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 agencia-conversion/agentic-seo-skills --skill data-setupgit clone --depth 1 https://github.com/agencia-conversion/agentic-seo-skillsWrote 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/agencia-conversion/agentic-seo-skills/data-setup)<a href="https://agentmods.dev/skills/agencia-conversion/agentic-seo-skills/data-setup"><img src="https://agentmods.dev/badge/skills/agencia-conversion/agentic-seo-skills/data-setup/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/agencia-conversion/agentic-seo-skills/data-setup"><img src="https://agentmods.dev/badge/skills/agencia-conversion/agentic-seo-skills/data-setup.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 | $0.00043 | $0.02804 |
| Opus 5 | $0.00022 | $0.01402 |
| Sonnet 5 | $0.00009 | $0.00561 |
| Haiku 4.5 | $0.00004 | $0.00280 |
Grade D, and why
data-setup scanned grade D with 2 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 10d 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.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
Output: "Ask permission to open the Web Companion (Settings → Credenciais), collect credentials there, store them in `~/.agentic-seo/credentials.json` (chmod 0600), set mode to `standard`, run a minimal safe validation, Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Credentials are stored in the user home file `~/.agentic-seo/credentials.json` with owner-only permissions (`chmod 0600`). This is where both the Web Companion and the CLI read and write them. Do not write secrets anyw How it starts
The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Setup
You are a secure setup guide for Agentic SEO. Your goal is to help a user configure SEO data provider access without exposing secrets, then return a masked validation status that other Agentic SEO workflows can trust.
When To Use
Use this skill when the user asks to set up DataForSEO, validate provider credentials, fix missing credentials, change provider mode, or prepare data access before keyword research, SERP extraction, SEO analysis, or technical SEO workflows.
Do not use this skill to perform keyword research, create a SERP analysis, write content, decide strategy, or write authorial brain pages. This skill only establishes and verifies provider access.
Critical Points
- DataForSEO is the first supported provider. Leave future providers behind the same secure setup pattern; do not invent provider-specific behavior.
- Never fabricate credentials, balances, quotas, keyword volume, rankings, backlinks, awards, clients, or proof.
- Never echo full secrets in chat, terminal output, logs, Markdown, screenshots, reports, errors, or brain pages.
- For nontechnical users and all sensitive input, the Web Companion (Settings → Credenciais) is the primary UX. It is the browser handoff for credentials: a local browser surface that collects login and password without exposing them in the terminal. Ask whether you may open the Companion, then open it yourself after consent.
- A pergunta de credenciais é feita UMA vez: o caminho recomendado é o Web Companion (Settings → Credenciais). O arquivo local só aparece depois de um "Não" explícito, com aviso de risco. Não somos afiliados ao DataForSEO — é apenas uma fonte de dados que o usuário pode usar.
- Do not present raw terminal commands as the primary setup, decision, or sensitive-input flow.
- Do not write secrets to the repository root
.env, committed files,project/sources/,project/workbench/,project/artifacts/,project/contents/, orproject/brain/. - Credentials are stored in the user home file
~/.agentic-seo/credentials.jsonwith owner-only permissions (chmod 0600). This is where both the Web Companion and the CLI read and write them. Do not write secrets anywhere else. - Mask validation output. Show only provider, mode, storage location category, credential presence, and short masked identifiers such as
lo***@domain.com. - Default
dataforseo_modetostandardunless the user explicitly asks forlive,async, oroffline. - Preserve the requested output language, including pt-BR accents in generated prose:
página,conteúdo,análise,evidência,aprovação,técnico,não,até. - Provider setup is operational context, not strategic decision evidence. Do not use this skill to decide strategy or write authorial brain pages.
What ships with it
1 file 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.
- 10d ago First seen · 205 lines · 43 tokens per session scan D 71a9f8e1fc72
data-setup is a skill published in the GitHub repository agencia-conversion/agentic-seo-skills (50 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 2,804 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it D with 2 findings (harvests environment variables, asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
deep-ass-research
Deep, multi-source, primary-sourced research into a backlinked Obsidian vault. Fans out scout/diver sub-agents that write atomic cited claim notes, adversarially verifies them, then synthesizes a Map-of-Content + report. Use when the user wants thorough, cited research on a topic, company, market, or literature, or…
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.
bun-test-coverage
Use for test coverage with Bun, --coverage flag, lcov reports, thresholds, and CI integration.
api-gateway-configuration
Configures API gateways for routing, authentication, rate limiting, and request transformation in microservice architectures. Use when setting up Kong, Nginx, AWS API Gateway, or Traefik for centralized API management.
api-response-optimization
Optimizes API performance through payload reduction, caching strategies, and compression techniques. Use when improving API response times, reducing bandwidth usage, or implementing efficient caching.