What is seo-task-runner?

A task runner that takes an SEO task from a tool's to-do list and completes it in a local website project. SEO, or search engine optimisation, improves how a site can be found and understood by search engines.

Use it to select a task, make the smallest required source change, check the result, and mark the task done or skipped.

It applies the requested change in the client's actual Astro, Next.js, or HTML project instead of merely describing what someone should edit.

seo-task-runner — Skill for Claude Code by IamRamgarhia

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 IamRamgarhia/All-In-One-Free-SEO-Tool --skill seo-task-runner

Clone the repo

git clone --depth 1 https://github.com/IamRamgarhia/All-In-One-Free-SEO-Tool

Made for: Claude Code.

Or install seo-tool, the plugin that ships this one along with the rest of its 5 skills.

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/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner/github.svg)](https://agentmods.dev/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner)

Your own site

<a href="https://agentmods.dev/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner"><img src="https://agentmods.dev/badge/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner/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/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner"><img src="https://agentmods.dev/badge/skills/iamramgarhia/all-in-one-free-seo-tool/seo-task-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 622 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.

Model	Per session	Once invoked
Fable 5.1	$0.00042	$0.00622
Opus 5.5	$0.00017	$0.00249
Sonnet 5.5	$0.00008	$0.00124
Haiku 4.5	$0.00004	$0.00062

Measured 14d ago against content hash 699a5ee5601d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

seo-task-runner 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 14d 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.

plugins/seo-tool/skills/seo-task-runner/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Do an SEO task in the client's project

Goal

Take one task from the tool's list and finish it where the site's source lives, instead of describing what someone should do. Use this when the client's site is a local project (Astro, Next.js, plain HTML) and there is no CMS for the tool to write through.

Before you touch anything

Run list_clients and find the client's localPath. Work in that folder and nowhere else. If it is null, ask the user where the project is. Do not search the disk for it.

Steps

list_tasks for the client, status todo. High priority comes first.
get_task for the one you are taking. Its brief states the site, the stack, the folder and where such things usually live. Those locations are places to look. They are not facts about this project, so read the files before editing.
update_task to "in progress" if the work will take more than one step.
Make the smallest change that completes the task, in the project folder. Do not deploy or push unless the user asked you to.
Check the result: build the site, open the changed file, or re-read the sitemap. Say what you verified.
update_task to done, or skipped with the reason if the task does not apply to this site. Marking a task done is recorded in the activity log, so do not do it for work that is not finished.

Blog drafts for a static site

If the user wants a generated article in the project, call list_publish_queue (kind blog_draft, status pending_review) and then get_queue_item. It returns a Markdown file with frontmatter. With forAi it also carries a brief on how to enrich it. Save it into the project's content folder, follow that folder's frontmatter conventions, and keep the keywords.

Tools

list_clients — ids and each client's localPath.
list_tasks — the to-do list for one client.
get_task — one task plus a ready-made brief.
update_task — set the status. Does not change the live website.
list_publish_queue — generated items waiting for review.
get_queue_item — one item; blog drafts come as Markdown.

Read the full file on GitHub · 60 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.

14d ago First seen · 60 lines · 42 tokens per session scan A 699a5ee5601d

Subscribe to this mod's changes

seo-task-runner is a skill published in the GitHub repository IamRamgarhia/All-In-One-Free-SEO-Tool (126 stars, last pushed 13d ago), licensed MIT. It adds 42 tokens to every session and 622 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-30.

Marketing and SEO ahrefs-alternative ai-seo ai-seo-tool free-seo-tools local-seo rank-tracker

seo-task-runner next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
seo-task-runnerIamRamgarhia/All-In-One-Free-SEO-Tool	Skill	126	13d ago	MIT	A	42	Claude Code
local-seo-datalocalseodata/mcp-server	Skill	3	yesterday	MIT	A	114	Claude Code, Codex
ai-seocoreyhaines31/marketingskills	Skill	60k	yesterday	MIT	A	85	Claude Code
conversion-trackingcoreyhaines31/marketingskills	Skill	60k	yesterday	MIT	A	105	Claude Code
reverse-engineer-marketingcoreyhaines31/marketingskills	Skill	60k	yesterday	MIT	A	93	Claude Code
attributioncoreyhaines31/marketingskills	Skill	60k	yesterday	MIT	A	100	Claude Code
churn-preventioncoreyhaines31/marketingskills	Skill	60k	yesterday	MIT	A	61	Claude Code