project-bootstrap

project-bootstrap is a skill for Claude Code from jerseycheese/agent-skills. It costs 145 tokens per session (1,301 once invoked), scanned A, original, MIT.

A project setup workflow that adds standard files and instructions to a new project under the Projects folder. The setup can include guidance for agents, editor and Git settings, launch commands, and stack-specific files.

In plain words
What is it for?
Use it when starting a project or adding the standard development and coding-agent scaffolding to an existing repository.
Why use it?
It gives a new repository consistent instructions for running, testing, and protecting the project. This reduces setup work and prevents agents from having to rediscover basic project details.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions AGENTS.md.

Part of the workflow-skills plugin — 31 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/jerseycheese/agent-skills/project-bootstrap
Any agent
npx skills add jerseycheese/agent-skills --skill project-bootstrap
Clone the repo
git clone --depth 1 https://github.com/jerseycheese/agent-skills

Made for: Claude Code.

Or install workflow-skills, the plugin that ships this one along with the rest of its 31 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/jerseycheese/agent-skills/project-bootstrap.svg)](https://agentmods.dev/skills/jerseycheese/agent-skills/project-bootstrap)
Your own site
<a href="https://agentmods.dev/skills/jerseycheese/agent-skills/project-bootstrap"><img src="https://agentmods.dev/badge/skills/jerseycheese/agent-skills/project-bootstrap.svg" alt="Measured on agentmods" height="20"></a>
Per session 145 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,301 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00145 $0.01301
Opus 5 $0.00072 $0.00651
Sonnet 5 $0.00029 $0.00260
Haiku 4.5 $0.00015 $0.00130

Measured 5d ago against content hash 7280ec46177d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, 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 5d 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.

skills/project-bootstrap/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Bootstrap

Purpose

Every repo should hand an agent the same things up front: what it is, how to run it, how to test it, and what not to break. This skill stamps that scaffolding from one source of truth - the starter kit - so cold sessions (and cheaper models) execute instead of rediscovering. The CLAUDE.md is the deliverable; it gets smoke-tested before it counts.

The starter kit (single source of truth)

All scaffolding lives at ~/Projects/shared/Development/templates/starter-kit/. Never re-author these files inline - copy them from the kit and fill the placeholders.

  • core/ - stamped into every project, any stack:
    • CLAUDE.md.template, README.md.template - filled with judgment from recon
    • .editorconfig, .gitignore - copied verbatim
    • .claude/settings.json - copied verbatim (committed canon: minimal safe permissions)
    • .claude/settings.local.json.template - copied to settings.local.json, adjusted to stack; only if absent
    • .claude/launch.json.template - filled with dev command + port
    • scripts/worktree-port.cjs - copied verbatim (stable per-worktree dev port)
  • layers/<stack>/ - opt-in, applied over the core; each has its own README with steps:
    • frontend-vite - React + Vite + TS + current Storybook + design-token enforcement (ready)
    • js-ts, python, static-11ty - planned; skip if the directory isn't there yet

Inputs

Ask only for what can't be discovered: the project's name and one-line purpose if there's no README. Everything else comes from recon.

Process

  1. Recon the repo (skip whatever doesn't exist):
    • package.json / pyproject.toml / composer.json - scripts and deps (these also tell you the stack -> which layer, if any)
    • Server entry: grep for PORT|listen; check .env.example for required vars
    • Existing docs (README, AGENTS.md, docs/) - the CLAUDE.md points at them, never duplicates
    • git log --oneline -15 - recent themes become "Common tasks" candidates
    • git worktree list - decides whether the worktrees section applies

Read the full file on GitHub · 65 lines

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. 5d ago First seen · 65 lines · 145 tokens per session scan A 7280ec46177d

Subscribe to this mod's changes

project-bootstrap is a skill published in the GitHub repository jerseycheese/agent-skills (1 stars, last pushed 4d ago), licensed MIT. It adds 145 tokens to every session and 1,301 once invoked, about $0.0007 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

env-scanner

Scan and audit Gemini CLI, Claude Code, Antigravity, Continue, Windsurf, JetBrains AI, and OpenCode environments. Discovers configurations, audits memory tiers, detects skill extraction state, analyzes behavioral tool chains, checks policy governance (v0.40+), and suggests reusable skills with evidence gating.…

pauldatta/gemini-cli-scanner · 101 tokens

scan

Scan your AI coding tool ecosystem — Gemini CLI, Claude Code, Antigravity (Desktop, CLI, IDE), Continue, Windsurf, JetBrains AI, OpenCode. Produces a maturity score, advisory recommendations, and optionally generates reusable SKILL.md files from your conversation patterns. Use when the user asks to audit their…

pauldatta/gemini-cli-scanner · 82 tokens

local-places

Search for places (restaurants, cafes, etc.) via Google Places API proxy on localhost.

geezerrrr/motive · 22 tokens

chorus-council

Run an LLM council — Claude (correctness), Gemini (edge cases), Cursor (integration), Kilo (maintainability), and you (scope) tackle the same task in parallel. Use when the user wants multiple independent perspectives on a decision, approach, or problem.

valpere/chorus · 62 tokens

chorus-vote

Put a yes/no proposition to five agents and tally YES / NO / ABSTAIN votes when the user wants a quick decision signal.

valpere/chorus · 32 tokens

chorus-parallel-debug

Parallel root-cause hypotheses from multiple agents for a reported bug. Use when the user says "parallel debug", "chorus debug", "multiple hypotheses", or "debug with all agents".

valpere/chorus · 44 tokens