A content audit gives every page on your site one verdict: keep it, refresh it, merge it into a sibling, or prune it. Claude can do the sorting for you, but only if it can see which pages Google sends people to, and that means connecting your Search Console to it.
Most audits are done by reading the pages, and reading is the wrong evidence. The page that reads worst is often earning, and the page that reads fine may have lost half its clicks since last year. Search Console keeps 16 months of data, enough to compare this quarter with the same quarter a year ago for every page, and that comparison is the audit.
We run this audit with the tool we build, ContextBolt SEO, which reads your Search Console and the live results page from inside Claude. The Search Console half costs nothing.
- A content audit gives every page one of four verdicts, keep, refresh, merge or prune. The evidence is each page’s clicks and impressions this quarter against the same quarter a year ago, from your own Search Console.
- Claude cannot see your Search Console on its own. Connect it through MCP and it reads the real rows. ContextBolt SEO is a full SEO toolkit that runs inside the agent, pulls both windows for free, and reads the live top ten for one credit when a refresh needs it.
- Search Console hides the prune column. A page with zero impressions has no row, so the audit starts from your sitemap, not from the report.
- A 184-page audit costs about 16 credits, all of them on the refresh shortlist. The 7-day free trial includes 100.
What does a content audit with Claude involve?
Ask Claude to audit your content with nothing connected and it reads the pages and grades them: thin, outdated, duplicate, off-topic. The grades sound reasonable and none is a verdict, because Claude has no idea which pages Google is showing.
The fix is MCP, the open standard Anthropic introduced in late 2024 for connecting an agent to live data. Connect Claude to your Search Console through an MCP server and it reads the real rows for every page in both windows, joins them on URL, and applies the same four rules to 184 pages without getting bored. The tools fetch, Claude sorts and drafts, and you read the verdicts and decide. The one-time setup is in connecting Search Console to an AI agent.
The four verdicts:
Keep: The page earns what it earned a year ago, or more. Leave it alone.
Refresh: The page still earns impressions but its clicks fell. The fix is a section, a title or a first screen, not a rewrite.
Merge: Two of your pages do one job, either sharing queries or both thin on one topic. One page should survive.
Prune: The page has earned nothing in 16 months and nobody links to it.
Anything under six months old isn’t audited. It has no year-ago window to compare against and probably hasn’t settled where it will rank.
Step 1: Start from the sitemap
Say you run a site about indoor plants. It’s four years old and the sitemap lists 184 pages. The Performance report for the last 90 days shows 121 pages with at least one impression and 64 with at least one click. The other 63 aren’t in the report at all, because a page Google never showed has no row.
So a report-first audit can never find the pages that most need a verdict. Have Claude read your sitemap and list every URL instead, and mark anything first published in the last six months as too new. The sitemap’s lastmod moves on every edit, so take the date from the page’s own byline or dateline. On the plant site that returns 184 URLs, 11 of them too new, so 173 go into the audit.
Step 2: Pull two windows a year apart
Pull clicks, impressions and position by page for the last 90 complete days, then for the same 90 days one year earlier, and join the two on URL. Search Console has kept 16 months of data since 2018, and Google’s stated reason was to “enable year-over-year comparisons”.
In ContextBolt SEO the tool is search_console_performance, which takes exact start and end dates and one dimension, and costs no credits. Ask for the page dimension and the maximum 100 rows. Google’s Search Analytics API returns rows sorted by clicks, descending, so each call gives your top 100 pages. The data lags two to three days, so end the current window three days ago rather than today.
On the plant site the two top-100 lists overlap into about 130 URLs, which leaves 43 sitemap pages in neither. Each of those needs its own exact-page call over the last 480 days, which covers the 16 months Search Console keeps. A page that returns no rows across all of it has been shown for no query in 16 months. That is the prune test, and it can only run this way, because it needs the page’s name from the sitemap before Search Console can say nothing about it.
Step 3: Give every page one verdict
These thresholds are ours, a starting point only. Move them if your site is much bigger or smaller.
| Verdict | The rule | What it means |
|---|---|---|
| KEEP | Clicks within 25% of a year ago, or up | Working. Do not let a rewrite near it |
| REFRESH | Clicks down 25% or more, still earning impressions | Something changed. Diagnose the shape, then fix that section |
| MERGE | Two or more pages earning on the same queries, or two thin pages on one topic | One page should survive and carry both |
| PRUNE | ZERO across 480 days, and nobody links to it | Remove it. A 404 or a 410, and Google treats them the same |
| TOO NEW | Published in the last six months | Not audited. Next quarter |
Two pages sharing a query isn’t visible in a by-page table, so the merge rule needs one more free pull. For every KEEP and REFRESH page, ask for its top 20 queries in the current window and look for queries that appear under more than one URL.
On the plant site the counts come back as 115 KEEP, 14 REFRESH, 6 MERGE (three pairs) and 38 PRUNE candidates, with the 11 TOO NEW pages set aside. Five of the 43 tail pages earned a trickle and landed in KEEP. Here are six rows, because the shapes are what you learn to read.
| Page | Clicks (now / year ago) | Position (now / year ago) | Verdict |
|---|---|---|---|
| /monstera-yellow-leaves/ | 610 / 1,240 | 7.9 / 4.1 | REFRESH, position slipped |
| /pothos-vs-philodendron/ | 90 / 310 | 3.6 / 3.2 | REFRESH, clicks fell at the same position |
| /fiddle-leaf-fig-care/ | 420 / 900 | 6.0 / 5.2 | REFRESH, impressions halved |
| /best-grow-lights/ | 175 / 180 | 8.8 / 8.6 | KEEP |
| /how-to-water-succulents/ and /succulent-watering-schedule/ | 40 and 35 | 11.3 and 12.8 | MERGE, same queries |
| /plant-of-the-month-march-2023/ | 0 (480 days) | none | PRUNE candidate |
Step 4: Diagnose each refresh
A page whose clicks fell by a quarter or more fits one of three shapes, and the two windows say which.
Position slipped, impressions steady or up. The monstera page went from 4.1 to 7.9 while Google showed it more often than before. Demand is fine, and a better page arrived above it. Read the live results page, because the fix depends on what took the slot. serp_overview returns the top ten for one credit and page_audit reads your own page for one more, worst issue first. If the page now sits between position 5 and 20, striking distance keywords with Claude is the follow-up, and this audit’s output is the list it starts from.
Clicks fell, position and impressions held. The pothos comparison is at 3.6, Google shows it as often as ever, and it earns a third of the clicks it used to. The results page changed, and on a comparison query the first thing to check is an AI Overview. We measured this on our own site in AI Overview click loss. Give the page something the summary can’t carry, such as a table or a tool, rather than more words. Some of those clicks aren’t coming back.
Impressions fell, position held. The fiddle-leaf page still ranks about where it did, and Google shows it for half as many searches. Either demand moved or Google stopped showing the page for queries it used to hold. Pull the page’s query list in both windows and diff them. The queries that vanished point at the section that went stale. On the plant site, every query ending in “2025” disappeared, so the fix was the dated product section.
A refresh rewrites the section that changed, not the page. A page that still ranks is ranking on something, and a rewrite that changes its angle throws that away to fix a problem that lived in one table. The content brief guide covers writing the missing section from the results page, and the on-page audit guide explains each page_audit finding.
Step 5: Merge and prune
Merge. Two pages earning on the same queries is keyword cannibalization, and the cannibalization guide covers choosing the survivor from the numbers. For two thin pages on one topic with no shared queries, keep the page with more clicks, fold the other’s one useful section into it, and redirect the weaker URL. Google’s documentation on consolidating duplicate URLs lists redirects first among the methods, as “a strong signal that the target of the redirect should become canonical”. A merge without the redirect is a prune with extra steps.
Prune. Thirty-eight candidates on the plant site is the first-pass number, because ZERO across 480 days is the first test and not the last.
The second test is links. A page nobody searches for can still be linked to, and you don’t throw away a referring domain to tidy a sitemap. Open Search Console’s Links report and read the top linked pages from external sites. Our backlink tools read a domain’s profile, not a single page’s, so this is a click in Search Console. Any candidate with a real external link becomes a KEEP or a MERGE.
The third test is internal. Ask Claude to find every page that links to the candidate, and if a page you’re keeping depends on it, merge the useful part in first. On the plant site, 38 became 19, and 12 of those were monthly announcement pages from the site’s first year.
Then return a 404 or a 410. Google’s documentation on HTTP status codes says all 4xx errors except 429 are treated the same, and that the indexing pipeline removes a previously indexed URL. Don’t redirect a pruned page to the homepage, since a redirect says the target is the same page. Redirect only to a page that answers the same question, which is a merge.
Prune is the verdict that gets the most attention and gets the least payoff. Google said in its 2022 helpful content announcement that removing unhelpful content “could help the rankings of your other content”, and that sites with lots of unhelpful content “may notice a stronger effect”. By March 2024 that system was folded into core ranking, and Google says its ranking systems are “primarily designed to work on the page level”. Pruning is site-wide hygiene for sites carrying many thin pages. For most sites the value is in the refresh column.
Step 6: Verify the changes
Inspect each refreshed or redirected URL to confirm Google recrawled it. Because every lookup saves to your SEO Dashboard, next quarter’s audit starts from what you found, and you can re-run the two-window pull then.
The whole audit as one prompt
Once you’ve walked it by hand, the audit collapses into one instruction worth saving and running each quarter.
Run a content audit on my site from Search Console.
1. Read my sitemap and list every URL. Anything under six months old
is TOO NEW.
2. Pull clicks, impressions and position by page for the 90 days
ending three days ago, and for the same 90 days a year earlier,
100 rows each. Join them on URL. For sitemap pages in neither
table, pull each one's own 480-day row.
3. Verdict every page: KEEP (clicks within 25% or up), REFRESH
(clicks down 25%+, still earning impressions), PRUNE (no data in
480 days), TOO NEW. Then pull the top 20 queries for each KEEP and
REFRESH page and re-tag any pages that share a query as MERGE.
4. For each REFRESH page, name the shape: SLIPPED, FEATURE or DEMAND.
For DEMAND pages, list the queries that disappeared. For SLIPPED
pages, pull the live top 10 and audit the page.
5. Give me the counts, the table sorted by verdict then clicks lost,
and a drafted change for each REFRESH page. Change only the
section that the numbers point at.
Tell me the credits this will cost before you start. Only step 4
costs credits.
The agent quotes the cost, you say go, and everything that came from your own Search Console stays free however many pages the site has.
What does a content audit with Claude cost?
Every tool has a fixed price, so the bill adds up before you start. The example is the plant site: 173 audited pages, 14 refreshes, 8 of them SLIPPED.
| Step | Tool | Calls | Credits |
|---|---|---|---|
| Read the sitemap | Claude’s own URL fetch | 1 | 0 |
| Two windows by page | search_console_performance | 2 | 0 |
| The tail, one exact page at a time | search_console_performance | 43 | 0 |
| Query lists for the merge check | search_console_performance | One per KEEP and REFRESH page, 129 | 0 |
| Live top 10 for SLIPPED pages | serp_overview | 8 | 8 |
| Page audit for SLIPPED pages | page_audit | 8 | 8 |
| Verify recrawl after the changes | inspect_url | One per changed URL, 20 | 0 |
| Total | 16 |
That is 16 credits out of 1,000 a month on the $35 plan, and the 7-day free trial comes with 100. The verdicts come from your own Search Console, which costs nothing to read, and the paid calls are the live reads on the eight pages where something on the results page took the slot.
ContextBolt SEO is a hosted SEO MCP server. Start the trial, paste one URL into Claude, Cursor, Codex or ChatGPT, connect your Google Search Console property once, and ask in plain language. Every lookup saves to your SEO Dashboard, so next quarter’s audit starts from what you found.
What are the limits of this audit?
The performance call returns 100 rows, in click order. On a site with a few hundred pages the tail runs one page at a time, which is free and slow. On a site with thousands of pages it’s the wrong shape, so audit one folder of the sitemap per pass.
Position is an average and a year is a long time. A page at 6.0 now and 5.2 a year ago may be at 3 on desktop and 12 on mobile. Before you call a page KEEP on a steady position, break the current window down by device, which the same call does for free. A year-ago window that straddles a redesign, a domain move or a core update compares two different sites, so read the trend on the date dimension instead.
Never automate the verdict. The pull can run on a schedule, the way the SEO automation guide sets up its monthly decay loop. The verdict is a decision a person makes with the table in front of them, because a MERGE done as a PRUNE loses a page that was half of something.