolio-audit is a skill published in the GitHub repository OpenClaudia/openclaudia-skills (689 stars, last pushed yesterday), licensed MIT. It adds 158 tokens to every session and 951 once invoked, about $0.0008 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…