agentmods.dev

launch-security

launch-security is a skill for Claude Code from Magerko/claude-code-skills. It costs 105 tokens per session (1,303 once invoked), scanned A, original, MIT.

A pre-release security check for an application. It reviews common risks such as exposed secrets, login sessions, unauthorised data access, injection attacks, file uploads, dependencies, webhooks and payments, then writes a prioritised report.

In plain words
What is it for?
Use it to review an application before launch, check specific security controls, and produce a report showing what needs attention first. Active tests require permission and should be run only against your own environment.
Why use it?
It helps find security problems before the application goes live, without creating false confidence that the application is fully secure. It reports findings but does not change project files.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the NotebookEdit tool.

not rated 27repo 2mo ago A scan 105 tokens original MIT

Good fit Use it to review an application before launch, check specific security controls, and produce a report showing what needs attention first. Active tests require permission and should be run only against your own environment.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/magerko/claude-code-skills/launch-security
View source ↗ Magerko/claude-code-skills
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.

Any agent
npx skills add Magerko/claude-code-skills --skill launch-security
Clone the repo
git clone --depth 1 https://github.com/Magerko/claude-code-skills

Made for: Claude Code.

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 launch-security

README.md
[![agentmods](https://agentmods.dev/badge/skills/magerko/claude-code-skills/launch-security/github.svg)](https://agentmods.dev/skills/magerko/claude-code-skills/launch-security)
Your own site
<a href="https://agentmods.dev/skills/magerko/claude-code-skills/launch-security"><img src="https://agentmods.dev/badge/skills/magerko/claude-code-skills/launch-security/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 launch-security

Your own site · 80×15
<a href="https://agentmods.dev/skills/magerko/claude-code-skills/launch-security"><img src="https://agentmods.dev/badge/skills/magerko/claude-code-skills/launch-security.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,303 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00105 $0.01303
Opus 5.5 $0.00042 $0.00521
Sonnet 5.5 $0.00021 $0.00261
Haiku 4.5 $0.00011 $0.00130

Measured 1mo ago against content hash 05d28bd7b2fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

launch-security scanned grade A 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

allowed-tools: Read, Glob, Grep, Write, AskUserQuestion, Bash(git *), Bash(ls *), Bash(date *), Bash(curl *), Bash(npm ls *), Bash(pip list *)
skills/launch-security/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Launch check: безопасность

Сегодня: !date +%F

Аудит перед выкаткой в прод. Ты находишь и докладываешь. Правки — отдельным запросом пользователя после отчёта.

Границы (нарушать нельзя)

  • Только проект пользователя. Ты не сканируешь и не проверяешь чужие сайты, чужие аккаунты и продакшены, которые тебе не принадлежат.
  • Активные проверки — с явного разрешения и только на своём стенде. Подстановка чужого id, попытка чтения через анонимный ключ, проверка rate limit — это нагрузка и запись в логи. Спроси, прежде чем делать, и предпочитай локальное окружение проду.
  • Не эксплуатируй найденное дальше подтверждения. Убедился, что доступ есть, — остановись. Дамп чужих данных «для доказательства» не нужен.
  • Секреты в отчёт не копируются. Пиши файл:строка и маску: sk-live-…a91f (первые 8 и последние 4 символа). Полное значение — никогда, отчёт попадёт в git.
  • Не редактируешь файлы проекта. Единственный файл, который ты пишешь, — отчёт.

Главная оговорка, которую пишешь в отчёт

Чек-лист не заменяет аудит и пентест. Зелёные галочки означают «эти конкретные проверки прошли», а не «приложение безопасно». Ложная уверенность здесь опаснее, чем её отсутствие. Эта фраза идёт в шапку отчёта всегда.

Статусы

Значение
✅ проверено фактом, реализовано верно
⚠️ реализовано частично или неправильно
❌ отсутствует
н/п неприменимо к этому стеку — с объяснением, почему
🙋 требует действия человека (ротация ключа, доступ к консоли провайдера, решение)
⏭ не проверено, и написано почему

Приоритеты: P1 — не выкатываем. P2 — чинится до роста нагрузки/аудитории. P3 — гигиена.

Порядок работы

  1. Определи стек первым делом. Читай package.json, requirements.txt, go.mod, конфиги хостинга, миграции. Ищи: Supabase / Firebase / Next.js / Express / Django / Rails / Laravel, где живёт БД, есть ли серверная часть вообще. Без этого не начинай — половина пунктов стеко-зависима, и совет про RLS в проекте без Postgres обесценивает весь отчёт. Детали по стекам — references/stack-notes.md.
  2. Прочитай references/checklist.md — нужные секции. Там у каждого пункта конкретная проверка и ловушка.
  3. Проверяй по коду: Grep по паттернам из чек-листа, чтение обработчиков, роутов, политик доступа. Активные проверки — по правилам выше.
  4. Найден живой секрет — прерви обход и скажи немедленно. Это единственный случай, когда ты не ждёшь конца аудита. Порядок действий для пользователя: сначала отозвать и перевыпустить ключ, потом чистить историю. Обратный порядок бесполезен.
  5. Запиши отчёт в docs/launch/security-<дата>.md. Формат — в references/report-template.md.
  6. Покажи сжатую сводку: счётчик, все P1, все 🙋. Остальное — числом.

Read the full file on GitHub · 77 lines

Files

What ships with it

3 files 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.

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. 1mo ago First seen · 77 lines · 105 tokens per session scan A 05d28bd7b2fc

Subscribe to this mod's changes

launch-security is a skill published in the GitHub repository Magerko/claude-code-skills (27 stars, last pushed 2mo ago), licensed MIT. It adds 105 tokens to every session and 1,303 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude CodeSecurityai-agentschecklistclaudepre-launchsecurity-checklist
Related

Other skills, from other repositories

improve-rule

Use when reviewing or improving a Front-End Checklist rule MDX file to raise its quality score, fix stub prompts, add missing fields, or enrich content with real code examples.

thedaviddias/Front-End-Checklist · 39 tokens

find-npm-packages

Use when you need to find the 2-3 most popular and well-maintained npm packages relevant to a frontend checklist rule, validate they meet quality thresholds, and add them to the rule's frontmatter.

thedaviddias/Front-End-Checklist · 48 tokens

content-dates

Use when auditing article or blog pages for date markup, generating Article JSON-LD with datePublished/dateModified, or checking whether a CMS template surfaces dates correctly.

thedaviddias/Front-End-Checklist · 36 tokens

faq

Use when adding FAQ sections to landing pages or blog posts, generating FAQPage JSON-LD from existing Q&A content, or validating that structured data on pages with FAQ sections is syntactically and semantically correct.

thedaviddias/Front-End-Checklist · 45 tokens

favicon

Use when checking whether a site has a correctly configured favicon, auditing tags in the , or setting up favicon infrastructure for a new project.

thedaviddias/Front-End-Checklist · 39 tokens

freshness

Use when auditing content pages for freshness signals, setting up HTTP Last-Modified headers in a web server config, or ensuring Article JSON-LD dateModified is updated when CMS content changes.

thedaviddias/Front-End-Checklist · 40 tokens