geo-lint-fixer

geo-lint-fixer is an agent for Claude Code from IJONIS/geo-lint. It costs 47 tokens per session (770 once invoked), scanned A, original, MIT.

An automated fixer for content files that fail geo-lint checks. It finds a file from its content type and slug, applies the checker’s suggested changes, and checks the file again.

In plain words
What is it for?
Use it to fix SEO and AI-search issues in blog posts, pages, or project entries until the file passes or five fixing rounds have been attempted.
Why use it?
It removes the repeated work of locating violations, editing the content, and running the checker after each change.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the geo-lint plugin — 2 skills, 1 agent shipped together

Good fit Use it to fix SEO and AI-search issues in blog posts, pages, or project entries until the file passes or five fixing rounds have been attempted.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ijonis/geo-lint/geo-lint-fixer
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/IJONIS/geo-lint

Made for: Claude Code.

Or install geo-lint, the plugin that ships this one along with the rest of its 2 skills, 1 agent.

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 geo-lint-fixer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ijonis/geo-lint/geo-lint-fixer/github.svg)](https://agentmods.dev/agents/ijonis/geo-lint/geo-lint-fixer)
Your own site
<a href="https://agentmods.dev/agents/ijonis/geo-lint/geo-lint-fixer"><img src="https://agentmods.dev/badge/agents/ijonis/geo-lint/geo-lint-fixer/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 geo-lint-fixer

Your own site · 80×15
<a href="https://agentmods.dev/agents/ijonis/geo-lint/geo-lint-fixer"><img src="https://agentmods.dev/badge/agents/ijonis/geo-lint/geo-lint-fixer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 770 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 $0.00047 $0.00770
Opus 5 $0.00023 $0.00385
Sonnet 5 $0.00009 $0.00154
Haiku 4.5 $0.00005 $0.00077

Measured 9d ago against content hash 152ee21edc86, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

geo-lint-fixer 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/geo-lint-fixer.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a content optimization specialist using @ijonis/geo-lint. Your job is to fix SEO and GEO violations in Markdown/MDX content files autonomously.

Core Loop

  1. You receive a content slug and its violations
  2. Resolve the slug to a filesystem path
  3. Read the file
  4. Fix all violations using their suggestion fields
  5. Re-run the linter, filter to your file
  6. Repeat until clean or 5 passes exhausted

Slug Resolution

The violation file field uses the format <contentType>/<slug>:

Content Type Default Directory
blog content/blog/
page content/pages/
project content/projects/

To find the file:

grep -rl "^slug: <slug-value>" content/<type-dir>/ 2>/dev/null

If no match, try: content/<type-dir>/<slug>.mdx or content/<type-dir>/<slug>.md

If the project has a geo-lint.config.ts, read it to check for custom contentPaths mappings that override the defaults.

Fixing Rules

  • Fix error severity violations first, then warning
  • Apply the fix described in each violation's suggestion field
  • Preserve the author's voice -- restructure, do not rewrite
  • For heading changes: maintain the existing topic flow
  • For GEO rules: add structure (tables, FAQ sections, question headings) without removing existing content
  • For SEO metadata rules: adjust titles, descriptions to meet length requirements while preserving meaning
  • Never fabricate statistics, data, or citations
  • Never invent image files or internal link targets

Human-Escalation Rules -- DO NOT FIX

Skip these rules entirely. Report them in your final output but do not attempt to fix them:

  • geo-low-citation-density -- requires real statistics; fabricating violates E-E-A-T
  • image-not-found -- a real image file must exist on disk
  • broken-internal-link -- the target page may not exist yet
  • category-invalid -- valid categories come from geo-lint.config.ts only

Re-Lint Command

After each fix pass:

Read the full file on GitHub · 105 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 · 105 lines · 47 tokens per session scan A 152ee21edc86

Subscribe to this mod's changes

geo-lint-fixer is an agent published in the GitHub repository IJONIS/geo-lint (39 stars, last pushed 5mo ago), licensed MIT. It adds 47 tokens to every session and 770 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

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

geo-brand

Brand and entity signal specialist analyzing Wikipedia/Wikidata presence, third-party platform profiles, community mentions, and cross-source brand consistency for AI entity recognition.

Cognitic-Labs/geoskills · 33 tokens

geo-technical

Technical SEO specialist analyzing crawlability, indexability, security, URL structure, mobile optimization, Core Web Vitals (INP replaces FID), server-side rendering, and JavaScript dependency.

Cognitic-Labs/geoskills · 42 tokens

geo-content

Content quality specialist evaluating E-E-A-T signals (Experience, Expertise, Authoritativeness, Trustworthiness), content depth, readability, AI content detection, and topical authority.

asale-ai/seo-geo-skill · 37 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.

asale-ai/seo-geo-skill · 44 tokens