agent-dev-kit

A repeatable setup for developing AI agents, combining a selected set of development skills with a bootstrap for related external tools. Its included skills are dependency-free and aimed at everyday development work.

In plain words
What is it for?
Use it to start or standardize an agent-development environment and provide common development skills to the agent.
Why use it?
It reduces the effort of assembling the same agent-development tools and skills for each project. The setup also keeps those parts organized as one system.

Plugin for Claude Code

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.

Claude Code
/plugin marketplace add LFTPadilla/agent-dev-kit
agentmods
npx agentmods add plugins/lftpadilla/agent-dev-kit/marketplace
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-dev-kit 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 yesterday.

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.

.claude-plugin/marketplace.json · 18 lines

What it actually says

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "agent-dev-kit",
  "description": "A replicable agent development system: curated skills, plus a bootstrap for the external tools (GSD, caveman, ponytail) that complete the stack.",
  "owner": {
    "name": "Felipe Tejada",
    "url": "https://github.com/LFTPadilla"
  },
  "plugins": [
    {
      "name": "dev-skills",
      "description": "Curated, dependency-free agent skills for everyday development work.",
      "source": "./plugins/dev-skills",
      "category": "productivity"
    }
  ]
}
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. yesterday First seen · 18 lines scan A 356b9b5d6f6a

Subscribe to this mod's changes

agent-dev-kit is a plugin published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 4d 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 2026-08-31.