clarificar

clarificar is a skill for Claude Code, Codex from igoruehara/spec-driven. It costs 137 tokens per session (1,041 once invoked), scanned A, original, MIT.

Riadený rozhovor, ktorý postupne spresňuje nejasný plán, špecifikáciu alebo návrh. Kladenie jednej otázky za druhou odhaľuje závislé rozhodnutia a uzatvára otvorené voľby.

In plain words
What is it for?
Na spresnenie rozsahu, hraníc, kritérií prijatia, technických rozhodnutí a ďalších častí plánu pred začatím implementácie.
Why use it?
Znižuje riziko, že sa začne pracovať s neúplným alebo rozdielne chápaným zadaním. Pomáha vyriešiť dôležité nejasnosti v správnom poradí.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/igoruehara/spec-driven/clarificar
Any agent
npx skills add igoruehara/spec-driven --skill clarificar
Clone the repo
git clone --depth 1 https://github.com/igoruehara/spec-driven

Made for: Claude Code, Codex.

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 clarificar

README.md
[![agentmods](https://agentmods.dev/badge/skills/igoruehara/spec-driven/clarificar.svg)](https://agentmods.dev/skills/igoruehara/spec-driven/clarificar)
Your own site
<a href="https://agentmods.dev/skills/igoruehara/spec-driven/clarificar"><img src="https://agentmods.dev/badge/skills/igoruehara/spec-driven/clarificar.svg" alt="Measured on agentmods" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00137 $0.01041
Opus 5 $0.00068 $0.00521
Sonnet 5 $0.00027 $0.00208
Haiku 4.5 $0.00014 $0.00104

Measured 4d ago against content hash 568b3590af5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarificar 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 4d 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.

template/.claude/skills/clarificar/SKILL.md · 51 lines

How it starts

The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: Clarificar (sabatina de plano/spec)

Entrevista implacável para afiar um plano, uma spec ou um design antes de construir. O alvo é entendimento compartilhado: nenhuma ambiguidade que vire retrabalho ou SPEC_DEVIATION depois. Inspirada na técnica de grilling — adaptada ao vocabulário da esteira (AC testáveis, tier, decisão difícil de reverter → ADR, linguagem ubíqua).

Quando usar isto e não "lotes curtos": o resto da esteira pergunta em lotes (AskUserQuestion) para escolhas independentes. A sabatina é o oposto e o complemento: para uma árvore de decisão com dependências, onde a resposta 3 só faz sentido depois das respostas 1 e 2. Use quando a ambiguidade é profunda e ramificada, não quando são opções ortogonais.

Princípios (o motor)

  • Uma pergunta por vez. Faça a pergunta, espere a resposta, e só então a próxima. Várias perguntas de uma vez confundem e impedem que cada resposta refine a seguinte.
  • Caminhe pela árvore. Cada resposta abre/fecha ramos. Resolva dependências em ordem: não pergunte o "como" antes do "se", nem o detalhe antes da fronteira.
  • Sempre proponha uma resposta recomendada. Não interrogue no vácuo — para cada pergunta dê sua recomendação com o porquê (em AskUserQuestion, a primeira opção leva "(Recomendado)").
  • Explore antes de perguntar. Se a resposta está no codebase, nos docs (specs/, docs/, ADRs, glossário) ou num MCP de referência conectado, descubra você mesmo — só pergunte o que exige decisão humana. (É a Verificação de conhecimento do CLAUDE.md.) Nunca invente: incerteza explícita > chute confiante.
  • Cave até o testável. Uma resposta vaga ("rápido", "seguro", "vários") não fecha o ramo — refine até virar critério verificável (número, caso concreto, Given/When/Then).

Processo

  1. Enquadre o alvo. Diga em 1-2 linhas o que está sendo sabatinado (esta feature / este design / esta prioridade) e o que será considerado "entendido o bastante para seguir".
  2. Levante os ramos abertos. A partir do material existente, liste mentalmente as decisões em aberto e as ambiguidades. Priorize as de maior impacto / mais difíceis de reverter.
  3. Sabatine, um ramo por vez. Para cada ponto: explore primeiro; se restar decisão, pergunte uma coisa com a recomendação; integre a resposta; deixe-a abrir os próximos ramos. Repita.
  4. Pare quando a árvore fechar — sem ramos abertos que mudem o que será construído. Não estenda por esporte; quando o usuário e você concordam no escopo, encerre.

Read the full file on GitHub · 51 lines

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. 4d ago First seen · 51 lines · 137 tokens per session scan A 568b3590af5c

Subscribe to this mod's changes

clarificar is a skill published in the GitHub repository igoruehara/spec-driven (213 stars, last pushed 1mo ago), licensed MIT. It adds 137 tokens to every session and 1,041 once invoked, about $0.0007 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens