grill-with-docs-batch

grill-with-docs-batch is a skill for Claude Code, Codex from MiaoDX/intuitive-flow. It costs 72 tokens per session (2,279 once invoked), scanned A, original, MIT.

A batch version of a documentation review process that stress-tests a plan against a project’s documents and domain terms. It groups related questions and checks whether the documents already support a sound decision.

In plain words
What is it for?
Use it to review plans, architecture decisions, and specifications against domain documentation, then ask focused batches of questions only where uncertainty remains.
Why use it?
It reduces repeated discussion by separating decisions that need human agreement from implementation choices the agent can make locally.

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/miaodx/intuitive-flow/grill-with-docs-batch
Any agent
npx skills add MiaoDX/intuitive-flow --skill grill-with-docs-batch
Clone the repo
git clone --depth 1 https://github.com/MiaoDX/intuitive-flow

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-batch

README.md
[![agentmods](https://agentmods.dev/badge/skills/miaodx/intuitive-flow/grill-with-docs-batch.svg)](https://agentmods.dev/skills/miaodx/intuitive-flow/grill-with-docs-batch)
Your own site
<a href="https://agentmods.dev/skills/miaodx/intuitive-flow/grill-with-docs-batch"><img src="https://agentmods.dev/badge/skills/miaodx/intuitive-flow/grill-with-docs-batch.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,279 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 $0.00072 $0.02279
Opus 5 $0.00036 $0.01140
Sonnet 5 $0.00014 $0.00456
Haiku 4.5 $0.00007 $0.00228

Measured 5d ago against content hash d22f17a49ba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

grill-with-docs-batch 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.

skills/grill-with-docs-batch/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill With Docs Batch

Challenge a plan against the repository's domain model and documentation like grill-with-docs, but move in small coherent batches instead of one question at a time.

First Decide Whether To Stop

Before asking any batch, run a saturation audit:

  • Read the target plan/ADR/spec and the domain glossary or context file it depends on.
  • Check recent git history for the same target docs when available, but use it only as supporting evidence. Commit count is not a stop condition by itself; it helps find decisions that were already made and areas that may be getting re-litigated.
  • Separate durable decision questions from implementation defaults. Do not ask the user to discuss things the implementation can decide locally without changing public contracts, private-data boundaries, safety policy, cost/model infrastructure, or irreversible file moves.
  • If an ADR is accepted, a plan names what changes, what is out of scope, the important boundaries, the acceptance gates, and the next execution step, and local docs/code do not contradict it, answer that no more discussion is needed.
  • Classify the documentation target before proposing updates: plans and ADRs answer different questions, and some tasks legitimately need both.

When the user asks whether remaining questions exist, answer the yes/no first. Only ask a batch if at least one unresolved question would materially change the plan, contract, public/private boundary, or acceptance gate.

Convergence Loop

This skill should remove the burden of asking "are we done yet?" from the user. After every accepted batch, do the loop yourself:

  1. Interpret the user's reply, including shorthand such as "LGTM", "all agree", "others are fine", "2 no because...", or "do it".
  2. Apply the resolved updates to the plan, context doc, or ADR surface named in the batch. If no document update is warranted, say why.
  3. Re-read the updated target and run a fresh saturation audit.
  4. Either ask the next material batch or stop with the no-more-discussion response.

Read the full file on GitHub · 227 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 · 227 lines · 72 tokens per session scan A d22f17a49ba8

Subscribe to this mod's changes

grill-with-docs-batch is a skill published in the GitHub repository MiaoDX/intuitive-flow (48 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 2,279 once invoked, about $0.0004 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.