A setup workflow for adding a standard .claude directory and project guidance to a codebase or knowledge project.

Use it to inspect a new project, identify its technology and commands, and create files such as CLAUDE.md, CODEBASE.md, documentation, knowledge notes, and optional skills.

It helps an AI assistant understand a project's structure, conventions, tools, and working rules before making changes.

bootstrap — Skill by mp-web3

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/mp-web3/claude-starter-kit/bootstrap

Any agent

npx skills add mp-web3/claude-starter-kit --skill bootstrap

Clone the repo

git clone --depth 1 https://github.com/mp-web3/claude-starter-kit

Made for: Claude Code, Codex.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,821 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.

Model	Per session	Once invoked
Fable 5	$0.00082	$0.01821
Opus 5	$0.00041	$0.00911
Sonnet 5	$0.00016	$0.00364
Haiku 4.5	$0.00008	$0.00182

Measured 2d ago against content hash f1789eeedf6f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 2d 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/bootstrap/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bootstrap — Set Up a Project for Claude Code

First: Read LEARNINGS.md in this skill's directory.

Arguments: $ARGUMENTS

If no project path given, use the current working directory. If --type not specified, infer from context (has src/, package.json, Cargo.toml -> code; otherwise -> knowledge).

Step 1: Reconnaissance

Before creating anything, understand what exists.

Read the project's existing README, package.json/Cargo.toml/pyproject.toml, or equivalent
ls the top-level directory structure
Check if .claude/ already exists — if so, audit what's there and fill gaps instead of overwriting
Identify:
- Tech stack (languages, frameworks, package manager)
- Build/lint/test commands (from package.json scripts, Makefile, etc.)
- Major modules (top-level dirs that represent distinct concerns)
- Project type: code (has source code, build system) or knowledge (notes, docs, automation)

Present findings to the user in a table. Confirm before proceeding.

Step 2: Create Directory Structure

.claude/
  CLAUDE.md              # Behavioral core (always created)
  CODEBASE.md            # Project overview + module index (code projects only)
  docs/                  # Module documentation (code projects only)
    <module>.md          # One per major module
  knowledge/             # On-demand context
    <framework>.md       # Language/framework conventions
  settings.local.json    # Project-scoped settings (if hooks needed)

For knowledge projects, skip CODEBASE.md and docs/. Add instead:

.claude/
  rules/                 # Domain rules (always loaded)
  knowledge/sessions/    # Session logs

Create the directories. Do NOT create empty placeholder files.

Step 3: Write CLAUDE.md

Target: 30-40 lines max. This burns context tokens every session.

Structure — adapt sections to the project:

# <Project Name>

## Commands
- `<build command>` -- build the project
- `<test command>` -- run tests
- `<lint command>` -- lint/typecheck

## Process
- Before starting, read `.claude/CODEBASE.md` and relevant `.claude/docs/` files
- Do NOT use the Explore agent by default -- read documentation first
- After code changes, update documentation if interfaces or behavior changed
- When fetching context, state which documents you loaded

## Available Documentation
- `.claude/CODEBASE.md` -- project overview and module index
- `.claude/docs/<module>.md` -- <one-line description>

## Available Knowledge
- `.claude/knowledge/<topic>.md` -- <one-line description>

Read the full file on GitHub · 192 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

LEARNINGS.md 808 B

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.

2d ago First seen · 192 lines · 82 tokens per session scan A f1789eeedf6f

Subscribe to this mod's changes

bootstrap is a skill published in the GitHub repository mp-web3/claude-starter-kit (106 stars, last pushed 5mo ago), licensed MIT. It adds 82 tokens to every session and 1,821 once invoked, about $0.0004 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 2026-08-30.

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens