agentic-skills

A plugin collection for AI coding agents, including tools for building temporary local workbenches. These workbenches are browser interfaces for tasks such as evaluations, pull-request reviews, document edits, spreadsheets, triage, and trace viewing.

In plain words
What is it for?
Use it to create disposable localhost applications with Bun, SQLite, React, and Astryx. It supports two-way human-and-agent sessions without a deployment step.
Why use it?
It provides a defined local setup for giving an agent and a person a shared working interface. The workbench uses a local database and live updates between the browser and terminal.

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 theagenticguy/agentic-plugins
agentmods
npx agentmods add plugins/theagenticguy/agentic-plugins/agentic-skills
Clone the repo
git clone --depth 1 https://github.com/theagenticguy/agentic-plugins

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

agentic-skills 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.

plugins/agentic-skills/.claude-plugin/plugin.json · 27 lines

What it actually says

{
  "name": "agentic-skills",
  "version": "0.3.0",
  "description": "Flagship skills for AI coding agents. Includes workbench-builder: disposable localhost Bun.serve + bun:sqlite + React 19 + Astryx workbenches with a two-way human↔agent loop over SSE — eval viewers, PR review rooms, document-redline surfaces, grid/spreadsheet editors, multi-surface triage queues, and trace replays, with zero build config and no deploy.",
  "author": {
    "name": "Laith Al-Saadoon"
  },
  "license": "MIT",
  "keywords": [
    "claude-code",
    "agent-skills",
    "ai-agents",
    "workbench",
    "localhost",
    "bun",
    "react",
    "astryx",
    "sse",
    "server-sent-events",
    "sqlite",
    "eval-viewer",
    "pr-review",
    "human-in-the-loop",
    "developer-tools"
  ]
}
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 · 27 lines scan A 1dfdbe5fcc33

Subscribe to this mod's changes

agentic-skills is a plugin published in the GitHub repository theagenticguy/agentic-plugins (5 stars, last pushed 20d 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.