grill

grill is a skill for Claude Code, Codex from lwalden/AIAgentMinder. It costs 10 tokens per session (719 once invoked), scanned A, original, MIT.

A structured questioning tool for testing a software plan or design by examining each choice and its possible outcomes. It is intended for work with several connected decisions or important risks.

In plain words
What is it for?
Use it to examine feature plans, design documents, pull request descriptions, or proposed approaches involving choices such as authentication, rate limits, or error formats.
Why use it?
It exposes assumptions, missing cases, and conflicts before implementation begins, when changing the plan is usually easier.

Skill for Claude CodeCodex

Part of the aiagentminder plugin — 15 skills, 16 agents, 5 hooks 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/lwalden/aiagentminder/grill
Any agent
npx skills add lwalden/AIAgentMinder --skill grill
Clone the repo
git clone --depth 1 https://github.com/lwalden/AIAgentMinder

Made for: Claude Code, Codex.

Or install aiagentminder, the plugin that ships this one along with the rest of its 15 skills, 16 agents, 5 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/lwalden/aiagentminder/grill.svg)](https://agentmods.dev/skills/lwalden/aiagentminder/grill)
Your own site
<a href="https://agentmods.dev/skills/lwalden/aiagentminder/grill"><img src="https://agentmods.dev/badge/skills/lwalden/aiagentminder/grill.svg" alt="Measured on agentmods" height="20"></a>
Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 719 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 $0.00010 $0.00719
Opus 5 $0.00005 $0.00360
Sonnet 5 $0.00002 $0.00144
Haiku 4.5 $0.00001 $0.00072

Measured 5d ago against content hash a3b77e3c0607, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 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/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aiagentminder:grill - Plan Interrogation

Stress-test a plan or design by walking every branch of the decision tree. This is the intensive counterpart to the Approach-First check embedded in the dev agent profile — use it when a design is non-obvious, high-stakes, or involves multiple interdependent decisions.


Step 1: Scope the Interrogation

Read the plan or design being questioned. Sources may include:

  • An approach statement from the dev agent's Approach-First check
  • A feature description from docs/strategy-roadmap.md
  • A freeform plan the user describes
  • An existing design doc or PR description

Also read:

  • DECISIONS.md — for prior decisions that constrain the design space
  • docs/strategy-roadmap.md — for scope context

Step 2: Map the Decision Tree

Identify every decision branch in the plan — any point where two or more reasonable approaches exist. Present the branches as a numbered list, noting dependencies between them.

Example:

Decision branches identified:

  1. Auth storage: session vs JWT
  2. Rate limiting: middleware vs API gateway (depends on #1)
  3. Error format: structured vs freeform

Step 3: Walk Each Branch

For each decision branch, one at a time:

  1. If the codebase can answer it — explore the code first. Check existing patterns, conventions, and constraints. Do not ask the user questions that the code can answer.
  2. If the user needs to decide — present:
    • The options available
    • Tradeoffs of each
    • Reversal cost: High (hard to undo), Medium (costly but possible), or Low (easy to change later)
    • Downstream dependencies: "If you choose X, then Y becomes constrained"

Resolve one branch before moving to the next. If branches have dependencies, resolve the upstream branch first.

Continue until the user says they are satisfied or all branches are resolved.


Step 4: Decision Summary

After all branches are resolved, produce a structured summary:

Grill Summary — {plan name}

Decisions made:
1. {topic}: {choice}. Alternatives: {what was considered}. Reversal cost: {H/M/L}. Rationale: {why}.
2. ...

Open questions (deferred):
- {question} — deferred because {reason}

Constraints discovered:
- {constraint found during codebase exploration}

Read the full file on GitHub · 92 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 · 92 lines · 10 tokens per session scan A a3b77e3c0607

Subscribe to this mod's changes

grill is a skill published in the GitHub repository lwalden/AIAgentMinder (4 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 719 once invoked, about $0.0001 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 2026-08-31.

Related

Other skills, from other repositories

sdd-serve

Serve the SDD Builder's AI request queue: claim requests with sddnextrequest, draft the proposal, answer with sddrespondrequest. Never writes spec files — the user accepts each proposal in the builder. Use when the user asks to attend, serve or listen to the SDD board queue. / Atiende la cola de peticiones del SDD…

juanklagos/spec-driven-development-template · 80 tokens

sdd-workflow

Guide a project with Spec-Driven Development (SDD) discipline - idea, approved spec, consistent plan, tasks, a gate that verifies approval and consent, implementation, validation, and logbook. Bilingual EN/ES. Use when the user wants to start, spec, plan, implement, or validate work with SDD, or mentions specs, plans…

juanklagos/spec-driven-development-template · 84 tokens

metrics-instrumentation

Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…

comet-ml/opik · 93 tokens

notifications

Send notifications through the unified notification router.

vellum-ai/vellum-assistant · 9 tokens

release

Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.

lycorp-jp/sim-use · 61 tokens

vellum-skills-catalog

Discover bundled skills and search/install community skills from the skills.sh registry.

vellum-ai/vellum-assistant · 20 tokens