What is agentic-local-seo-audit CLAUDE.md?

Project instructions for an automated local search-engine optimization audit system. Local SEO means improving how a business appears in online searches for nearby customers.

Use them to crawl a business website, check its local search setup, calculate scores, generate reports, and track or improve audit quality.

They organize the audit process, scoring methods, scripts, quality checks, and improvement loop in one place.

How mshahiddigital/agentic-local-seo-audit configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to mshahiddigital/agentic-local-seo-audit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/mshahiddigital/agentic-local-seo-audit/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/mshahiddigital/agentic-local-seo-audit

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/mshahiddigital/agentic-local-seo-audit/claude-md/github.svg)](https://agentmods.dev/instructions/mshahiddigital/agentic-local-seo-audit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/mshahiddigital/agentic-local-seo-audit/claude-md"><img src="https://agentmods.dev/badge/instructions/mshahiddigital/agentic-local-seo-audit/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/mshahiddigital/agentic-local-seo-audit/claude-md"><img src="https://agentmods.dev/badge/instructions/mshahiddigital/agentic-local-seo-audit/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 7,824 This file is loaded in full into every session.

When invoked 7,824 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.07824	$0.07824
Opus 5	$0.03912	$0.03912
Sonnet 5	$0.01565	$0.01565
Haiku 4.5	$0.00782	$0.00782

Measured 11d ago against content hash a597f46427f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

agentic-local-seo-audit CLAUDE.md 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 11d 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.

CLAUDE.md · 579 lines

How it starts

The opening of the file, as written. The whole thing — 579 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — Local Business SEO Audit System

Version: 3.5 | Last Updated: March 2026

Scope: Folder-level instructions — activates automatically when this project folder is opened

Full phase checklists: references/phase-checklists.md Scoring frameworks: references/local-impact-benchmark.md | references/serp-trust-benchmark.md Scoring methodology: references/scoring-methodology.md Python scripts: scripts/ directory (setup_project, generate_pdf, check_url, score_calculator, audit_status, report_compiler, site_crawler, quality_checker) Auto-improve: auto-improve.md (loop instructions) | scripts/quality_checker.py (quality metric) | IMPROVEMENT_LOG.md (session log) Slash commands: .claude/commands/ directory (42 commands — thin triggers that invoke full SKILL.md skills)

SEO-AUTOIMPROVE MODE

Inspired by karpathy/autoresearch. Runs an autonomous improvement loop on SKILL.md files.

Trigger Commands

When ANY of the following are detected, read auto-improve.md and start the improvement loop: Read auto-improve.md and start improving | Run auto-improve | Start skill improvement loop Improve all skills | Run the improvement loop | /auto-improve

How It Works

REPEAT FOREVER:
  1. Pick SKILL.md with lowest quality score
  2. python3 scripts/quality_checker.py --skill [path] → baseline_score
  3. Web-research latest 2025/2026 best practices for this domain
  4. Improve the SKILL.md (specificity, recency, actionability, completeness)
  5. git commit → re-score → IF improved: KEEP | IF not: git reset
  6. Log to IMPROVEMENT_LOG.md → cycle to next skill
  NEVER STOP until manually interrupted

Auto-Improve Rules

Only modify SKILL.md files — never touch quality_checker.py, auto-improve.md, CLAUDE.md, or Python scripts
Revert on no improvement — stash uncommitted work first (git stash --include-untracked), then git reset --hard HEAD~1, then restore (git stash pop 2>/dev/null || true)
Log every experiment — every attempt (kept or reverted) goes in IMPROVEMENT_LOG.md
Never push — all changes stay local until user reviews and merges
Branch isolation — always work on autoimprove/YYYY-MM-DD branch

Read the full file on GitHub · 579 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.

11d ago First seen · 579 lines · 7,824 tokens per session scan A a597f46427f1

Subscribe to this mod's changes

agentic-local-seo-audit CLAUDE.md is an instructions file published in the GitHub repository mshahiddigital/agentic-local-seo-audit (20 stars, last pushed 5mo ago), licensed MIT. It adds 7,824 tokens to every session, about $0.0391 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.

Claude Code Marketing and SEO ai-seo claude-code-plugin competitor-analysis content-strategy google-business-profile

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

agentic-local-seo-audit: Instructions file for Claude Code