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.
npx skills add CraftOS-dev/CraftBot --skill programmatic-seogit clone --depth 1 https://github.com/CraftOS-dev/CraftBotWrote 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/skills/craftos-dev/craftbot/programmatic-seo)<a href="https://agentmods.dev/skills/craftos-dev/craftbot/programmatic-seo"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/programmatic-seo/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/skills/craftos-dev/craftbot/programmatic-seo"><img src="https://agentmods.dev/badge/skills/craftos-dev/craftbot/programmatic-seo.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 | $0.00085 | $0.03854 |
| Opus 5.5 | $0.00034 | $0.01542 |
| Sonnet 5.5 | $0.00017 | $0.00771 |
| Haiku 4.5 | $0.00009 | $0.00385 |
Grade A, and why
programmatic-seo 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 1mo 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.
Copies of this mod
6 near-identical copies found in the catalogue:
- tool-programmatic-seo — 100% identical, 8 lines differ
- programmatic-seo — 100% identical, 0 lines differ
- programmatic-seo — 100% identical, 0 lines differ
- programmatic-seo — 100% identical, 3 lines differ
- programmatic-seo — 100% identical, 0 lines differ
- programmatic-seo — 98% identical, 30 lines differ
How it starts
The opening of the file, as written. The whole thing — 627 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Programmatic SEO
You are an expert in programmatic SEO—building SEO-optimized pages at scale using templates and data. Your goal is to create pages that rank, provide value, and avoid thin content penalties.
Initial Assessment
Before designing a programmatic SEO strategy, understand:
-
Business Context
- What's the product/service?
- Who is the target audience?
- What's the conversion goal for these pages?
-
Opportunity Assessment
- What search patterns exist?
- How many potential pages?
- What's the search volume distribution?
-
Competitive Landscape
- Who ranks for these terms now?
- What do their pages look like?
- What would it take to beat them?
Core Principles
1. Unique Value Per Page
Every page must provide value specific to that page:
- Unique data, insights, or combinations
- Not just swapped variables in a template
- Maximize unique content—the more differentiated, the better
- Avoid "thin content" penalties by adding real depth
2. Proprietary Data Wins
The best pSEO uses data competitors can't easily replicate:
- Proprietary data: Data you own or generate
- Product-derived data: Insights from your product usage
- User-generated content: Reviews, comments, submissions
- Aggregated insights: Unique analysis of public data
Hierarchy of data defensibility:
- Proprietary (you created it)
- Product-derived (from your users)
- User-generated (your community)
- Licensed (exclusive access)
- Public (anyone can use—weakest)
3. Clean URL Structure
Always use subfolders, not subdomains:
- Good:
yoursite.com/templates/resume/ - Bad:
templates.yoursite.com/resume/
Subfolders pass authority to your main domain. Subdomains are treated as separate sites by Google.
URL best practices:
- Short, descriptive, keyword-rich
- Consistent pattern across page type
- No unnecessary parameters
- Human-readable slugs
4. Genuine Search Intent Match
Pages must actually answer what people are searching for:
- Understand the intent behind each pattern
- Provide the complete answer
- Don't over-optimize for keywords at expense of usefulness
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.
- 1mo ago First seen · 627 lines · 85 tokens per session scan A f54fd1731b67
programmatic-seo is a skill published in the GitHub repository CraftOS-dev/CraftBot (399 stars, last pushed today), licensed MIT. It adds 85 tokens to every session and 3,854 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
turix-mac
Computer Use Agent (CUA) for macOS automation using TuriX. Use when you need to perform visual tasks on the desktop, such as opening apps, clicking buttons, or navigating UIs that don't have a CLI or API.
scan-mode-as-skill
Operational modes (quick/standard/deep) should be first-class skills, not hard-coded branching — each mode defines its own phases, priorities, and completion criteria.
blender-agent
Drive Blender with the official Blender MCP for everything inside the app, and computer-use only for what has no API. Never read Blender through the accessibility tree.
browser-control
Control web pages in an existing Chromium remote-debugging session with deterministic sagui commands or the browser-only AI Agent. Use when Claude Code needs to inspect tabs, observe semantic elements, navigate, click, type, send keys, scroll, or complete a browser goal through CDP without controlling native macOS UI…
computer-use
Desktop automation with computer-use-mcp. Use when controlling native macOS/Windows apps via accessibility, OCR, screenshots or scripting — not for pure git/file/http tasks.
analytics-agent
Answer a business question from an organisation's real dashboards — citing measured numbers, using the company's own metric definitions, and showing the person what you looked at.