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.
git clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/plugins/ozzeron/prompt-pack/fullstack)<a href="https://agentmods.dev/plugins/ozzeron/prompt-pack/fullstack"><img src="https://agentmods.dev/badge/plugins/ozzeron/prompt-pack/fullstack/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.
<a href="https://agentmods.dev/plugins/ozzeron/prompt-pack/fullstack"><img src="https://agentmods.dev/badge/plugins/ozzeron/prompt-pack/fullstack.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
fullstack 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 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.
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.
What it actually says
{
"name": "fullstack",
"displayName": "Prompt Pack — Fullstack",
"description": "Frontend plus backend plus every review skill: architecture, UI, database, security, duplication audit, refactor planning, docs. task-router is excluded — Claude Code's native skill discovery does the routing.",
"source": "./",
"skills": [
"./prompts/meta/engineering-principles",
"./prompts/meta/reuse-before-create",
"./prompts/meta/token-discipline",
"./prompts/architecture/backend-api",
"./prompts/architecture/frontend-feature",
"./prompts/architecture/database-schema",
"./prompts/architecture/database-migrations",
"./prompts/architecture/postgres-supabase",
"./prompts/architecture/refactor-planner",
"./prompts/interface/ui-designer",
"./prompts/review/code-review",
"./prompts/review/repo-audit",
"./prompts/review/frontend-audit",
"./prompts/review/database-review",
"./prompts/review/security-review",
"./prompts/review/duplication-audit",
"./prompts/review/debugger",
"./prompts/delivery/handoff",
"./prompts/delivery/test-writer",
"./prompts/delivery/doc-writer"
],
"keywords": [
"fullstack",
"frontend",
"backend",
"review"
]
}What it installs
The manifest is a name and a version. 20 skills travel with it, and installing the plugin installs all of them — 1,831 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill duplication-audit A 90 tokens
- Skill frontend-feature A 100 tokens
- Skill repo-audit A 100 tokens
- Skill reuse-before-create A 89 tokens
- Skill security-review A 86 tokens
- Skill ui-designer A 94 tokens
- Skill code-review A 91 tokens
- Skill database-migrations A 97 tokens
- Skill database-schema A 92 tokens
- Skill debugger A 87 tokens
- Skill postgres-supabase A 92 tokens
- Skill refactor-planner A 95 tokens
- Skill test-writer A 95 tokens
- Skill database-review A 91 tokens
- Skill backend-api A 89 tokens
- Skill handoff A 91 tokens
- Skill doc-writer A 96 tokens
- Skill engineering-principles A 77 tokens
- Skill frontend-audit A 92 tokens
- Skill token-discipline A 87 tokens
What ships with it
1 file beside marketplace.json#fullstack 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.
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.
- 1mo ago First seen · 34 lines scan A 5f2e56d4cf56
fullstack is a plugin published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.
Other plugins, from other repositories
website-extraction
Extract structured data from public website pages using Iteration Layer.
distributed-debugging
Distributed system tracing and debugging across microservices.
project-brain
Folder structure + collaboration protocol so AI sessions can resume project context after compaction or window switch. One brain/ folder, 5 core files (PROJECT/MAP/STATUS/DECISIONS/HANDOFF), and a topic taxonomy.
tray-api
Plugin completo para integração com as APIs da Tray. Acelera o desenvolvimento de aplicativos e-commerce por parceiros e comunidade na plataforma Tray, fornecendo documentação detalhada de todos os endpoints, fluxos de autenticação OAuth, webhooks e boas práticas de integração.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.