spec-driven

spec-driven is a command for Claude Code from agencia-conversion/agentic-seo-skills. It costs 32 tokens per session (233 once invoked), scanned A, original, MIT.

A request-planning command that breaks a compound task into a specification, an execution plan, and checks for the final result.

In plain words
What is it for?
Use it for requests with several deliverables or review gates, creating control files in the project workbench.
Why use it?
It makes the required work, dependencies, decision points, and success conditions explicit before other tools run.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Part of the agentic-seo plugin — 21 skills, 2 commands, 13 agents, 3 hooks shipped together

Good fit Use it for requests with several deliverables or review gates, creating control files in the project workbench.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/agencia-conversion/agentic-seo-skills/spec-driven
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.

Clone the repo
git clone --depth 1 https://github.com/agencia-conversion/agentic-seo-skills

Made for: Claude Code.

Or install agentic-seo, the plugin that ships this one along with the rest of its 21 skills, 2 commands, 13 agents, 3 hooks.

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.

agentmods badge for spec-driven

README.md
[![agentmods](https://agentmods.dev/badge/commands/agencia-conversion/agentic-seo-skills/spec-driven/github.svg)](https://agentmods.dev/commands/agencia-conversion/agentic-seo-skills/spec-driven)
Your own site
<a href="https://agentmods.dev/commands/agencia-conversion/agentic-seo-skills/spec-driven"><img src="https://agentmods.dev/badge/commands/agencia-conversion/agentic-seo-skills/spec-driven/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.

agentmods 80×15 button for spec-driven

Your own site · 80×15
<a href="https://agentmods.dev/commands/agencia-conversion/agentic-seo-skills/spec-driven"><img src="https://agentmods.dev/badge/commands/agencia-conversion/agentic-seo-skills/spec-driven.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 233 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00233
Opus 5 $0.00016 $0.00117
Sonnet 5 $0.00006 $0.00047
Haiku 4.5 $0.00003 $0.00023

Measured 9d ago against content hash ebc98ed52c8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

spec-driven 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 9d 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.

commands/spec-driven.md · 23 lines

What it actually says

Invoke the spec-driven skill on the user's most recent compound request.

Request to decompose:

$ARGUMENTS

If $ARGUMENTS is empty, use the previous user message in the conversation as the request.

Follow the spec-driven skill contract exactly:

  1. Decompose the request into deliverables, source inputs, downstream skills, dependencies, decision gates, and deterministic checks.
  2. Present a simple design (entregáveis, ordem, decisões, critérios de sucesso, arquivos de controle).
  3. Write project/workbench/specs/<slug>/spec.md, plan.md, and result-check.md unless the user explicitly requested review-only planning.
  4. Never write into project/brain/ from this command.
  5. Name every downstream gate with its consequence.

Preserve pt-BR diacritics in all human-facing prose.

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.

  1. 9d ago First seen · 23 lines · 32 tokens per session scan A ebc98ed52c8b

Subscribe to this mod's changes

spec-driven is a command published in the GitHub repository agencia-conversion/agentic-seo-skills (50 stars, last pushed 3mo ago), licensed MIT. It adds 32 tokens to every session and 233 once invoked, about $0.0002 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 2026-08-30.