grilling

grilling is a skill for Claude Code, Codex from terva-sh/terva. It costs 37 tokens per session (895 once invoked), scanned A, original, MIT.

An interview process that asks the user about important decisions before building something. It maps which choices depend on earlier choices so the requirements are clear.

In plain words
What is it for?
Use it when a project has several open design decisions and the user wants to be questioned before implementation begins.
Why use it?
It reduces the risk of confidently building the wrong product or workflow from unstated assumptions.

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/terva-sh/terva/grilling
Any agent
npx skills add terva-sh/terva --skill grilling
Clone the repo
git clone --depth 1 https://github.com/terva-sh/terva

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 grilling

README.md
[![agentmods](https://agentmods.dev/badge/skills/terva-sh/terva/grilling.svg)](https://agentmods.dev/skills/terva-sh/terva/grilling)
Your own site
<a href="https://agentmods.dev/skills/terva-sh/terva/grilling"><img src="https://agentmods.dev/badge/skills/terva-sh/terva/grilling.svg" alt="Measured on agentmods" height="20"></a>
Per session 37 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 895 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 $0.00037 $0.00895
Opus 5 $0.00018 $0.00447
Sonnet 5 $0.00007 $0.00179
Haiku 4.5 $0.00004 $0.00089

Measured 5d ago against content hash 18a20398aab7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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.

packages/agent/skills/builtin/grilling/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grilling

Run this when the user asks to be interviewed before you build. It prevents the expensive failure: building the wrong thing confidently, from a goal you and the user each read differently.

The trigger is the ask, not your own read of whether a request is vague. You are poor at noticing that you are about to invent a decision, so do not wait to feel uncertain. When you do spot unstated decisions and the user has not asked for an interview, name the two or three that matter and offer to run this, rather than starting an interview nobody requested.

Leave it alone when the shape is already clear: a one-line fix, a rename, a question with one obvious answer. An interview over a settled task spends the user's attention for nothing.

The design tree and the frontier

Every decision branches into the decisions that hang off it. Picking a storage engine opens questions about migration and backup; it settles none of the questions about the interface above it.

The frontier is every decision whose prerequisites are already settled: the questions answerable now, without guessing at an answer you have not heard yet. A question whose answer depends on another question still open belongs to a later round, not this one.

Working the frontier is what keeps an interview short. Asking a downstream question early forces the user to invent a premise, and you then build on it.

The loop

  1. Map the frontier. From what the user has said, list every decision that is open and answerable now. Park the rest as later branches.
  2. Send every fact question to a sub-agent. Anything answerable from the environment goes to swarm_spawn rather than to the user: what the config says, whether a symbol exists, how a test behaves today. Only the questions downstream of that exploration wait for it; ask the rest of the frontier now.
  3. Ask the whole frontier in one round, using a single ask_user_question call. See the format below.
  4. Recompute the frontier from the answers. New answers settle prerequisites and usually open new branches.
  5. Repeat from step 2 until the frontier is empty.
  6. State the shared understanding back and wait for confirmation.

Read the full file on GitHub · 80 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 First seen · 80 lines · 37 tokens per session scan A 18a20398aab7

Subscribe to this mod's changes

grilling is a skill published in the GitHub repository terva-sh/terva (2 stars, last pushed 3d ago), licensed MIT. It adds 37 tokens to every session and 895 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 2026-08-31.

Related

Other skills, from other repositories

pi-sync

Daily upstream-sync job for the pi Go port — fetch upstream pi, triage every change since the recorded pin, port what's in scope, verify idiomatic + parity via independent reviews, update the ledger, and push. Use for "sync with upstream", "porting job", or as the scheduled daily run.

sky-valley/pi · 66 tokens

pi-go-review

Review ported Go code for idiomatic quality — that the port maximizes Go rather than transliterating TypeScript. Use after porting upstream pi changes, or standalone on any diff in this repo.

sky-valley/pi · 45 tokens

use-modern-go

Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.

JetBrains/go-modern-guidelines · 32 tokens

modern-go

Modernize Go code by applying version-appropriate idioms and APIs (gofix-style transformations). Scans go.mod for the Go version, then transforms Go source files to use modern patterns—from Go 1.0 through 1.26+. Use when the user says "现代化","现代Go语言", "地道的", "idiomatic", "modernize", "modern-go", "update Go code"…

smallnest/pigo · 102 tokens

go-127

What changed in Go 1.27 (released August 2026) and how it changes the way Go is written in pi-go. Use this skill when writing or reviewing Go that could use a 1.27 feature, when bumping the go directive in go.mod, when a build or test behaves differently after a toolchain upgrade, or when code-guidelines-go points…

dimetron/pi-go · 177 tokens

code-guidelines-go

Go 1.24–1.27 coding guidelines for the dimetron/pi-go AI agent runtime. Use this skill whenever writing, reviewing, or refactoring ANY Go code in pi-go. This covers idiomatic style, error handling, concurrency, project layout, testing (table-driven, fuzz, benchmarks, synctest), new stdlib usage, golangci-lint v2…

dimetron/pi-go · 124 tokens