seo-performance-tracker

seo-performance-tracker is a skill for Claude Code from siddiqss/semantic-seo-suite. It costs 108 tokens per session (842 once invoked), scanned A, original, MIT.

A reporting skill that compares a site's topical map with Google Search Console (GSC), Google's data about search visibility and clicks. It measures performance by topic group, page, and search query.

In plain words
What is it for?
Use it to create reports on content performance, find pages worth improving, detect search-term overlap between pages, and discover topics the site has not covered.
Why use it?
It replaces guesses about search performance with data from the site's own Google account. It also highlights pages losing traffic, pages close to ranking higher, competing pages, and missing queries.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is python ../../scripts/gsc_client.py --site "<property>" --creds <path> \.

Part of the semantic-seo-suite plugin — 10 skills shipped together

Good fit Use it to create reports on content performance, find pages worth improving, detect search-term overlap between pages, and discover topics the site has not covered.

Compare 6 skills from other repositories ↓
Install

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.

Clone the repo
git clone --depth 1 https://github.com/siddiqss/semantic-seo-suite
agentmods
npx agentmods add skills/siddiqss/semantic-seo-suite/seo-performance-tracker

Made for: Claude Code.

Or install semantic-seo-suite, the plugin that ships this one along with the rest of its 10 skills.

Wrote 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.

agentmods badge for seo-performance-tracker

README.md
[![agentmods](https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/seo-performance-tracker/github.svg)](https://agentmods.dev/skills/siddiqss/semantic-seo-suite/seo-performance-tracker)
Your own site
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/seo-performance-tracker"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/seo-performance-tracker/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.

agentmods 80×15 button for seo-performance-tracker

Your own site · 80×15
<a href="https://agentmods.dev/skills/siddiqss/semantic-seo-suite/seo-performance-tracker"><img src="https://agentmods.dev/badge/skills/siddiqss/semantic-seo-suite/seo-performance-tracker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 842 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00108 $0.00842
Opus 5 $0.00054 $0.00421
Sonnet 5 $0.00022 $0.00168
Haiku 4.5 $0.00011 $0.00084

Measured 10d ago against content hash 4aa937ed0eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

seo-performance-tracker 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 10d 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.

skills/seo-performance-tracker/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

seo-performance-tracker

The measured feedback loop. It replaces guesswork (and the fabricated "Pillar Page Rank" that wrapper tools invent) with real Search Console data joined to the topical map. Every figure is measured (GSC) or derived (rollups) — never estimated.

Read first: ../../framework/topical-map-theory.md (pillars/priority), ../../framework/query-semantics.md (query networks → new nodes).

Preconditions

  • topical-map.json with urls on published nodes (the auditor sets these).
  • GSC configured: grounding.sources.gsc: true + credentials.gsc_credentials_path. If not configured, say so and do NOT invent metrics — spot-checking positions via web_search is unreliable; be explicit about that limitation.

Workflow

  1. Pull GSC data:

    python ../../scripts/gsc_client.py --site "<property>" --creds <path> \
      --start <date> --end <date> --dims query,page \
      --out brands/<slug>/data/gsc/pull.json
    # optional prior period for decay:
    python ../../scripts/gsc_client.py ... --start <earlier> --end <earlier> \
      --out brands/<slug>/data/gsc/prev.json
    
  2. Analyse against the map:

    python ../../scripts/gsc_analyze.py --gsc brands/<slug>/data/gsc/pull.json \
      [--gsc-prev brands/<slug>/data/gsc/prev.json] \
      --map brands/<slug>/topical-map.json --brand "<Brand>" \
      --out brands/<slug>/audits/<date>-performance.md
    

    Produces:

    • Pillar rollups — impressions/clicks/avg-position per pillar (derived). The honest Pillar Page Rank.
    • Striking-distance — queries at position 5–15 → quick-win update targets.
    • Measured cannibalization — one query landing on multiple pages (the strongest cannibalization signal; confirms/ː refutes the auditor's embedding guess).
    • Decaying pages — >30% click loss vs the prior period.
    • Uncovered queries — GSC queries not in any node's query network → candidate new map nodes.
  3. Feed the loop:

    • Add uncovered-query candidates to the map via topical-map-builder (as new nodes or as query-network additions to existing nodes).
    • Mark striking-distance and decaying nodes needs-update; push them up calendar.md.
    • Send confirmed measured-cannibalization pairs to semantic-site-auditor / linking-and-schema for consolidation/redirect.

Read the full file on GitHub · 74 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 74 lines · 108 tokens per session scan A 4aa937ed0eb4

Subscribe to this mod's changes

seo-performance-tracker is a skill published in the GitHub repository siddiqss/semantic-seo-suite (8 stars, last pushed 2mo ago), licensed MIT. It adds 108 tokens to every session and 842 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.