Agent Builder
shareAI-lab/learn-claude-code
Design and build AI agents for any domain. An agent skill from shareAI-lab/learn-claude-code.
Protocol that interviews the user in rounds over the Architect's design tree.
Install Grill
$ npx skills add ntorga/agent-starter-kit --skill grill -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ntorga/agent-starter-kit grill --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/grill .claude/skills/grill && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .claude/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ntorga/agent-starter-kit/tree/main/skills/grillType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ntorga/agent-starter-kit --skill grill -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ntorga/agent-starter-kit grill --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/grill .agents/skills/grill && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .agents/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill grill -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ntorga/agent-starter-kit grill --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/grill .cursor/skills/grill && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .cursor/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ntorga/agent-starter-kit.git --path skills/grill--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ntorga/agent-starter-kit --skill grill -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ntorga/agent-starter-kit grill --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/grill .gemini/skills/grill && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .gemini/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ntorga/agent-starter-kit grillInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ntorga/agent-starter-kit --skill grill -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/grill .github/skills/grill && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .github/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill grill -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ntorga/agent-starter-kit grill --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/grill .opencode/skills/grill && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "grill" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/grill into .opencode/skills/grill/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "grill", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
grill- GitHub stars
- 146
- Token cost
- ~1.3k tokens
- SKILL.md length
- 702 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Protocol that interviews the user in rounds over the Architect's design tree.
- Works in 6 steps: Select path. Check long-term memory… → Build the tree. Dispatch the Architect… → Work the frontier in rounds. The… → …
- AI & LLM Engineering work in your project
- SKILL.md covers Purpose, Procedure, Post-Grill Execution and Guardrails
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Grill is an agent skill from ntorga/agent-starter-kit. Protocol that interviews the user in rounds over the Architect's design tree. Three paths control depth. Produces plan.md, arch.md, impl.md.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.
When your agent uses it
- AI & LLM Engineering work in your project
Example prompts
- “/grill”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Select path. Check long-term memory (uses: skills/agent-memory/SKILL.md) for a recorded grill path under ## Preferences. If one exists…
- Build the tree. Dispatch the Architect (personas/architect.md) (follows: skills/dispatch/SKILL.md) in tree mode with the selected path…
- Work the frontier in rounds. The frontier is every open node in tree.md whose dependencies are all settled. Send up to 5 frontier…
- Checkpoint after each round. Transcribe the settled decisions of the round into the relevant artifact files. Create a file if it does not…
- Re-tree on scope change. If an answer does not map to a node in the tree — a new branch, a scope change — re-dispatch the Architect…
- Terminate. The grill is done when the frontier is empty. Present plan.md, arch.md, and impl.md to the user. Do not act until the user…
What it can do on your machine
Read from SKILL.md and the folder at commit 851e942. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Grill loads about 1.3k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 702 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 702 words, ~1,264 tokens.
Download SKILL.mdSave it as
.claude/skills/grill/SKILL.md (or your agent's skills folder).- name
- grill
- description
- Protocol that interviews the user in rounds over the Architect's design tree. Three paths control depth. Produces plan.md, arch.md, impl.md.
- usedBy
- maestro
- version
- 0.2.1
- lastUpdated
- 2026-09-12
Purpose
Reach shared understanding with the user before execution. The Architect owns the design tree — the decisions the feature must settle, mapped with dependencies, pruned by path, ranked by impact. You work the frontier in rounds: ask up to 5 frontier questions, wait for the user's answers, transcribe the settled decisions into the artifacts. After the user confirms, execution is autonomous. The user is bothered in rounds, not on every micro-delivery.
Procedure
The path determines which branches the tree explores. Step 1 resolves it from long-term memory, or asks the user when none is recorded:
- Beginner — business questions only. The Architect infers architecture from the maintenance, lightweight, and safe principles (KISS, single responsibility, safe boundaries —
rules/code/general.md). Ceiling: 30 business questions. - Tinkerer — business and architecture questions. Ceiling: 30 business, 10 architecture.
- Pro — business, architecture, and implementation questions. Ceiling: 100 questions per branch.
Artifacts live at .memory/plan/<feature-slug>/:
tree.md— the design tree. The Architect owns it.plan.md— acceptance criteria, from the settled business decisions.arch.md— directory structure, layer separation, reference projects. Tinkerer and pro. Beginner gets defaults.impl.md— epics grouped at one day of work, with parallelizable groups.
You transcribe plan.md, arch.md, and impl.md as decisions settle. The Architect owns tree.md and the grounded impl.md.
Select path. Check long-term memory (uses:
skills/agent-memory/SKILL.md) for a recorded grill path under## Preferences. If one exists, proceed with it — state the path in the first message to the user so they can override in one word. If the user overrides, replace the recorded entry. If none exists, ask the user to choose: beginner, tinkerer, or pro. Record the choice under## Preferencesas[grill] path: <beginner | tinkerer | pro>.Build the tree. Dispatch the Architect (
personas/architect.md) (follows:skills/dispatch/SKILL.md) in tree mode with the selected path. The Architect writestree.md.Work the frontier in rounds. The frontier is every open node in
tree.mdwhose dependencies are all settled. Send up to 5 frontier questions per round, ordered by impact. Each question carries the tree's recommendation. Wait for the user's answers before the next round.Format each round:
❓ **Q1** - **<question title>**: <question body> ➡️ <recommendation from the tree>- If the frontier exceeds 5, ask the 5 questions whose answers unblock the most downstream questions.
- A node that depends on another question open in this round belongs to a later round.
- A node that depends on a fact in
## Facts: dispatch a host exploration agent (e.g., the host's Explore tool) to find the fact. Never ask the user for a fact you can look up. Do not block the rest of the frontier on a running fact-finder. Record the found fact intree.mdwhen it lands.
Checkpoint after each round. Transcribe the settled decisions of the round into the relevant artifact files. Create a file if it does not exist. This survives context compaction and keeps the session on track.
Re-tree on scope change. If an answer does not map to a node in the tree — a new branch, a scope change — re-dispatch the Architect (
personas/architect.md) (follows:skills/dispatch/SKILL.md) in tree mode to extendtree.md. Settled nodes stay settled.Terminate. The grill is done when the frontier is empty. Present
plan.md,arch.md, andimpl.mdto the user. Do not act until the user confirms you have reached a shared understanding.
Show full SKILL.md (169 more words)Show less
Post-Grill Execution
After the user confirms, the plan-management flow takes over (follows: skills/plan-management/SKILL.md): ground, review, then the coder per epic.
Interrupt the user only for escalations:
- A fact that contradicts a settled decision.
- A business rule the grill did not cover.
The Architect classifies every discovery as adjust (folded into the remaining epics, no user gate) or escalate (user gate). Anything else, the Architect decides and documents inline.
Guardrails
- Never ask for a path that is recorded in long-term memory. State it; do not ask.
- The quality filter and the ceilings are applied by the Architect in the tree. Stop when the frontier is empty, not when you hit a ceiling.
- Send at most 5 questions per round.
- Never ask the user for a fact you can look up. Dispatch a subagent.
- Never skip the checkpoint.
- Never work a node whose dependencies are unsettled.
- Never act on the tree until the user confirms shared understanding.
- Never let a persona talk to the user directly. You are the only voice.
© ntorga, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/grill of ntorga/agent-starter-kit.
Open the folder on GitHubat commit 851e942
Compare with similar skills
Grill next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Grill this skillntorga/agent-starter-kit | 146 | — | ~1.3k | Automated safety check: Pass | MIT | |
| Agent BuildershareAI-lab/learn-claude-code | 78k | 6 repos | ~1.2k | Automated safety check: Pass | MIT | |
| Planning With Filesjarrodwatts/claude-code-config | 1.1k | 5 repos | ~967 | Automated safety check: Pass | None | |
| Codebase Managementgiancarloerra/SocratiCode | 3.3k | 1 repos | ~1.8k | Automated safety check: Pass | AGPL-3.0 | |
| Context Compressionguanyang/open-agent-hub | 973 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Looperksimback/looper | 710 | — | ~2.7k | Automated safety check: Notes | MIT |
Similar skills
Planning With Files
jarrodwatts/claude-code-config
Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage.
Codebase Management
giancarloerra/SocratiCode
Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.
Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
Looper
ksimback/looper
Scaffold a well-designed agent loop with best-practice coaching and a cross-model review council.
Docs Planner
strands-agents/harness-sdk
Identify documentation gaps and prioritize the docs backlog.
More from ntorga/agent-starter-kit
All 21 skills in this repoAgent Decision
ntorga/agent-starter-kit
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
Agent Memory
ntorga/agent-starter-kit
Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.
Architect Design Tree
ntorga/agent-starter-kit
Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.
Architect Impl Grounding
ntorga/agent-starter-kit
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
Boot
ntorga/agent-starter-kit
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Browser Inspect
ntorga/agent-starter-kit
Browser inspection and interaction for verifying rendered web UI during development.
Related
Categories
Questions about Grill
What does Grill do?
Protocol that interviews the user in rounds over the Architect's design tree. Grill is an agent skill from ntorga/agent-starter-kit. Protocol that interviews the user in rounds over the Architect's design tree.
When should I use Grill?
Grill fits situations like: AI & LLM Engineering work in your project.
How do I install Grill in Claude Code?
Run `npx skills add ntorga/agent-starter-kit --skill grill -a claude-code`. Or copy the skill folder (skills/grill in ntorga/agent-starter-kit) into .claude/skills/grill in your project. Claude Code loads it when a task matches its description.
How do I install Grill in Codex?
Run `npx skills add ntorga/agent-starter-kit --skill grill -a codex`. Or copy the skill folder (skills/grill in ntorga/agent-starter-kit) into .agents/skills/grill in your project. Codex loads it when a task matches its description.
Can I use Grill in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ntorga/agent-starter-kit --skill grill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/grill, .gemini/skills/grill, .github/skills/grill and .opencode/skills/grill in your project.
What does Grill need to run?
SKILL.md names no scripts, command-line tools or credentials: Grill is instructions for the agent only.
Does Grill access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Grill safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Grill use?
Grill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Grill use?
About 1.3k tokens (SKILL.md is roughly 5.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Grill?
Skills that share tags, products or a category with Grill: Agent Builder (shareAI-lab/learn-claude-code, 78k stars), Planning With Files (jarrodwatts/claude-code-config, 1.1k stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars) and Context Compression (guanyang/open-agent-hub, 973 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Grill?
ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.
Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.