agentmods.dev

UserPromptSubmit

A prompt-submission hook that runs two shell commands before the coding agent receives your prompt: a session heartbeat and a supervisor script.

In plain words
What is it for?
Use it to start session monitoring and supervision whenever a new prompt is submitted.
Why use it?
It lets these checks happen automatically at the start of every prompt, so you do not have to run them yourself.

Hook

Part of the agent-harness plugin — 13 skills, 1 command, 3 agents, 5 hooks shipped together

2 8d ago A scan tokens not measured copy · 92% MIT
View the source file joymin5655/Agent
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/joymin5655/agent/user-prompt-submit
Clone the repo
git clone --depth 1 https://github.com/joymin5655/Agent

Or install agent-harness, the plugin that ships this one along with the rest of its 13 skills, 1 command, 3 agents, 5 hooks.

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 92% copy Near-identical to another mod 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 2d 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

92% identical to SessionStart — 10 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.

hooks/hooks.json · 17 lines

What it actually says

{
  "UserPromptSubmit": [
    {
      "matcher": "*",
      "hooks": [
        {
          "type": "command",
          "command": "\"${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh\" agent-session-heartbeat.sh"
        },
        {
          "type": "command",
          "command": "\"${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh\" supervisor.py"
        }
      ]
    }
  ]
}
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 A 0c075b6c4f2e

Subscribe to this mod's changes

UserPromptSubmit is a hook published in the GitHub repository joymin5655/Agent (2 stars, last pushed 8d 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 92% identical to SessionStart, differing in 10 lines, and is treated as a copy.

LLMagent-infrastructureai-agentsclaude-codedevtoolspolicy-as-code
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Edit, Write, Read and Bash tool calls, executing block-dist.sh, enforce-bun.sh and no-truncated-schema-proof.sh via bash with --show-toplevel (3 commands). From lobu-ai/lobu.

lobu-ai/lobu · not measured

SessionStart

Runs when a session starts on startup, resume and compact, executing session-start.sh via bash (3 commands). From JKHeadley/instar.

JKHeadley/instar · 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

SessionStart

Runs when a session starts on startup and resume, executing goalflight-session-start-watchdog.sh. From simonrowland/goal-flight.

simonrowland/goal-flight · not measured

PostToolUse

Runs after a tool call finishes, executing pii_checker_hook.py and observability_hook.py via python3 (2 commands). From alibaba/anolisa.

alibaba/anolisa · not measured

WorktreeCreate

Runs when a git worktree is created, executing hook-event-reporter.js via node. From JKHeadley/instar.

JKHeadley/instar · not measured