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.
npx skills add paulo-yamagishi/claude-code-setup --skill bootstrapgit clone --depth 1 https://github.com/paulo-yamagishi/claude-code-setupWrote 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.
[](https://agentmods.dev/skills/paulo-yamagishi/claude-code-setup/bootstrap)<a href="https://agentmods.dev/skills/paulo-yamagishi/claude-code-setup/bootstrap"><img src="https://agentmods.dev/badge/skills/paulo-yamagishi/claude-code-setup/bootstrap.svg" alt="Measured on agentmods" height="20"></a>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 5.1 | $0.00029 | $0.03487 |
| Opus 5 | $0.00015 | $0.01743 |
| Sonnet 5 | $0.00006 | $0.00697 |
| Haiku 4.5 | $0.00003 | $0.00349 |
Grade C, and why
bootstrap scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"Bash(rm -rf *)", How it starts
The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap — Auto-Configure Claude Code for Your Project
Work through each phase sequentially, asking the user for input only where marked.
Phase 0: Check for Setup Report
Before running detection, check if a /setup audit report exists earlier in this conversation. Look for a fenced code block with the setup-report language tag.
If found:
- Parse the stack, tools, category statuses, and suggestions
- Tell the user: "Found your /setup audit — focusing on the gaps it identified."
- Still run Phase 1 detection as normal, but use the setup report to enhance subsequent phases:
- Prioritize categories marked IMPROVE or MISSING — generate config for these first
- Skip prompting for categories marked GOOD — they're already configured
- Use setup's suggestions as a checklist — ensure each one is addressed in the generated config
- In Phase 8 summary, note which setup suggestions were applied
If not found:
- Proceed normally — this is the default path for standalone
/bootstrapusage
Phase 1: Detect Project Stack
1.1 Read Project Metadata
Check for these files (in priority order):
package.json(Node.js/JavaScript/TypeScript)pyproject.tomlorsetup.py(Python)Cargo.toml(Rust)go.mod(Go)pom.xmlorbuild.gradle(Java/JVM)Gemfile(Ruby)composer.json(PHP)
1.2 Detect Tools
Package managers:
- Check for lockfiles:
package-lock.json(npm),yarn.lock,pnpm-lock.yaml,bun.lockb,poetry.lock,Cargo.lock,go.sum, etc.
Formatters:
.prettierrc,.prettierrc.json,prettier.config.js→ Prettierpyproject.tomlwith[tool.black]→ Black.rustfmt.toml→ rustfmt.gofmtor standard Go project → gofmt.php-cs-fixer.php→ PHP CS Fixerbiome.json,biome.jsonc→ Biome (format:biome format --write)
Linters:
.eslintrc*→ ESLinteslint.config.*→ ESLint (flat config)biome.json,biome.jsonc→ Biome (lint:biome check)pyproject.tomlwith[tool.ruff]or.ruff.toml→ Ruffpylint.rc→ Pylintclippy.toml→ Clippy.golangci.yml→ golangci-lint
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.
- 6d ago First seen · 381 lines · 29 tokens per session scan C 48365e9fc166
bootstrap is a skill published in the GitHub repository paulo-yamagishi/claude-code-setup (2 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 3,487 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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.
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…