drift-detector

drift-detector is a skill for Claude Code from XuanRanL/loamwright-SEO-Skill. It costs 54 tokens per session (482 once invoked), scanned A, original, Apache-2.0.

A website monitoring tool that compares the current site with a saved SQLite snapshot using 17 checks for SEO, links, structured data, security, and AI-search visibility.

In plain words
What is it for?
It helps take a baseline, compare later versions, produce a dated report with severity levels, and identify changes such as lost AI Overview citations or changed robots.txt rules.
Why use it?
It reveals important changes that may have happened after an update, such as missing schema, altered titles, broken HTTPS, new broken links, or a noindex setting.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the xuanran-seo-blog-writer plugin — 68 skills, 34 agents, 4 hooks shipped together

Good fit It helps take a baseline, compare later versions, produce a dated report with severity levels, and identify changes such as lost AI Overview citations or changed robots.txt rules.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/xuanranl/loamwright-seo-skill/drift-detector
Install

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.

Any agent
npx skills add XuanRanL/loamwright-SEO-Skill --skill drift-detector
Clone the repo
git clone --depth 1 https://github.com/XuanRanL/loamwright-SEO-Skill

Made for: Claude Code.

Or install xuanran-seo-blog-writer, the plugin that ships this one along with the rest of its 68 skills, 34 agents, 4 hooks.

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 drift-detector

README.md
[![agentmods](https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/drift-detector/github.svg)](https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/drift-detector)
Your own site
<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/drift-detector"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/drift-detector/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 drift-detector

Your own site · 80×15
<a href="https://agentmods.dev/skills/xuanranl/loamwright-seo-skill/drift-detector"><img src="https://agentmods.dev/badge/skills/xuanranl/loamwright-seo-skill/drift-detector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 482 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00054 $0.00482
Opus 5 $0.00027 $0.00241
Sonnet 5 $0.00011 $0.00096
Haiku 4.5 $0.00005 $0.00048

Measured 8d ago against content hash bfb698a61051, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

drift-detector 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 8d 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.

subskills/monitor/drift-detector/SKILL.md · 54 lines

What it actually says

Drift Detector

Per claude-seo 17-rule diff pattern.

Workflow

1. python -m scripts.monitor.drift_baseline --site {slug} --url {url}  # snapshot
2. python -m scripts.monitor.drift_compare --site {slug} --baseline {sha}  # 17 rules

Output: drift-report-{date}.json with 3 severity levels

17 rules (per claude-seo)

Rule Severity
1. Title tag changed high
2. Meta description changed medium
3. H1 changed high
4. Canonical URL changed high
5. Robots meta changed (noindex added) critical
6. JSON-LD schema removed high
7. JSON-LD schema type changed medium
8. Featured image removed medium
9. Internal links count -20%+ medium
10. External Tier-1 link removed high
11. Word count dropped >30% high
12. H2 count changed by ±2 medium
13. AIO citation lost critical
14. Broken outbound link emerged medium
15. AI bots robots.txt policy changed high
16. SSL/HTTPS broken critical
17. dateModified missing low

Cross-skill recommendations

Per rule, suggest:

  • 5/13 → trigger ai-overview-recovery
  • 9/14 → trigger internal-linker / link verification
  • 6/7 → trigger schema-generator
  • 1/3/11 → likely manual review needed
  • 16 → halt all operations; site emergency

See also

  • scripts/monitor/drift_baseline.py (TODO)
  • scripts/monitor/drift_compare.py (TODO)
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. 8d ago First seen · 54 lines · 0 tokens per session scan A bfb698a61051

Subscribe to this mod's changes

drift-detector is a skill published in the GitHub repository XuanRanL/loamwright-SEO-Skill (49 stars, last pushed 25d ago), licensed Apache-2.0. It adds 54 tokens to every session and 482 once invoked, about $0.0003 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 2026-09-03.