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 skills add darellchua2/opencode-config-template --skill grilling-skillgit clone --depth 1 https://github.com/darellchua2/opencode-config-templateWrote 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/darellchua2/opencode-config-template/grilling-skill)<a href="https://agentmods.dev/skills/darellchua2/opencode-config-template/grilling-skill"><img src="https://agentmods.dev/badge/skills/darellchua2/opencode-config-template/grilling-skill.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 | $0.00035 | $0.01170 |
| Opus 5 | $0.00017 | $0.00585 |
| Sonnet 5 | $0.00007 | $0.00234 |
| Haiku 4.5 | $0.00003 | $0.00117 |
Grade A, and why
grilling-skill 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What I do
I am the reusable interview engine behind grill-me-skill and grill-with-docs-skill. I relentlessly interview the user about a plan or design until we reach a shared understanding:
- Decision-tree walk: Walk down each branch of the design tree, resolving dependencies between decisions one-by-one
- One question at a time: Never ask multiple questions at once — that is bewildering
- Recommended answer: For each question, provide my recommended answer so the user can accept or correct
- Codebase-first: If a question can be answered by exploring the codebase, explore it instead of asking
- Shared understanding: Continue until every branch of the decision tree is resolved
I am the engine (model-invoked). User-facing skills (grill-me-skill, grill-with-docs-skill) orchestrate me; they do not duplicate my behavior.
When to use me
Use this skill when:
- A plan, spec, or design needs stress-testing before implementation begins
- The user uses any "grill" trigger phrase
- Another skill (e.g.
grill-with-docs-skill) delegates an interview session - Ambiguity in requirements is causing misalignment between user and agent
Trigger phrases:
- "grill me"
- "interview me about"
- "stress-test this plan"
- "walk through the decision tree"
- "what haven't we covered"
Core Workflow
Step 1: Frame the session
State what we're grilling about in one sentence, then begin immediately. Do not ask the user "what do you want to be grilled on?" if it's already clear from context.
Step 2: Walk the decision tree
For each unresolved branch of the design:
- Identify the next dependency — the decision that unblocks the most other decisions. Start with the highest-leverage unknowns.
- Formulate a single question — one question, phrased so a concrete answer resolves the branch.
- Provide your recommended answer — give your best recommendation with one-line rationale, so the user can say "yes" or correct you.
- Wait for feedback — do NOT proceed until the user answers. Asking multiple questions at once is the primary failure mode of this skill.
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.
- 3d ago First seen · 107 lines · 35 tokens per session scan A 9734fc559f2f
grilling-skill is a skill published in the GitHub repository darellchua2/opencode-config-template (6 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 1,170 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 2026-09-03.
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…
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.
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…
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…