A guided decision process that uses a project's written principles before exploring implementation choices. It asks one question at a time and creates a short brief for later planning.

Use it to work through design or product decisions using principles stored in project documentation.

It prevents brainstorming from jumping straight to a wide list of technical options without first agreeing on the project's reasons and constraints.

grill — Skill for Claude Code by technicalpickles

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 technicalpickles/pickled-claude-plugins --skill grill

Clone the repo

git clone --depth 1 https://github.com/technicalpickles/pickled-claude-plugins

Made for: Claude Code.

Or install stay-principled, the plugin that ships this one along with the rest of its 2 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/technicalpickles/pickled-claude-plugins/grill/github.svg)](https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/grill)

Your own site

<a href="https://agentmods.dev/skills/technicalpickles/pickled-claude-plugins/grill"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/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/technicalpickles/pickled-claude-plugins/grill"><img src="https://agentmods.dev/badge/skills/technicalpickles/pickled-claude-plugins/grill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 140 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,407 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	$0.00140	$0.01407
Opus 5.5	$0.00056	$0.00563
Sonnet 5.5	$0.00028	$0.00281
Haiku 4.5	$0.00014	$0.00141

Measured 1mo ago against content hash 76b0ff5b66d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 1mo 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.

plugins/stay-principled/skills/grill/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Grill with Principles

Walk a depth-first decision tree using the project's principles as the tree roots, before brainstorming opens. The mechanism is grill-me's: one question at a time, recommended answer per node, explore the codebase instead of asking when the answer is there. The anchor is principles, not generic decisions.

Why this exists

Brainstorming-style breadth-first menus drag conversations toward implementation variants. Depth-first walking with principle anchoring stays at the why level. Principles loaded as upfront context are necessary but not sufficient: they need to act as a forcing function during decision moments, not as wallpaper.

Process

1. Discover principles

Read docs/agents/principles.md if it exists. This is the canonical config written by stay-principled:setup.
Otherwise probe docs/principles.md and docs/ops-principles.md directly.
Resolve all paths against git rev-parse --show-toplevel so worktree invocations find the right files.
If nothing is found, ask: "No principles configured. Skip principle-anchoring, or run stay-principled:setup first?" and exit cleanly. Do not pretend to grill without principles. The whole point is anchoring.
If docs/agents/principles.md includes a ## Skip patterns section, check whether the current branch (git branch --show-current) or current path matches any pattern. If so, mention it to the user and ask whether to proceed anyway. The skip patterns are advisory in v1, not strict gates.

2. Read and shortlist

Read all configured principle files into your working set.
Based on the user's stated topic and visible context (recent commits, branch name, files mentioned, current cwd), propose a shortlist by number and name.
Cite by number AND name so the user can react fast: "I think principles 3 (agent proposes), 4 (capture vs triage), and 9 (resilience) bear on this. Anything I'm missing?"
If the topic touches a named domain in the domain map, include the domain-specific principles for that domain.
Wait for the user to confirm, add, or remove before moving on.

Read the full file on GitHub · 100 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.

1mo ago First seen · 100 lines · 140 tokens per session scan A 76b0ff5b66d4

Subscribe to this mod's changes

grill is a skill published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 1,407 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-12.

Building agents Claude Code Planning buildkite claude-skills monorepo workflow

create-pubsub-dotnet

Creates a Dapr pub/sub app in .NET (publisher, subscriber or both) with declarative, programmatic or streaming subscriptions, run with dapr run or Aspire. Use for "create a pub/sub app in .NET" or "build a Dapr publisher and subscriber in C#". For an existing project use add-pubsub-dotnet.

diagrid-labs/dapr-skills · 79 tokens

create-agent-dotnet

Creates a durable AI agent app in .NET with Microsoft Agent Framework on Dapr Workflow, run locally with dapr run. Use for "create an agent in .NET" or "scaffold a .NET agent". For Diagrid Catalyst use the catalyst-ai plugin.

diagrid-labs/dapr-skills · 59 tokens

create-workflow-from-diagram

Creates a Dapr workflow app from a diagram image (PNG, JPG, GIF, WebP) or a BPMN 2.0 file, in Go, Python, .NET, Java or JavaScript, run locally with dapr run. Use for "create a workflow from this diagram" or "scaffold a workflow from this BPMN". For a Mermaid or hand-drawn sketch, or Diagrid Catalyst, use the…

diagrid-labs/dapr-skills · 98 tokens

create-workflow-typescript

Creates a TypeScript Dapr app, run locally with dapr run, that demonstrates Workflow, service invocation, pub/sub, bindings, jobs, state and secrets. Use for "create a workflow in TypeScript" or "create a Dapr app in Node.js". For Diagrid Catalyst use the catalyst-ai plugin.

diagrid-labs/dapr-skills · 70 tokens

create-pubsub-python

Creates a Dapr pub/sub app in Python with FastAPI (publisher, subscriber or both) and declarative, programmatic or streaming subscriptions. Use for "create a pub/sub app in Python" or "build a FastAPI publisher and subscriber with Dapr". For an existing app use add-pubsub-python.