audit-drift

audit-drift is an agent for Claude Code from XuanRanL/loamwright-SEO-Skill. It costs 43 tokens per session (942 once invoked), scanned A, original, Apache-2.0.

An SEO comparison check that compares a website's current crawl with an earlier saved crawl. SEO means improving how pages appear in search engines.

In plain words
What is it for?
Use it when a previous crawl baseline exists and you need to find SEO regressions between the old and current site.
Why use it?
It reveals changes that can reduce search visibility, such as removed structured data, changed canonical URLs, added noindex settings, or slower page experience scores.

Agent for Claude Code

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

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

Good fit Use it when a previous crawl baseline exists and you need to find SEO regressions between the old and current site.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/xuanranl/loamwright-seo-skill/audit-drift
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.

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 audit-drift

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/xuanranl/loamwright-seo-skill/audit-drift"><img src="https://agentmods.dev/badge/agents/xuanranl/loamwright-seo-skill/audit-drift.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 942 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 $0.00043 $0.00942
Opus 5 $0.00022 $0.00471
Sonnet 5 $0.00009 $0.00188
Haiku 4.5 $0.00004 $0.00094

Measured 9d ago against content hash 8ca83a57bb34, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

audit-drift 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.

agents/audit-drift.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Audit Drift Agent

Spawn Condition

Previous baseline exists: {audit_dir}/baseline/ directory present, OR config.json :: baseline_path valid. If no baseline, write minimal output noting absence and exit.

Inputs

  • {audit_dir}/crawl-results.json — current state
  • {audit_dir}/baseline/crawl-results.json — prior state
  • {audit_dir}/baseline/modules/*.json — prior module scores

Scripts

There is NO executor for the audit-dir comparison this agent performs — no scripts.audit.drift_compare module exists. Read crawl-results.json and baseline/crawl-results.json yourself and apply the 17 rules below manually.

Related but DIFFERENT workflow: python -m scripts.monitor.drift_compare --site {project_slug} --url {live_url} --json compares ONE published URL against its SQLite baseline in projects/{slug}/baselines/drift.sqlite (the /drift monitor path). It does not read audit-dir crawl results and takes no --current/--baseline flags.

17 Comparison Rules

CRITICAL (immediate ranking impact):

  1. Schema removed — had structured data, now absent
  2. Canonical changed — href differs
  3. Canonical removed — was present, now missing
  4. Noindex added — was indexable, now noindex
  5. H1 removed — was present, now missing
  6. H1 changed >50% — token overlap < 50%
  7. Title removed — <title> absent
  8. Status 4xx/5xx — was 200, now error

WARNING (likely impact): 9. Title changed — content differs 10. Meta description changed 11. CWV regressed >20% — any metric degraded >20% 12. Module score dropped 10+ pts 13. OG tags removed — og:title/description/image gone 14. Schema modified — type or content materially changed

INFO (notable, no immediate penalty): 15. New schema added 16. H2 structure changed — headings added/removed/reordered 17. Content hash changed — body content edited

Pages in baseline but absent from current = CRITICAL (rule 8). Pages in current but absent from baseline = INFO (new page).

Scoring

base = 100; per_critical = -15 (cap -60); per_warning = -5 (cap -30); per_info = -1 (cap -10)
drift_score = max(0, 100 + critical_penalty + warning_penalty + info_penalty)

90-100 stable | 70-89 minor drift | 50-69 significant | 30-49 major regressions | 0-29 critical drift.

Read the full file on GitHub · 75 lines

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. 9d ago First seen · 75 lines · 43 tokens per session scan A 8ca83a57bb34

Subscribe to this mod's changes

audit-drift is an agent published in the GitHub repository XuanRanL/loamwright-SEO-Skill (47 stars, last pushed 22d ago), licensed Apache-2.0. It adds 43 tokens to every session and 942 once invoked, about $0.0002 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.

Related

Other agents, from other repositories

schema-generator

Structured-data specialist. Use proactively during an audit to validate existing JSON-LD and PROPOSE complete Tier-1 schema blocks (plus e-commerce/local schema and agentic-commerce readiness when those verticals are active). It proposes diffs only and does NOT write files.

Hainrixz/claude-seo-ai · 56 tokens

seo-fixer-writer

The ONLY agent allowed to write files. Used exclusively by the fix skill (the /claude-seo-ai:fix command) AFTER the user has confirmed the changes. Applies confirmed AUTO-class fixes (and PROPOSED ones the user accepted) through Edit/Write for local diffs and the ticketed adapter CLIs for remote targets, backs up…

Hainrixz/claude-seo-ai · 93 tokens

geo-schema

Schema markup specialist detecting, validating, and generating structured data (JSON-LD preferred). Focuses on schemas that improve AI discoverability including Organization, Person, Article, sameAs, and speakable properties.

Cognitic-Labs/geoskills · 44 tokens

geo-citability

AI citability scoring and optimization specialist. Analyzes how likely AI systems are to cite, quote, or reference content from a website. Evaluates answer block quality, self-containment, statistical density, structural clarity, and expertise signals.

Cognitic-Labs/geoskills · 53 tokens

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens