agentmods.dev

claude-code-recipes-v2

A small set of agent settings for a JavaScript project. It allows selected test, run, and configuration-reading commands, while blocking two specified actions.

In plain words
What is it for?
Use it to allow npm tests and scripts, read files under the user configuration directory, set NODE_ENV to development, and deny recursive removal or writes under /etc.
Why use it?
It defines a narrow permission boundary for the agent instead of leaving these actions unspecified. The settings also set the project environment to development.

Settings file for Claude Code

5 4mo ago C scan tokens not measured original MIT
View the source file forest6511/claude-code-recipes-v2
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.

agentmods
npx agentmods add settings/forest6511/claude-code-recipes-v2/settings
Clone the repo
git clone --depth 1 https://github.com/forest6511/claude-code-recipes-v2

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

claude-code-recipes-v2 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.

"Bash(rm -rf *)",
ch01-claude-md/recipe-05/.claude/settings.json · 17 lines

What it actually says

{
  "permissions": {
    "allow": [
      "Bash(npm test:*)",
      "Bash(npm run:*)",
      "Read(~/.config/**)"
    ],
    "deny": [
      "Bash(rm -rf *)",
      "Write(//etc/**)"
    ]
  },
  "env": {
    "NODE_ENV": "development"
  }
}
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 · 17 lines scan C 7307f840a294

Subscribe to this mod's changes

claude-code-recipes-v2 is a settings file published in the GitHub repository forest6511/claude-code-recipes-v2 (5 stars, last pushed 4mo 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.

LanguagesTesting
Related

Other settings, from other repositories

supabase

Agent settings declaring 2 hook events (SessionStart, PostToolUse).

supabase/supabase · not measured

claude-cookbooks

Agent settings declaring 2 hook events (SessionStart, PreToolUse).

anthropics/claude-cookbooks · not measured

claude-code-best-practice

Agent settings declaring 30 hook events (PreToolUse, PermissionRequest, PostToolUse, PostToolUseFailure) and 24 allowed tools.

shanraisshan/claude-code-best-practice · not measured

electron

Agent settings declaring 17 allowed tools.

electron/electron · not measured

uv

Agent settings declaring 2 hook events (SessionStart, PostToolUse).

astral-sh/uv · not measured

ui-ux-pro-max-skill

Agent settings declaring 7 allowed tools.

nextlevelbuilder/ui-ux-pro-max-skill · not measured