plastic-intent-grilling

plastic-intent-grilling is a skill for Claude Code, Codex from zalom/plastic. It costs 87 tokens per session (1,140 once invoked), scanned A, original, MIT.

A structured brainstorming process that questions a plan or design in depth until its assumptions and decisions are understood.

In plain words
What is it for?
Reviewing software architecture, feature designs, workflows, product plans, and other proposals through detailed questions and discussion.
Why use it?
It helps reveal missing requirements, risks, dependencies, and unclear choices before work begins.

Skill for Claude CodeCodex

Part of the plastic plugin — 43 skills, 10 agents, 5 hooks, 1 MCP server 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/zalom/plastic/intent-grilling
Any agent
npx skills add zalom/plastic --skill intent-grilling
Clone the repo
git clone --depth 1 https://github.com/zalom/plastic

Made for: Claude Code, Codex.

Or install plastic, the plugin that ships this one along with the rest of its 43 skills, 10 agents, 5 hooks, 1 MCP server.

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 plastic-intent-grilling

README.md
[![agentmods](https://agentmods.dev/badge/skills/zalom/plastic/intent-grilling.svg)](https://agentmods.dev/skills/zalom/plastic/intent-grilling)
Your own site
<a href="https://agentmods.dev/skills/zalom/plastic/intent-grilling"><img src="https://agentmods.dev/badge/skills/zalom/plastic/intent-grilling.svg" alt="Measured on agentmods" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,140 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 $0.00087 $0.01140
Opus 5 $0.00044 $0.00570
Sonnet 5 $0.00017 $0.00228
Haiku 4.5 $0.00009 $0.00114

Measured 4d ago against content hash 8ee89f6a38e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plastic-intent-grilling 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.

skills/intent-grilling/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill Me — Deep Brainstorming

You are about to interview the user relentlessly. This is NOT a quick brainstorm — it is a thorough interrogation of every assumption, dependency, and design decision until you reach shared understanding.

Detect Mode

Coding mode — the user is designing something that involves code (feature, architecture, refactor, system design):

  • You CAN and SHOULD explore the codebase to answer your own questions
  • Before asking "how does X work?", check if you can find out yourself
  • Ground your questions in what actually exists, not what you imagine

Non-coding mode — the user is designing something conceptual (process, workflow, strategy, product):

  • No codebase to explore
  • Focus purely on the design tree

Workflow

1. Identify the Root

Ask: "What are we designing?" Get the one-sentence version. Restate it back to confirm.

2. Walk the Decision Tree

For each branch of the design:

  1. State the branch — "Let's talk about [aspect]."
  2. Ask your question — Be specific. "How will X handle Y when Z happens?"
  3. Provide your recommended answer — Always lead with what YOU think the answer should be, based on what you know. Let the user confirm, correct, or redirect.
  4. Resolve before moving on — Do not leave ambiguity. If the user says "I'm not sure", help them decide. Push.
  5. Track dependencies — If decision A affects decision B, say so. Resolve A first.

3. Be Relentless

  • Do NOT accept vague answers. "It depends" requires "on what?"
  • Do NOT skip edge cases. "What happens when the list is empty?"
  • Do NOT assume. If you think you know, verify.
  • Do NOT be polite at the expense of thoroughness. Friendly but unrelenting.
  • DO challenge the user's assumptions. "Why not [alternative]?"
  • DO synthesize as you go. After every 3-4 questions, summarize what's been decided.

4. Time Awareness

This process is thorough. It typically takes 20-45 minutes for a complex design. At natural checkpoints (~every 10 questions), offer:

Read the full file on GitHub · 109 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. 4d ago First seen · 109 lines · 87 tokens per session scan A 8ee89f6a38e4

Subscribe to this mod's changes

plastic-intent-grilling is a skill published in the GitHub repository zalom/plastic (10 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 1,140 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 2026-08-31.

Related

Other skills, from other repositories

autoprompt

Explicit-only useful-first orchestration. Invoke only when the user names autoprompt - typed as /autoprompt or in plain language such as "act in autoprompt mode" - to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Do not infer invocation from…

Spielewoy/autoprompt-skill · 85 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

autoprompt

Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.

Spielewoy/autoprompt-skill · 56 tokens

agent-spec-tool-first

CRITICAL: Use for agent-spec CLI tool workflow. Triggers on: agent-spec, contract, lifecycle, guard, verify, explain, stamp, checkpoint, plan, requirements, work-units, knowledge requirements, KLL, docs vs knowledge, spec verification, task contract, spec quality, lint spec, run log, "how to verify", "how to use…

ZhangHanDong/agent-spec · 165 tokens

agent-spec-authoring

CRITICAL: Use for writing and editing agent-spec .spec/.spec.md files. Triggers on: write spec, create spec, edit spec, new spec, spec authoring, task contract, .spec file, .spec.md file, BDD scenario, acceptance criteria, completion criteria, test selector, boundary, constraint, intent, decision, out of scope, "how…

ZhangHanDong/agent-spec · 172 tokens

agent-spec-intent-compiler

Use when converting PRD or issue prose into KLL requirements, running the intent compiler plan, or reverse-interviewing a human to resolve requirement ambiguity before task spec generation.

ZhangHanDong/agent-spec · 42 tokens