Borrowing it
Nothing to install: this file belongs to prashishh/seo-geo-report-engine. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/prashishh/seo-geo-report-engine/main/.agents/skills/content-refresh/SKILL.mdgit clone --depth 1 https://github.com/prashishh/seo-geo-report-engineWrote 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/prashishh/seo-geo-report-engine/content-refresh)<a href="https://agentmods.dev/skills/prashishh/seo-geo-report-engine/content-refresh"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/content-refresh/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/prashishh/seo-geo-report-engine/content-refresh"><img src="https://agentmods.dev/badge/skills/prashishh/seo-geo-report-engine/content-refresh.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 | $0.00158 | $0.01597 |
| Opus 5 | $0.00079 | $0.00798 |
| Sonnet 5 | $0.00032 | $0.00319 |
| Haiku 4.5 | $0.00016 | $0.00160 |
Grade A, and why
content-refresh 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 9d 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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
content-refresh
Closes the loop on existing content. Other skills create pages; this one finds the ones that
are bleeding, decides what to do about each, and proves the decision was right next run. It fuses
two patterns: a baseline→compare→history regression gate (claude-seo seo-drift) and an
audit verdict of SHIP / FIX / BLOCK (seo-geo content-quality-auditor). Runs on the same CSV
cadence as rank-tracking (data/rank-history.csv) and kpi-dashboard (data/kpi-history.csv), so
it slots into a monthly retainer. Prefer Ahrefs MCP (knowledge/ahrefs-mcp-map.md); call doc on a
tool before first use. Methodology lives in playbooks/content-decay.md.
Methodology (PERCEIVE → ANALYZE → VALIDATE → ACT)
PERCEIVE — decay detection. Resolve the project (./bin/mkt config show --project <client>);
read client.yml for domain and locales. Find pages losing ground period-over-period (compare the
last ~90 days to the prior ~90, ending 2026-06-23):
site-explorer-pages-by-traffic— current organic traffic + value per URL (the inventory).gsc-pages-history(all pages) thengsc-page-history(per declining URL) — clicks, impressions, and average position over time. Decay = clicks down ≥20% or average position worsened ≥3 spots while impressions held (intent still there, we slipped) vs an SERP-wide volume collapse (don't refresh a page whose whole topic died — verify withkeywords-explorer-volume-history).- Tag each declining URL with a decay cause hypothesis: stale facts/date, SERP intent shift,
thinner than current top results, cannibalization, or lost links (
site-explorer-pages-by-backlinks).
ANALYZE — baseline + diff. For each candidate URL, snapshot ~13 on-page fields. Pull on-page
state from site-audit-page-content / site-audit-page-explorer (or WebFetch the live URL as
fallback): url, title, meta_description, canonical, h1, h2_count, h3_count, schema_types, word_count, internal_links, date_modified, content_hash, snapshot_date. Append the row to
projects/<client>/data/content-baselines.csv. Diff against this URL's most recent prior snapshot
and classify each changed field:
- CRITICAL — canonical changed/now points off-page, H1 lost/duplicated, schema removed, title
emptied,
noindexintroduced, word_count dropped >40%. These can cause the decay. - WARNING — title/meta rewritten,
date_modified>12 months stale (content rot), word_count down 15–40%, internal_links dropped materially, schema type changed. - INFO — minor copy edits (content_hash changed, structure intact), small link/count drift. First run = no prior snapshot, so there's no diff; record the baseline and judge decay on traffic signals alone.
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.
- 9d ago First seen · 93 lines · 158 tokens per session scan A ba7c90ab3f2a
content-refresh is a skill published in the GitHub repository prashishh/seo-geo-report-engine (5 stars, last pushed 2mo ago), licensed MIT. It adds 158 tokens to every session and 1,597 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 2026-08-31.
Other skills, from other repositories
content-amplifier
Use when the user asks to "amplify influencer content with paid media", "set up whitelisting or Spark Ads", "decide which posts to boost", "repurpose influencer content", "turn one video into multiple ads", or "build a UGC asset library"; produces (paid mode) a content-selection scorecard, a paid amplification…
campaign-planner
Use when the user asks to "plan an influencer campaign", "build a campaign blueprint", "track or close a creator campaign", or "record a late campaign correction"; produces the plan and, when requested, a non-canonical evidence tracker with scoped identity, publication, reconciliation, close, and reopen receipts. Not…
inbox-placement-monitor
Use when the user asks to "track where my emails are actually landing after I send", "read my seed-list inbox vs spam vs promotions results", "trend my Gmail Postmaster / Microsoft SNDS reputation", or "did placement drop after my last send"; produces a per-provider inbox/spam/promotions placement read, a domain/IP…
subject-line-lab
Use when the user asks to "generate subject line variants", "pre-score my subject lines", or "will this subject get truncated / trigger spam filters"; produces a labeled subject + preheader variant set and a per-variant heuristic pre-score card — spam-trigger flags, length/truncation across desktop + mobile…
email-sequence-designer
Use when the user asks to "design a welcome flow", "set up an abandoned-cart sequence", "build a light re-engagement branch inside a lifecycle flow", or "plan a cold-outbound sequence"; produces general lifecycle automation flows (welcome, cart, browse-abandon, post-purchase, in-flow re-engagement, B2B cold outbound)…
newsletter-monetization-planner
Use when the user asks to "monetize my newsletter", "build a sponsorship rate card", or "model paid-subscription revenue"; produces a revenue model (paid tiers, ad/sponsorship inventory + CPM/flat rate card, referral/boost loops), a list-growth ↔ revenue projection, and honest-offer / disclosure checks for the SEND-D…