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 agentmods add skills/benjaminthomas/spec-driven-dev/generative-seonpx skills add benjaminthomas/spec-driven-dev --skill generative-seogit clone --depth 1 https://github.com/benjaminthomas/spec-driven-devWhat 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 | $0.00180 | $0.03515 |
| Opus 5 | $0.00090 | $0.01758 |
| Sonnet 5 | $0.00036 | $0.00703 |
| Haiku 4.5 | $0.00018 | $0.00351 |
Grade A, and why
generative-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 yesterday.
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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generative SEO (GEO) Operations
Runs an SEO + GEO program the same way a sharp in-house SEO operator would: technical audits, answer-first content built to be quoted by AI engines, an AI-citation tracker, competitor watch, and (draft-only) distribution. It is deliberately generic — first use in a repo spends a few minutes learning that project's facts, then behaves like a project-specific skill from then on.
Mode selection: the argument names the mode (content, audit, optimize,
competitors, citations, report, social). No argument → read the project's docs
(below), summarize current state, and recommend the highest-impact next action.
For the full evidence behind every rule below (which studies, what they found, why
each technique works) and the complete technical checklist, see
references/geo-methodology.md. Read it before an audit or before writing a
first piece of content in a new project; skip re-reading it on later runs in the
same project.
First run in a project: learn the project
Look for a config file at docs/seo/geo-config.md (or wherever the user says their
SEO docs live — some repos keep them in content/, marketing/, or a wiki instead).
If it exists, read it and skip to Read these first.
If it does not exist, this is the first run — ask the user (batch these, don't interview one question at a time):
- Product/brand name(s) — and critically, if the product is a sub-brand of a parent company or a different name than the company that builds it, get that distinction explicit now (e.g. "Acme Corp is the company; Acme Flow is the product we're marketing" or "same name, no distinction needed"). Getting this wrong (writing "is Acme Corp free?" when the product is Acme Flow) is a real, recurring mistake — nail it once here instead of guessing per-page later.
- Primary domain the content lives on (affects sitemap/robots checks and internal-link audits).
- Framework — Next.js, Astro, Remix, SvelteKit, plain static HTML, a CMS
(WordPress/Webflow/etc.), or something else. This determines where
sitemap/robots/metadata/JSON-LD live (see
references/geo-methodology.mdfor the per-framework map) — if unsure, look at the repo yourself first (package.json, top-level config files) before asking. - Where marketing/content pages live in the repo (a directory, a headless CMS, or "not in this repo" if content is managed elsewhere).
- Existing design system doc, if any (a
DESIGN.md, a Storybook, a Figma library) — new/edited pages should match it rather than invent a new look. - How to source real statistics for content — product analytics the user can query, a public dataset, or "external sources only." Never invent numbers regardless of the answer.
- Docs folder for this skill's own working files (default:
docs/seo/at repo root — offer this default rather than making the user think of one).
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 256 lines · 180 tokens per session scan A 9bced6f1fa4b
generative-seo is a skill published in the GitHub repository benjaminthomas/spec-driven-dev (1 stars, last pushed 28d ago), licensed MIT. It adds 180 tokens to every session and 3,515 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
academic-paper
12-agent academic paper writing pipeline. 11 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure/rebuttal-audit). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX-via-Pandoc/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns…
academic-paper-reviewer
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on…
agent-platform-alert-configuration
Configures best-practice alerting policies for Google Cloud Vertex AI / Agent Platform agents on Agent Runtime. Use when analyzing, writing, or deploying alerting policies to monitor agent latency, error rates, and quality metrics (response quality, tool use, hallucination). Also use when provisioning online monitors…
agent-platform-eval-flywheel
Measures and improves the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on…
agent-platform-inference
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when you need to generate code for calling Gemini or OpenMaaS models, authenticate with GenAI SDK, OpenAI SDK, or legacy Agent…
gemini-omni-flash-api
Use this skill for generative video editing, text-to-video, image-referenced video generation, and first-frame-to-video transition animations using the official google-genai SDK. Includes workflows for pre-processing/optimizing high-resolution or long source videos with ffmpeg, stripping audio for full sound…