multi-agent-system-pattern: Skill for Claude Code

.cursor/skills/grill-with-context/SKILL.md

grill-with-context is a skill for Claude Code, Cursor from vpeetla-ai/multi-agent-system-pattern. It costs 45 tokens per session (346 once invoked), scanned A, original, MIT.

An interview process for resolving decisions in a plan or design before implementation begins. It also records important terms in CONTEXT.md and identifies decisions that may deserve an architecture decision record, or ADR.

In plain words
What is it for?
Use it before features spanning several layers, integrations across repositories, or requests without clear success criteria, especially when you need to decide the responsible codebase, API mode, safety steps, and test strategy.
Why use it?
It prevents large or unclear changes from starting without agreed goals, ownership, scope, side effects, and testing expectations. It turns vague requests into a more concrete implementation plan.

Skill for Claude CodeCursor

Written for Claude Code and Cursor: disable-model-invocation in frontmatter, but also installed under .cursor/.

This is vpeetla-ai/multi-agent-system-pattern's own configuration. It tells Claude Code and Cursor how to work on multi-agent-system-pattern itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything multi-agent-system-pattern configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vpeetla-ai/multi-agent-system-pattern. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vpeetla-ai/multi-agent-system-pattern/main/.cursor/skills/grill-with-context/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-pattern

Made for: Claude Code, Cursor.

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-context

README.md
[![agentmods](https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/grill-with-context.svg)](https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/grill-with-context)
Your own site
<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/grill-with-context"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/grill-with-context.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 346 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00346
Opus 5 $0.00023 $0.00173
Sonnet 5 $0.00009 $0.00069
Haiku 4.5 $0.00005 $0.00035

Measured 6d ago against content hash f58c899fabbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

grill-with-context 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/skills/grill-with-context/SKILL.md · 41 lines

What it actually says

Grill With Context

Inspired by mattpocock/skills grill-with-docs — org-specific version.

When to use

  • New feature spanning multiple stack layers
  • Unclear which repo should own the change
  • User says "build X" without success criteria

Process

  1. Restate the goal in one sentence; ask if correct
  2. Grill — ask one question at a time until resolved:
    • Which stack layer? (see governed-ai-stack)
    • What defines done? (test, demo URL, metric)
    • Side effects? (gateway/HITL required?)
    • Stub mode or live API keys?
  3. Sharpen vocabulary — if the user uses vague terms, propose CONTEXT.md entries
  4. ADR candidates — flag decisions that need an ADR in ai-architecture-portfolio
  5. Output — short plan with repo, files, test strategy, out-of-scope list

Rules

  • Do not start coding until grilling is complete
  • Do not ask five questions in one message
  • Prefer multiple-choice when options are finite

After grilling

Suggest tdd-agent-loops for implementation or to-prd equivalent: write plan to docs/plans/<slug>.md

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. 6d ago First seen · 41 lines · 45 tokens per session scan A f58c899fabbe

Subscribe to this mod's changes

grill-with-context is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 2d ago), licensed MIT. It adds 45 tokens to every session and 346 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.

Related

Other skills, from other repositories

data-visualization

Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.

langchain-ai/deepagents · 40 tokens

cuml-machine-learning

Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.

langchain-ai/deepagents · 43 tokens

blog-post

Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.

langchain-ai/deepagents · 58 tokens

social-media

Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.

langchain-ai/deepagents · 58 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens

cudf-analytics

Use for GPU-accelerated data analysis on datasets, CSVs, or tabular data using NVIDIA cuDF. Triggers when tasks involve groupby aggregations, statistical summaries, anomaly detection, or large-scale data profiling.

langchain-ai/deepagents · 51 tokens