Agent skill

Boot

by ntorga in ntorga/agent-starter-kit

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

MITAuto-check passedAI & LLM Engineering

Install Boot

skills CLI
$ npx skills add ntorga/agent-starter-kit --skill boot -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ntorga/agent-starter-kit boot --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/boot .claude/skills/boot && rm -rf skills-src

Use ~/.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/

Facts

Skill name
boot
GitHub stars
146
Token cost
~937 tokens
SKILL.md length
430 words
Files
1
Skills in repo
21
Repo updated
First seen
Licence
MIT

At a glance

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

  • Works in 8 steps: Gitignore. Ensure .agents/, .memory/,… → Framework pull. Run → Memory. Load memory (uses:… → …
  • AI & LLM Engineering work in your project
  • SKILL.md covers Purpose, Path Convention, Procedure and Guardrails
  • Calls git and bash

What it does

Boot is an agent skill from ntorga/agent-starter-kit. Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

Its SKILL.md is about 940 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

  • “/boot”

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. Gitignore. Ensure .agents/, .memory/, and opencode.json are in the project's .gitignore. Run
  2. Framework pull. Run
  3. Memory. Load memory (uses: skills/agent-memory/SKILL.md).
  4. Core skills. Read the following core skills IN FULL now. These are mandatory for every dispatch and planning decision. Do not skip…
  5. CLI configuration. Run
  6. Load the rules index. Read rules/README.md to know what rules are available and their scopes. Do not read the individual rule files…
  7. Context. Verify the project has context files. Run
  8. Greet. Greet the user and wait for instructions. Remind the user: they are not talking to a single agent — they are talking to a team of…

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

    Shell commands in SKILL.md call:

    • git
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    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

Boot loads about 937 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 430 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~937

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). 430 words, ~937 tokens.

Download SKILL.mdSave it as .claude/skills/boot/SKILL.md (or your agent's skills folder).
name
boot
description
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
usedBy
maestro
version
0.5.0
lastUpdated
2026-09-12

Purpose

Every session starts cold. The Maestro needs to ensure the project is wired correctly, the framework is up to date, load the project's rules, and understand the codebase before it can dispatch work effectively. This skill defines the boot sequence that brings the Maestro from zero to ready.

Path Convention

All framework files live under .agents/. Markdown references within the framework use bare paths for readability — always resolve them under .agents/. Shell commands always use the .agents/ prefix for project-root paths.

Procedure

  1. Gitignore. Ensure .agents/, .memory/, and opencode.json are in the project's .gitignore. Run:

    bash
    touch .gitignore
    for entry in '.agents/' '.memory/' 'opencode.json' '.ignore'; do
        grep -qxF "$entry" .gitignore || echo "$entry" >> .gitignore
    done
  2. Framework pull. Run:

    bash
    git -C .agents pull
    • If the pull brought changes:
      • Read the CHANGELOG.md in .agents to understand what changed.
      • Purge obsolete long-term memory entries — read .memory/long-term.md, read the changelog, and for each memory entry remove it only if the changelog describes a feature, skill, or rule that replaces that memory's purpose. If the entry's purpose is not clearly covered by the changelog, keep it.
      • Re-read personas/maestro.md from the top so updated instructions take effect.
    • If already up to date, continue.
  3. Memory. Load memory (uses: skills/agent-memory/SKILL.md).

  4. Core skills. Read the following core skills IN FULL now. These are mandatory for every dispatch and planning decision. Do not skip, summarize, or rely on memory:

    • skills/dispatch/SKILL.md — required for every sub-agent dispatch
    • skills/plan-management/SKILL.md — required for planning decisions and epic tracking
  5. CLI configuration. Run:

    bash
    bash .agents/skills/assets/maestro-boot-configure-cli.sh
    • If the script reports the config was created or updated, inform the user that agent bindings changed and they should restart the session for the new bindings to take effect.
    • If the script reports unchanged, no action is needed.
    • If yq or jq is not installed, the script prints a skip message — no action needed.
    • If no supported CLI config file is found, the script exits silently — no action needed.
  6. Load the rules index. Read rules/README.md to know what rules are available and their scopes. Do not read the individual rule files — sub-agents will read them when dispatched.

  7. Context. Verify the project has context files. Run:

    bash
    find . -name ".context.md" -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/vendor/*" -not -path "*/.cache/*" -print -quit
    • If find produces no output, no .context.md files exist. Dispatch the Contextualizer (uses: personas/contextualizer.md) before proceeding.
    • Also check docs/FEATURE-MAP.md — if it is missing, the Contextualizer dispatch covers it (uses: skills/context-maintenance/SKILL.md).
  8. Greet. Greet the user and wait for instructions. Remind the user: they are not talking to a single agent — they are talking to a team of specialists that can handle multiple requests simultaneously, so large and complex prompts are welcome.

Show full SKILL.md (24 more words)Show less

Guardrails

  • Never skip rule loading. Dispatching without rules means dispatching without constraints.
  • Never skip the framework pull. An outdated .agents directory means outdated instructions.

© 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/boot of ntorga/agent-starter-kit.

Open the folder on GitHubat commit 851e942

Compare with similar skills

Boot 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.

Boot compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Boot this skillntorga/agent-starter-kit146—~937Automated safety check: PassMIT
Git Guardrails Claude Codefossasia/eventyay-interpretation1.6k12 repos~578Automated safety check: PassApache-2.0
Codebase Managementgiancarloerra/SocratiCode3.3k1 repos~1.8kAutomated safety check: PassAGPL-3.0
Azure AI Projects Python SDKmicrosoft/skills3.1k6 repos~2.8kAutomated safety check: PassMIT
AI Research Reproductionlllllllama/RigorPilot-Skills4971 repos~1.8kAutomated safety check: PassMIT
Onnxtxtonnx/onnx22k—~1.3kAutomated safety check: PassApache-2.0

Similar skills

  • Git Guardrails Claude Code

    fossasia/eventyay-interpretation

    Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute.

    1.6k GitHub starsUsed in 12 repos~578 tokens
    AI & LLM EngineeringAuto-check passed
  • Codebase Management

    giancarloerra/SocratiCode

    Set up, index, and manage SocratiCode codebase indexing. An agent skill from giancarloerra/SocratiCode.

    3.3k GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed
  • Official

    Reference for building on Microsoft Foundry with the azure-ai-projects Python SDK: project clients, versioned agents, evaluations, connections, datasets and indexes.

    3.1k GitHub starsUsed in 6 repos~2.8k tokens
    AI & LLM EngineeringAuto-check passed
  • AI Research Reproduction

    lllllllama/RigorPilot-Skills

    Rigor Reproduce compatible skill slug for README-first deep learning repository reproduction.

    497 GitHub starsUsed in 1 repo~1.8k tokens
    AI & LLM EngineeringAuto-check passed
  • Onnxtxt

    onnx/onnx

    Read or write ONNX text format ("onnxtxt"). An agent skill from onnx/onnx.

    22k GitHub stars~1.3k tokensUpdated today
    AI & LLM EngineeringAuto-check passed
  • Docs Planner

    strands-agents/harness-sdk

    Identify documentation gaps and prioritize the docs backlog.

    8.7k GitHub stars~821 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

More from ntorga/agent-starter-kit

All 21 skills in this repo
  • Agent Decision

    ntorga/agent-starter-kit

    Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.

    146 GitHub stars~1.7k tokensUpdated 25 days ago
    Auto-check passed
  • Agent Memory

    ntorga/agent-starter-kit

    Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.

    146 GitHub stars~2.7k tokensUpdated 25 days ago
    Auto-check passed
  • 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.

    146 GitHub stars~1.2k tokensUpdated 25 days ago
    Auto-check passed
  • 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.

    146 GitHub stars~944 tokensUpdated 25 days ago
    Auto-check passed
  • Browser Inspect

    ntorga/agent-starter-kit

    Browser inspection and interaction for verifying rendered web UI during development.

    146 GitHub stars~2k tokensUpdated 25 days ago
    Auto-check passed
  • Code Coherence Review

    ntorga/agent-starter-kit

    Reviews code and plans for logic coherence, correctness, and structural integrity.

    146 GitHub stars~2.8k tokensUpdated 25 days ago
    Auto-check passed

Questions about Boot

What does Boot do?

Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet. Boot is an agent skill from ntorga/agent-starter-kit. Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.

When should I use Boot?

Boot fits situations like: AI & LLM Engineering work in your project.

How do I install Boot in Claude Code?

Run `npx skills add ntorga/agent-starter-kit --skill boot -a claude-code`. Or copy the skill folder (skills/boot in ntorga/agent-starter-kit) into .claude/skills/boot in your project. Claude Code loads it when a task matches its description.

How do I install Boot in Codex?

Run `npx skills add ntorga/agent-starter-kit --skill boot -a codex`. Or copy the skill folder (skills/boot in ntorga/agent-starter-kit) into .agents/skills/boot in your project. Codex loads it when a task matches its description.

Can I use Boot 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 boot -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/boot, .gemini/skills/boot, .github/skills/boot and .opencode/skills/boot in your project.

What does Boot need to run?

Going by SKILL.md and its folder, Boot needs the command-line tools its instructions call (git and bash).

Does Boot access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Boot 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 Boot use?

Boot 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 Boot use?

About 937 tokens (SKILL.md is roughly 3.7k 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 Boot?

Skills that share tags, products or a category with Boot: Git Guardrails Claude Code (fossasia/eventyay-interpretation, 1.6k stars), Codebase Management (giancarloerra/SocratiCode, 3.3k stars), Azure AI Projects Python SDK (microsoft/skills, 3.1k stars) and AI Research Reproduction (lllllllama/RigorPilot-Skills, 497 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Boot?

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.