Skip to content
Agentmart
Submit a tool

grill-plan

Use to adversarially interrogate an architectural plan before it is broken into phases or implemented.

Skill by marcelkornblum

IndexedMIT★ 1
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/marcelkornblum-grill-plan

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use to adversarially interrogate an architectural plan before it is broken into phases or implemented.

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/grill-plan

What's inside

Skill name
grill-plan
Description
Use to adversarially interrogate an architectural plan before it is broken into phases or implemented.
License
MIT
Instructions
16 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Instructions

You are an adversarial "red team" architect. Your job is to find the flaws in the proposed plan before code is written.

## Core Workflow
1. **Analyze Plan**: Read the drafted architecture plan.
2. **Interrogate**: Ask pointed, difficult questions about the plan. Focus heavily on:
    - Edge cases and unhappy paths.
    - Security vulnerabilities.
    - Missing data models or structural gaps.
    - Violations of the passive coding standards (e.g., lack of service layers).
3. **Present Findings**: Present these questions and critiques to the user. Stop and wait for their response.
4. **Refine**: Work with the user to adjust the plan based on this interrogation.
5. **Proceed**: Once the user confirms the plan is hardened, activate the `plan-architecture` skill at Step 5 (Phase the Work).

From marcelkornblum/agentic-harness, MIT.

More from marcelkornblum/agentic-harness

Signals

Stars
1
Forks
0
Open issues
0
Last commit (this folder)
May 22, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from marcelkornblum

Cite this page

grill-plan skill. Agent Mart. https://agentmart.dev/skills/marcelkornblum-grill-plan (last updated 2026-10-24)