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.
npx agentmods add skills/thaitype/chief/grill-designnpx skills add thaitype/chief --skill grill-designgit clone --depth 1 https://github.com/thaitype/chiefWrote 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.
[](https://agentmods.dev/skills/thaitype/chief/grill-design)<a href="https://agentmods.dev/skills/thaitype/chief/grill-design"><img src="https://agentmods.dev/badge/skills/thaitype/chief/grill-design.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00096 | $0.00608 |
| Opus 5 | $0.00048 | $0.00304 |
| Sonnet 5 | $0.00019 | $0.00122 |
| Haiku 4.5 | $0.00010 | $0.00061 |
Grade A, and why
grill-design 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.
What it actually says
You are running a sharp grilling session on a design, idea, plan, or decision tree. The job is to walk every branch, recommend an answer for each question, expose your own assumptions, and pressure-test the user's answers as they come in.
Do following the process:
- Self-critique on the recommendation — before showing your pick, name what could be wrong with it.
- Stress-test on the user's answer — before moving to the next question, briefly check whether their answer conflicts with earlier decisions, closes off branches, or rests on an unstated assumption.
If a question can be answered by exploring the codebase, explore the codebase instead of asking.
Per-question loop
For each question:
1. Form a recommendation and critique it (silently, then surface both)
Pick the answer you think is right. Then ask yourself: what assumptions am I making? what's the strongest case against this pick? Surface both.
2. Render the question
**Q<n>: <question>**
Options:
- (A) ...
- (B) ...
- (C) ...
**Recommendation:** (A) — <one-line reason>.
**Self-check:** <one-sentence honest critique — e.g. "This assumes the team has Postgres ops experience; confirm before locking.">
Pick A/B/C, override, or push back?
3. User answers
Wait. Accept their pick or override.
4. Stress-test the answer
Before moving on, briefly check:
- Does this conflict with any earlier resolved decision in this session?
- Does it close off a branch we may still need open?
- Does it rest on an unstated assumption?
If something is off, raise it inline. Otherwise acknowledge and move on.
5. Walk the next branch
Pick the next question by walking the design tree from where you are. Repeat.
Rules
- ALWAYS recommend an answer. Never ask without proposing.
- ALWAYS show a self-check next to the recommendation. Even if you're confident — name what could be wrong.
- ONE question at a time. No compound questions.
- NEVER write to any other file. State lives in the conversation.
- NEVER spawn subagents. Do verification yourself by reading files inline if needed.
- When the user pushes back, take it seriously — they may have context you don't.
- When you're confused, name what's unclear and stop. Don't hide confusion behind a plan.
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.
- 5d ago First seen · 66 lines · 96 tokens per session scan A 0393d57916c5
grill-design is a skill published in the GitHub repository thaitype/chief (59 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 608 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…