agentmods.dev

UserPromptSubmit

A hook that runs a shell command whenever a user submits a prompt, before the coding agent processes it. It runs a script when that script is available and otherwise returns an empty result.

In plain words
What is it for?
Use it to trigger `share_hook.py` before prompt processing when the script is installed.
Why use it?
It provides a fixed point for performing an action at the start of every prompt. The supplied description does not explain what the script itself does.

Hook

Part of the agent-tunnel plugin — 1 hook shipped together

2.0k +3 3d ago A scan tokens not measured original MIT
View the source file pchalasani/claude-code-tools
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 hooks/pchalasani/claude-code-tools/user-prompt-submit
Clone the repo
git clone --depth 1 https://github.com/pchalasani/claude-code-tools

Or install agent-tunnel, the plugin that ships this one along with the rest of its 1 hook.

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

UserPromptSubmit 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 3d 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.

plugins/agent-tunnel/hooks/hooks.json · 13 lines

What it actually says

{
  "UserPromptSubmit": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "bash -c 'if test -f \"${CLAUDE_PLUGIN_ROOT}/hooks/share_hook.py\"; then python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/share_hook.py\"; else echo \"{}\"; fi'",
          "timeout": 10
        }
      ]
    }
  ]
}
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. 3d ago First seen · 13 lines scan A fdeb3d37addd

Subscribe to this mod's changes

UserPromptSubmit is a hook published in the GitHub repository pchalasani/claude-code-tools (1,989 stars, last pushed 3d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

LLMclaude-codeclicli-agentcode-agenttmux
Related

Other hooks, from other repositories

SessionEnd

Runs when a session ends, running claude-tmux-cleanup. From nicknisi/dotfiles.

nicknisi/dotfiles · not measured

Stop

Runs when the agent finishes a response, executing stop_report_hook.sh, tmux_signal_stop_receipt.sh and session_stop_rotation.py via bash with --show-toplevel (3 commands). From Vinix24/vnx-orchestration.

Vinix24/vnx-orchestration · not measured

SessionEnd

Runs when a session ends, executing session_reconcile_cleanup.sh and build_current_state.py via bash with --show-toplevel (2 commands). From Vinix24/vnx-orchestration.

Vinix24/vnx-orchestration · not measured

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing tmux_signal_prompt_received.sh via bash with --show-toplevel. From Vinix24/vnx-orchestration.

Vinix24/vnx-orchestration · not measured

PreToolUse

Runs before the agent uses a tool, executing pre-tool-use.sh via bash. From nicknisi/fleet.

nicknisi/fleet · not measured

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing inject_recall.py via python3. From Yuno15-bb/c-brain.

Yuno15-bb/c-brain · not measured