Is the Grill skill free?

Yes. The skill itself is free from Kanevry/session-orchestrator. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Grill SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install Grill?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Grill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Grill

Adversarial one-question-at-a-time interrogation of a plan, grounded in the actual codebase.

by Kanevry · Kanevry/session-orchestrator

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 2e4406a

Grilled a 'password-reset in 2 days' plan against a small stub codebase and it immediately surfaced a real, load-bearing code contradiction — verifyPassword() unconditionally returns true and verifyToken() always resolves to the same fake user — turning a generic checklist review into a concrete account-takeover finding a plain baseline pass missed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What Grill does

Pressure-tests a plan, design, or PRD the user already believes in: maps the decision tree, greps the codebase to resolve what the code can already answer, then walks remaining branches one question at a time using six tactics (glossary conflict, fuzzy-term sharpening, code contradiction, edge-case, assumption audit, pre-mortem). Triggers on 'grill me', 'stress-test this plan', 'poke holes in my design'; explicitly steps aside for still-ambiguous designs (use brainstorm instead).

How to install Grill

git clone https://github.com/Kanevry/session-orchestrator
mkdir -p ~/.claude/skills
cp -r session-orchestrator/skills/grill ~/.claude/skills/grill

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Grill

/grill Adversarial one-question-at-a-time interrogation of a plan, grounded in the actual codebase.

It also activates on plain-language prompts like these:

Stress-test this plan before I start building it, poke holes in it.
Challenge every assumption in this PRD before we ship the payment flow.
Interrogate my design for the export feature and find the weak spots.

Frequently asked questions

Is the Grill skill free?: Yes. The skill itself is free from Kanevry/session-orchestrator. SkillProof publishes the install command and an independent test verdict at no cost.
Does Grill work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Grilled a 'password-reset in 2 days' plan against a small stub codebase and it immediately surfaced a real, load-bearing code contradiction — verifyPassword() unconditionally returns true and verifyToken() always resolves to the same fake user — turning a generic checklist review into a concrete account-takeover finding a plain baseline pass missed.
What is the Grill SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install Grill?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Grill with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.