A structured interview that challenges a development plan’s assumptions using project documents, the codebase, and agreed rules.

Pressure-testing plans, resolving choices branch by branch, and preparing evidence-backed decisions for a project.

It exposes unclear decisions, conflicting terminology, and unsupported assumptions before implementation begins.

duck-grill — Skill for Claude Code by sprngr

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 sprngr/rubber-duck --skill duck-grill

Clone the repo

git clone --depth 1 https://github.com/sprngr/rubber-duck

Made for: Claude Code.

Or install rubber-duck, the plugin that ships this one along with the rest of its 17 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-grill/github.svg)](https://agentmods.dev/skills/sprngr/rubber-duck/duck-grill)

Your own site

<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-grill"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-grill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sprngr/rubber-duck/duck-grill"><img src="https://agentmods.dev/badge/skills/sprngr/rubber-duck/duck-grill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,175 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.02175
Opus 5	$0.00020	$0.01087
Sonnet 5	$0.00008	$0.00435
Haiku 4.5	$0.00004	$0.00217

Measured 13d ago against content hash 513e1eac0202, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

duck-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 13d 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/duck-grill/SKILL.md · 238 lines

How it starts

The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grilling interview 🦆. Batch up to 3 questions per turn. Challenge assumptions. Ground in evidence.

Purpose

Pressure-test plans through deep interrogation until decision is explicit, evidence-backed, and risk-aware.

Philosophy Guardrails (skill-local)

Inherit shared guardrails from references/GUARDRAILS.md.

ask 1-3 targeted clarifying questions when context is incomplete
state assumptions explicitly when evidence is missing

Philosophy Guardrails (skill-local delta)

Skill-specific delta:

Socratic interrogation mode; batch up to 3 related questions per turn to reduce question fatigue
Ground challenges in repo evidence (CONTEXT.md, ADRs, code reality)
Challenge glossary conflicts immediately; sharpen vague terms into canonical terms from CONTEXT.md
Document updates (ADRs, CONTEXT.md) require execution approval as semantic changes

Activation

Use when user explicitly requests deep plan grilling, assumption validation, or branch-by-branch decision resolution (e.g., "grill this", "grill with ducks", "challenge my assumptions").

Method

1. Clarify scope (if ambiguous)

ask 1-3 targeted clarifying questions when context is incomplete
state assumptions explicitly when evidence is missing

If grilling target is unclear, ask one scoping question:

"What decision needs grilling?" (architecture / rollout / product choice)
"What does 'done' look like for this session?" (decision locked / approach validated / spec ready / ADR written)
"What's the risk exposure?" (irreversible / expensive / trust-boundary)
"What evidence should constrain this?" (code / docs / domain model)

2. Ground in evidence first

If challenging an assumption, anchor it in:

CONTEXT.md / CONTEXT-MAP.md and docs/adr/ (if present)
Code reality (definitions, callers, tests, runtime behavior)
Domain language consistency (challenge glossary conflicts immediately)

When referencing evidence, use meaningful names not bare numbers: "ADR-003: Database choice" not just "#42"

Read the full file on GitHub · 238 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

13d ago First seen · 238 lines · 41 tokens per session scan A 513e1eac0202

Subscribe to this mod's changes

duck-grill is a skill published in the GitHub repository sprngr/rubber-duck (8 stars, last pushed 3d ago), licensed MIT. It adds 41 tokens to every session and 2,175 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 2026-08-31.

Claude Code Planning agent-skills ai-agents antivibe decision-quality developer-tools

expert-redteam-review

Use when a user asks to evaluate a complex, high-impact, ambiguous, cross-functional, or hard-to-reverse decision; mentions expert panel, red team, adversarial review, rebuttal, judge, arbitration, risk review, challenge assumptions, poke holes, or wants stronger decision quality than a normal review.

carbonshow/intent-fluid · 67 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

duck-grill