project-bootstrap

project-bootstrap is a skill for Claude Code from iot-forge/m5stack-skills. It costs 126 tokens per session (449 once invoked), scanned A, original, MIT.

A project generator for starting M5Stack Core2 firmware projects with Arduino or PlatformIO. It creates the standard project skeleton instead of requiring the configuration and starter source files to be written by hand.

In plain words
What is it for?
Use it when beginning a Core2 project to create the selected framework's project files, sketch or main source, and recommended M5Unified skeleton.
Why use it?
It removes repetitive setup work and avoids accidentally replacing existing files without asking first.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the core plugin — 3 skills shipped together

Good fit Use it when beginning a Core2 project to create the selected framework's project files, sketch or main source, and recommended M5Unified skeleton.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add iot-forge/m5stack-skills
Claude Code
/plugin install core

Made for: Claude Code.

Or install core, the plugin that ships this one along with the rest of its 3 skills.

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 project-bootstrap

README.md
[![agentmods](https://agentmods.dev/badge/skills/iot-forge/m5stack-skills/project-bootstrap/github.svg)](https://agentmods.dev/skills/iot-forge/m5stack-skills/project-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/iot-forge/m5stack-skills/project-bootstrap"><img src="https://agentmods.dev/badge/skills/iot-forge/m5stack-skills/project-bootstrap/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for project-bootstrap

Your own site · 80×15
<a href="https://agentmods.dev/skills/iot-forge/m5stack-skills/project-bootstrap"><img src="https://agentmods.dev/badge/skills/iot-forge/m5stack-skills/project-bootstrap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 449 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 $0.00126 $0.00449
Opus 5.5 $0.00050 $0.00180
Sonnet 5.5 $0.00025 $0.00090
Haiku 4.5 $0.00013 $0.00045

Measured 6d ago against content hash 0b2fd82ff21d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

project-bootstrap 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.

plugins/core/skills/project-bootstrap/SKILL.md · 40 lines

What it actually says

Core2 project bootstrap

When the user is starting a new Core2 firmware project and has already picked Arduino or PlatformIO as the framework, run the bundled generator instead of writing platformio.ini or the sketch/main.cpp skeleton by hand — the boilerplate never changes, so there is no reason to regenerate it token by token.

Ask the user for a project/sketch name if they haven't given one (default core2_project if they don't care). Then, in the user's project directory, run:

"${CLAUDE_PLUGIN_ROOT}"/scripts/bootstrap.py --board core2 --framework arduino --name <project_name>

or, for PlatformIO:

"${CLAUDE_PLUGIN_ROOT}"/scripts/bootstrap.py --board core2 --framework platformio --name <project_name>

Pass --framework platformio --name "" to scaffold platformio.ini and src/main.cpp straight into the current directory instead of a named subfolder.

Report the files the script printed as created. If it exits non-zero because a file already exists, tell the user and ask whether to pass --force to overwrite, rather than writing the file yourself.

This generates the recommended M5Unified skeleton only. For the legacy M5Core2 library skeleton, ESP-IDF, UIFlow, or anything past the initial scaffold (pinouts, power management, audio, etc.), use the core2 skill's own reference material instead.

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 · 40 lines · 126 tokens per session scan A 0b2fd82ff21d

Subscribe to this mod's changes

project-bootstrap is a skill published in the GitHub repository iot-forge/m5stack-skills (5 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 449 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-11.