agentmods.dev

UserPromptExpansion

UserPromptExpansion is a hook for Claude Code from skarn-security/agent-guard. Its token cost is not measured, scanned A, a copy of UserPromptSubmit, MIT.

A hook that runs a security-audit command when a user prompt is expanded before the coding agent sees it. A hook is an automatic action tied to a particular event.

In plain words
What is it for?
Use it to run skarn guard in audit mode during prompt expansion. The input does not describe any other job or behavior.
Why use it?
It adds a security check at the point where the prompt is being prepared, helping surface audit results before the agent handles the expanded prompt.

Hook for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skarn-guard plugin — 6 hooks, 1 MCP server shipped together

One of 6 entries in hooks.json upstream. Installing this one merges just its entry into your config; the other 5 are separate, each on its own page.

not rated 33repo 6d ago A scan tokens not measured copy · 94% MIT

Good fit Use it to run skarn guard in audit mode during prompt expansion. The input does not describe any other job or behavior.

Compare 6 hooks from other repositories ↓
Install with agentmods
npx agentmods add hooks/skarn-security/agent-guard/user-prompt-expansion
View source ↗ skarn-security/agent-guard getskarn.com
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.

Clone the repo
git clone --depth 1 https://github.com/skarn-security/agent-guard

Made for: Claude Code.

Or install skarn-guard, the plugin that ships this one along with the rest of its 6 hooks, 1 MCP server.

Wrote 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.

agentmods badge for UserPromptExpansion

README.md
[![agentmods](https://agentmods.dev/badge/hooks/skarn-security/agent-guard/user-prompt-expansion.svg)](https://agentmods.dev/hooks/skarn-security/agent-guard/user-prompt-expansion)
Your own site
<a href="https://agentmods.dev/hooks/skarn-security/agent-guard/user-prompt-expansion"><img src="https://agentmods.dev/badge/hooks/skarn-security/agent-guard/user-prompt-expansion.svg" alt="Measured on agentmods" height="20"></a>
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. A grade says what 26 rules found in the file — not that it is safe.
Origin 94% copy Near-identical to another mod in the catalogue.
Security

Grade A, and why

UserPromptExpansion 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 7d ago.

A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.

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.

Origin

This is a copy

94% identical to UserPromptSubmit — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

claude/hooks/hooks.json · 13 lines

What it actually says

{
  "UserPromptExpansion": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "skarn guard --guard-mode audit",
          "timeout": 5
        }
      ]
    }
  ]
}
Same file

What else hooks.json configures

This page is one entry in a file that holds 6. Installing the file brings all of them; each is measured and scanned on its own page.

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. 7d ago First seen · 13 lines scan A 278f47c196b3

Subscribe to this mod's changes

UserPromptExpansion is a hook published in the GitHub repository skarn-security/agent-guard (33 stars, last pushed 6d ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. It is 94% identical to UserPromptSubmit, differing in 2 lines, and is treated as a copy.

Securitygemini-cli-extension
Related

Other hooks, from other repositories

BeforeTool

Runs on the BeforeTool event for tool == "run_shell_command", tool == "run_shell_command", tool == "run_shell_command" && tool_input.command matches "^\\s*(npm (install, test, i, ci), pnpm (install, test, i), yarn (install, test, add, remove, upgrade), bun (install, test, i, add, remove), cargo build, make, docker…

Jamkris/everything-gemini-code · not measured

PreCompact

Runs before the context is compacted, executing nmem-hook-save.py with --event. From nowledge-co/community.

nowledge-co/community · not measured

SessionEnd

Runs when a session ends, executing nmem-hook-save.py with --event and --detach. From nowledge-co/community.

nowledge-co/community · not measured

BeforeAgent

Runs on the BeforeAgent event, running python -m securedact_enforced.gemini_hook --event BeforeAgen. From GigantesHJI/securedact-mcp.

GigantesHJI/securedact-mcp · not measured

SessionStart

Runs when a session starts, executing run.js via node. From Jamkris/everything-gemini-code.

Jamkris/everything-gemini-code · not measured

SessionStart

Runs when a session starts, executing hook.js via node. From yideng-xl/gemini-cli-hud.

yideng-xl/gemini-cli-hud · not measured