grill-with-docs

grill-with-docs is a skill for Claude Code, Codex from znlgis/my-opencode-deepseek-config. It costs 33 tokens per session (291 once invoked), scanned A, original, MIT.

A combined questioning and terminology practice for requests that are unclear and use inconsistent domain words. It asks one focused question at a time while recording clearer definitions in the project glossary.

In plain words
What is it for?
Use it to clarify requirements, distinguish competing interpretations, and pin down fuzzy terms in CONTEXT.md as decisions are made.
Why use it?
It helps teams resolve both what they want and what their key terms mean before implementation begins. This reduces misinterpretations caused by ambiguous requirements or shifting vocabulary.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to clarify requirements, distinguish competing interpretations, and pin down fuzzy terms in CONTEXT.md as decisions are made.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/znlgis/my-opencode-deepseek-config/grill-with-docs
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.

Any agent
npx skills add znlgis/my-opencode-deepseek-config --skill grill-with-docs
Clone the repo
git clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-config

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 grill-with-docs

README.md
[![agentmods](https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/grill-with-docs.svg)](https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/grill-with-docs)
Your own site
<a href="https://agentmods.dev/skills/znlgis/my-opencode-deepseek-config/grill-with-docs"><img src="https://agentmods.dev/badge/skills/znlgis/my-opencode-deepseek-config/grill-with-docs.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 291 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.00291
Opus 5 $0.00016 $0.00146
Sonnet 5 $0.00007 $0.00058
Haiku 4.5 $0.00003 $0.00029

Measured 4d ago against content hash d5b060982278, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grill-with-docs 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 4d 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.

opencode/skills/grill-with-docs/SKILL.md · 33 lines

What it actually says

Grill With Docs

Compose the grilling and domain-modeling skills when a request is ambiguous and the project's domain terms are themselves fuzzy. Converge on intent one question at a time while pinning down the vocabulary.

When to use

  • Requirements are ambiguous (multiple interpretations with different effort).
  • The domain language is inconsistent — the same concept is called different things, or a term's meaning shifts between uses.

How

  1. Load the grilling skill for the question discipline: ask ONE question at a time, prefer multiple choice, until intent is clear.
  2. Load the domain-modeling skill for the glossary discipline: as each answer sharpens a term, record it in CONTEXT.md inline.
  3. Alternate: a grilling question that exposes a fuzzy term becomes a domain-modeling clarification before you continue grilling.

Rules

  • Never batch questions — one at a time, per grilling.
  • Never let a fuzzy term pass unexamined — if a word could mean two things, the answer is ambiguous until you pin it down.
  • Stop as soon as intent is clear enough to proceed; do not over-grill.
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. 4d ago First seen · 33 lines · 33 tokens per session scan A d5b060982278

Subscribe to this mod's changes

grill-with-docs is a skill published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 291 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.