groundwork marketplace

A starter collection of tools for Claude Code, including command safety checks, a wiki-based quality process, and managed agent memory.

In plain words
What is it for?
Use it to block or confirm dangerous operations, record a redacted activity log, follow documentation-based checks, and manage memory over time.
Why use it?
It provides rules for risky commands, a way to ground work in project documentation, and a process for handling stored memories.

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 choiyounggi/groundwork
agentmods
npx agentmods add plugins/choiyounggi/groundwork/marketplace
Clone the repo
git clone --depth 1 https://github.com/choiyounggi/groundwork

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 C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade C, and why

groundwork marketplace 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 2d 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.

"description": "Safe-by-default guardrails for Claude Code — blocks supply-chain / disk-destroying / fork-bomb commands and asks before rm -rf, force-push, DROP/TRUNCATE, kubectl delete, secret/credential access, and clo
.claude-plugin/marketplace.json · 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.

{
  "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  "name": "groundwork",
  "description": "A safe-by-default, batteries-included Claude Code harness starter pack — guardrails, a wiki-grounded quality loop, and a memory lifecycle.",
  "owner": {
    "name": "choiyounggi",
    "url": "https://github.com/choiyounggi"
  },
  "plugins": [
    {
      "name": "guardrails",
      "description": "Safe-by-default guardrails for Claude Code — blocks supply-chain / disk-destroying / fork-bomb commands and asks before rm -rf, force-push, DROP/TRUNCATE, kubectl delete, secret/credential access, and cloud-resource deletion. Every rule configurable. Plus a redacted audit log.",
      "category": "development",
      "author": {
        "name": "choiyounggi",
        "url": "https://github.com/choiyounggi"
      },
      "source": "./plugins/guardrails",
      "homepage": "https://github.com/choiyounggi/groundwork",
      "version": "1.2.1",
      "tags": [
        "security",
        "guardrails",
        "hooks",
        "safety",
        "agent-safety",
        "claude-code"
      ]
    },
    {
      "name": "memory-loop",
      "description": "A memory lifecycle for Claude Code's native memory — a save gate against hallucinated memories, tiered expiry (short-tier memories archived, never deleted), a propose-then-confirm consolidation pass that merges and dedupes long-tier memory, a periodic learning-review nudge, a two-file habit frame (HABITS.md always loaded, HABITS-CASES.md on demand), and an optional one-time identity setup where the assistant can pick its own name. Local-only.",
      "category": "development",
      "author": {
        "name": "choiyounggi",
        "url": "https://github.com/choiyounggi"
      },
      "source": "./plugins/memory-loop",
      "homepage": "https://github.com/choiyounggi/groundwork",
      "version": "1.5.0",
      "tags": [
        "memory",
        "habits",
        "lifecycle",
        "identity",
        "se

Read the full file on GitHub · 77 lines

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. 2d ago First seen · 77 lines scan C b0c55b400cae

Subscribe to this mod's changes

groundwork marketplace is a plugin published in the GitHub repository choiyounggi/groundwork (3 stars, last pushed 3d 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 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.