Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/umutxyp/Seo-Promt-Masternpx agentmods add rules/umutxyp/seo-promt-master/seo-prompt-masterWrote 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.
[](https://agentmods.dev/rules/umutxyp/seo-promt-master/seo-prompt-master)<a href="https://agentmods.dev/rules/umutxyp/seo-promt-master/seo-prompt-master"><img src="https://agentmods.dev/badge/rules/umutxyp/seo-promt-master/seo-prompt-master/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.
<a href="https://agentmods.dev/rules/umutxyp/seo-promt-master/seo-prompt-master"><img src="https://agentmods.dev/badge/rules/umutxyp/seo-promt-master/seo-prompt-master.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00025 | $0.00612 |
| Opus 5.5 | $0.00010 | $0.00245 |
| Sonnet 5.5 | $0.00005 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
seo-prompt-master 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 23d 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.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SEO Prompt Master
Invoke this when the task involves search visibility: an SEO audit, indexing or
crawling problems, canonicals, hreflang, sitemaps, robots.txt, structured
data, a traffic drop, a site migration, or being cited by AI answer engines.
Also invoke it before shipping changes to routing, metadata, robots.txt or
sitemap generation.
Source of truth
docs/01–docs/18 in this repository, distilled from Google Search Central and
web.dev. Every recommendation must cite one (docs/13 §soft 404). If a claim is
not in there, say so rather than recalling it — most SEO advice online is years
out of date, and this knowledge base is explicit about what changed (FID → INP,
FAQ rich results removed, rel=next/prev unused since 2019).
verticals/01–24 add industry-specific overlays. They supplement the core
audit; they never replace it. docs/18 covers Bing, Yandex, Apple/Safari and
Brave, and prompt-library/ holds single-task prompts for narrow requests.
Run the tool, don't only read the code
node tools/seo-audit.mjs --url https://the-site.example --max 40 --md seo-report.md
Reading the repository tells you what the project intends. This tells you what
the server returns — soft 404s per template, one-way hreflang sets, canonicals
pointing at redirects, metadata streamed past </head>. Zero dependencies,
Node 18+, exits 1 on any P1 so it can gate a deploy. Works against
http://localhost:3000 when there is no live site.
Workflow
START.md holds the phases. In short: detect the stack → inventory every route
as public-index / public-noindex / private → audit each indexable page →
prioritise into P1 (crawl/index blockers), P2 (misrepresentation), P3 (hygiene)
→ fix shared infrastructure first, then per-page → verify by re-fetching.
Persist to ROUTES-INVENTORY.md and SEO-AUDIT-PROGRESS.md so a long run
survives a context reset, and resume from them if they already exist.
Non-negotiable
- Typecheck, lint and build after every change; never leave the build broken.
- A fix is not done until you have re-fetched the page and seen it.
- Finish with the SEO/GEO scores from
docs/11, with the category breakdown and the off-page caveat — never a bare number.
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.
- 23d ago Changed · +1 lines 158d1d69aa27
- 1mo ago First seen · 54 lines · 25 tokens per session scan A 1af7147aa472
seo-prompt-master is a cursor rule published in the GitHub repository umutxyp/Seo-Promt-Master (564 stars, last pushed 10d ago), licensed MIT. It adds 25 tokens to every session and 612 once invoked, about $0.0001 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 2026-08-30.
Other cursor rules, from other repositories
client-workflow-bootstrap
Cursor rule "client-workflow-bootstrap" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, interview process and gate before generating.
cursorrules
You are assisting the Orbital engineering team — 5 backend engineers building a multi-tenant SaaS for logistics operations. TypeScript monorepo using NestJS, PostgreSQL (drizzle-orm), and BullMQ. All engineers use shared conventions.
co-dialectic
Co-Dialectic prompt sharpening and verification rules for Cursor.
monobehaviour-lifecycle
Correct usage of MonoBehaviour lifecycle methods.
002-verify-before-act
Requires Claude to read before writing, verify before installing, and confirm before destructive operations.
cursor-workflow
Route development requests to the repository's reusable Cursor skills and commands.