agentmods.dev

UserPromptSubmit

A set of shell commands that runs whenever you submit a prompt, before the coding agent processes it. Shell commands are text instructions executed by the computer.

In plain words
What is it for?
Run behavior-feedback, prompt-submit, and subagent-stance scripts when a new prompt is submitted.
Why use it?
It lets the agent apply automatic behavior checks and feedback at the start of each request. The input only identifies the commands, not the details of what they do.

Hook

Part of the do-it plugin — 11 skills, 3 commands, 10 agents, 5 hooks shipped together

27 21d ago A scan tokens not measured original MIT
View the source file tdwhere123/do-it
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/tdwhere123/do-it/user-prompt-submit
Clone the repo
git clone --depth 1 https://github.com/tdwhere123/do-it

Or install do-it, the plugin that ships this one along with the rest of its 11 skills, 3 commands, 10 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 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.

hooks/hooks.json · 23 lines

What it actually says

{
  "UserPromptSubmit": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/hooks/behavior-feedback.sh",
          "timeout": 10
        },
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/hooks/prompt-submit.sh",
          "timeout": 25
        },
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/hooks/subagent-stance.sh",
          "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 · 23 lines scan A 11bd45ce882a

Subscribe to this mod's changes

UserPromptSubmit is a hook published in the GitHub repository tdwhere123/do-it (27 stars, last pushed 21d 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.

Writing and docsagentic-workflowagentsai-agentscodexcodex-clideveloper-tools
Related

Other hooks, from other repositories

PostToolUse

Runs after a tool call finishes for Bash tool calls, executing capture-tool-result.sh via bash. From share-skills/pi.

share-skills/pi · not measured

PostToolUse

Runs after a tool call finishes for Edit, MultiEdit and Write tool calls, executing post_tool_use.js and post_tool_probe.js via node (4 commands). From MaxForAI/Tokenless.

MaxForAI/Tokenless · not measured

WorktreeCreate

Runs when a git worktree is created, executing worktree-create.mjs via node. From OpenDigitalProductFactory/opendigitalproductfactory.

OpenDigitalProductFactory/opendigitalproductfactory · not measured

Stop

Runs when the agent finishes a response, executing validate_stop.py via python3 with --show-toplevel. From 45ck/open-genome-agent.

45ck/open-genome-agent · not measured

PermissionRequest

Runs when the agent asks permission for an action for Write, Edit, MultiEdit, Bash and mcp__.* tool calls, executing Safety.hook.ts (2 commands). From DorShaer/Husk.

DorShaer/Husk · not measured

UserPromptSubmit

Runs when you submit a prompt, before the agent sees it, executing capture-prompt.sh via bash. From share-skills/pi.

share-skills/pi · not measured