chief-grill

chief-grill is a skill for Claude Code, Codex from thaitype/chief. It costs 126 tokens per session (1,858 once invoked), scanned A, original, MIT.

A guided design interview that asks one question at a time and checks each answer against the codebase. It saves the discussion in a project file so an unfinished session can be resumed.

In plain words
What is it for?
It helps pressure-test a design, clarify requirements, review existing project rules, and maintain a persistent record of open and resolved decisions.
Why use it?
It exposes contradictions, unsupported assumptions, and conflicts with earlier decisions before implementation begins. Codebase checks help keep the design grounded in what actually exists.

Skill for Claude CodeCodex

Part of the chief-skills plugin — 14 skills shipped together

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/thaitype/chief/chief-grill
Any agent
npx skills add thaitype/chief --skill chief-grill
Clone the repo
git clone --depth 1 https://github.com/thaitype/chief

Made for: Claude Code, Codex.

Or install chief-skills, the plugin that ships this one along with the rest of its 14 skills.

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 chief-grill

README.md
[![agentmods](https://agentmods.dev/badge/skills/thaitype/chief/chief-grill.svg)](https://agentmods.dev/skills/thaitype/chief/chief-grill)
Your own site
<a href="https://agentmods.dev/skills/thaitype/chief/chief-grill"><img src="https://agentmods.dev/badge/skills/thaitype/chief/chief-grill.svg" alt="Measured on agentmods" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,858 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 5.1 $0.00126 $0.01858
Opus 5 $0.00063 $0.00929
Sonnet 5 $0.00025 $0.00372
Haiku 4.5 $0.00013 $0.00186

Measured 6d ago against content hash ddeaa3d73441, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

chief-grill 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 6d 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.

skills/chief/chief-grill/SKILL.md · 172 lines

How it starts

The opening of the file, as written. The whole thing — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are running a verified grill session. This is /grill-design with two extra things bolted on:

  1. Per-question self-review (in-skill). Before recommending an answer, you critique your own pick. After the user answers, you stress-test their answer.
  2. Per-question background verification by answer-verifier-agent. While the user is thinking about the next question, the agent cross-references the previous answer against the actual codebase. Findings surface as a sidebar.
  3. Persistent session log. All state lives in .chief/_grill/opened/NNNN-topic.md. Survives compaction and /clear.

Ask one question at a time. Wait for the user. Provide a recommended answer with each question.

Steps

1. Pre-flight

Inspect (do not create yet):

  • .chief/ — exists?
  • .chief/_grill/ — exists?
  • .chief/_grill/opened/ and .chief/_grill/closed/ — exist?
  • Any unresolved sessions in .chief/_grill/opened/?

2. Resume or start fresh

If .chief/_grill/opened/ contains files, list them with their topics (read the H1 of each) and ask:

Found N open grill session(s). Resume one, or start fresh?

  1. Resume 0003-payment-sdk (12 resolved, 3 open)
  2. Resume 0007-auth (5 resolved, 0 open — ready for final review)
  3. Start fresh

If the user picks resume → load that file as the session log, jump to step 5. If the user picks fresh → continue to step 3. If opened/ is empty or missing → continue to step 3.

3. Topic and slug

Take the first user message after /chief-grill was invoked (or the most recent describing what to grill). Derive a kebab-case topic slug from it (3–5 words max). Show it to the user:

Topic: payment-sdk. Continue, or pick a different slug?

If the user overrides, use their slug.

4. Create session log (deferred scaffolding)

Now scaffold the directories that don't exist yet:

  1. Create .chief/_grill/, .chief/_grill/opened/, .chief/_grill/closed/ as needed.
  2. Compute next sequence number: count files in opened/ + closed/, add 1, zero-pad to 4 digits.
  3. Create .chief/_grill/opened/NNNN-<slug>.md with this initial content:

Read the full file on GitHub · 172 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. 6d ago First seen · 172 lines · 126 tokens per session scan A ddeaa3d73441

Subscribe to this mod's changes

chief-grill is a skill published in the GitHub repository thaitype/chief (59 stars, last pushed today), licensed MIT. It adds 126 tokens to every session and 1,858 once invoked, about $0.0006 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

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

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

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens