code-ai-template: Skill for Claude Code

.claude/skills/grilling/SKILL.md

grilling is a skill for Claude Code from FHDumont/code-ai-template. It costs 81 tokens per session (1,538 once invoked), scanned A, original, MIT.

A structured questioning process for reaching shared agreement on a plan, decision, or idea and recording the result as a phase specification.

In plain words
What is it for?
Use it in planning sessions to ask decision-focused questions in rounds, investigate facts in the codebase, and finalize docs/SETUP.md.
Why use it?
It exposes unanswered decisions and dependencies before implementation begins.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions CLAUDE.md; names the ExitPlanMode tool; mentions Claude Code.

This is FHDumont/code-ai-template's own configuration. It tells Claude Code how to work on code-ai-template itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything code-ai-template configures →

Reuse

Borrowing it

Nothing to install: this file belongs to FHDumont/code-ai-template. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/FHDumont/code-ai-template/main/.claude/skills/grilling/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/FHDumont/code-ai-template

Made for: Claude Code.

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 grilling

README.md
[![agentmods](https://agentmods.dev/badge/skills/fhdumont/code-ai-template/grilling/github.svg)](https://agentmods.dev/skills/fhdumont/code-ai-template/grilling)
Your own site
<a href="https://agentmods.dev/skills/fhdumont/code-ai-template/grilling"><img src="https://agentmods.dev/badge/skills/fhdumont/code-ai-template/grilling/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 grilling

Your own site · 80×15
<a href="https://agentmods.dev/skills/fhdumont/code-ai-template/grilling"><img src="https://agentmods.dev/badge/skills/fhdumont/code-ai-template/grilling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,538 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 $0.00081 $0.01538
Opus 5.5 $0.00032 $0.00615
Sonnet 5.5 $0.00016 $0.00308
Haiku 4.5 $0.00008 $0.00154

Measured 5d ago against content hash d80b48b360bd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

grilling 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 5d 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.

.claude/skills/grilling/SKILL.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Interrogue o dono até chegarem a entendimento compartilhado — e só sobre o que ainda não está decidido. Modele o assunto como uma árvore de decisão: toda decisão ramifica nas decisões que penduram nela. Pergunta repetida, pergunta já respondida num doc, e pergunta cuja resposta não muda o trabalho são o custo que esta skill existe pra evitar.

Passo zero — o tamanho da fase decide o tamanho do grilling

Antes da primeira pergunta, classifique a fase e diga ao dono qual é:

  • Correção ou ajuste — achado do dono em caminho que já existe, defeito medido, mudança que não cria modelo nem tela: zero ou uma rodada. Corrija o que ele descreveu. O que você consegue fechar auditando vira suposição declarada, num bloco único que ele veta numa resposta só. Achado dele não vira varredura transversal: a generalização, se houver, é uma linha de ROADMAP.md, não pergunta.
  • Modelagem ou tela nova — muda schema, contrato entre pacotes, ou cria fluxo que o dono vai ver: grilling completo, em rodadas.

Antes de perguntar, procure

Achar fato é seu trabalho, nunca do dono. Toda pergunta candidata passa por três filtros antes de sair:

  1. Já está decidido? grep em docs/DECISOES.md, CONTEXT.md, nas regras R-NNN de docs/reference/ e no arquivo da fase de origem em docs/history/fases/. Decisão gravada vira citação na spec, não pergunta. Achado que contradiz um ADR aceito: procure o outro ADR que decide a mesma grandeza — conflito entre decisões é a hipótese principal, e ADR mal feito se corrige por emenda ou superseded, não se re-pergunta.
  2. É fato do ambiente? Código, filesystem, gh, banco do lab, laudos já feitos em docs/scratch/: dispare um subagente e olhe. Só as perguntas a jusante da exploração esperam por ela; o resto da fronteira sai agora. Número que não fecha se resolve com o documento (o extrato, o PDF, a linha do banco), não com um menu de hipóteses pro dono confirmar — peça o documento.
  3. A resposta muda o trabalho? Pergunta é pra decisão que muda o que o dono vai ver ou o que você vai construir. Recomendação óbvia sem alternativa real vira suposição declarada. O inverso também vale: o que o dono vê na tela — rótulo, subtipo, cadastro, o que um formulário pede — é decisão dele, e sai como pergunta com alternativas, nunca como linha solta dentro da recomendação. Descartar uma alternativa exige o mesmo grep que a recomendação teve.

Read the full file on GitHub · 52 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. 5d ago Changed d80b48b360bd
  2. 1mo ago Changed · +19 lines e3e8828e4772
  3. 2mo ago First seen · 33 lines · 81 tokens per session scan A 025d82247617

Subscribe to this mod's changes

grilling is a skill published in the GitHub repository FHDumont/code-ai-template (2 stars, last pushed 5d ago), licensed MIT. It adds 81 tokens to every session and 1,538 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 2026-08-31.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

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

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 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

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens