agentmods.dev

PreToolUse

A set of checks that run before selected shell commands and can warn or block unsafe actions.

In plain words
What is it for?
Use it to enforce safer branching and pull-request workflows, protect against commands such as deleting data, and require write-enabled delegated tasks.
Why use it?
It helps prevent destructive commands, commits directly to the main branch, unapproved pull requests, and read-only delegation mistakes.

Hook

Part of the agent-dashboard plugin — 8 skills, 5 agents, 10 hooks shipped together

21 1mo ago C scan tokens not measured original MIT
View the source file bjornjee/agent-dashboard
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/bjornjee/agent-dashboard/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/bjornjee/agent-dashboard

Or install agent-dashboard, the plugin that ships this one along with the rest of its 8 skills, 5 agents, 10 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 C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade C, and why

PreToolUse 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 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

"description": "Block destructive shell commands (rm -rf, git reset --hard, DROP TABLE, etc.)"
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

adapters/claude-code/hooks/hooks.json · 56 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/warn-destructive.js\""
        }
      ],
      "description": "Block destructive shell commands (rm -rf, git reset --hard, DROP TABLE, etc.)"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/block-main-commit.js\""
        }
      ],
      "description": "Block git commit on main/master — require a feature branch"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/pr-skill-gate.js\""
        }
      ],
      "description": "Block direct gh pr create — require /agent-dashboard:pr"
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/codex-write-gate.js\""
        }
      ],
      "description": "Block codex-companion task without --write (prevents read-only sandbox)"
    },
    {
      "matcher": "*",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PLUGIN_ROOT}/scripts/hooks/agent-state-fast.js\"",
          "async": true,
          "timeout": 3
        }
      ],
      "description": "Fast state sync for dashboard (state, permission_mode, current_tool)"
    }
  ]
}
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 · 56 lines scan C cfeeda653d7f

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository bjornjee/agent-dashboard (21 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. 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 2026-08-30.

Securityagent-orchestrationai-agentsclaude-codeclicodexdeveloper-tools
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From Kanevry/session-orchestrator.

Kanevry/session-orchestrator · not measured

PreToolUse

Runs before the agent uses a tool for ^(Write, Edit, MultiEdit)$, ^(Glob, Grep)$, ^Read$, ^(Bash, PowerShell)$ and ^Agent$ tool calls, executing gate-hook.mjs and hook-handler.cjs via node (9 commands). From eric-cielo/moflo.

eric-cielo/moflo · not measured

SubagentStop

Runs when a subagent finishes, running an inline shell check. From MostAshraf/ai-sdlc-harness.

MostAshraf/ai-sdlc-harness · not measured

Stop

Runs when the agent finishes a response, running an inline shell check. From codician-team/growmos.

codician-team/growmos · not measured

PreToolUse

Runs before the agent uses a tool, executing hook.cjs via node. From Cotal-AI/Cotal.

Cotal-AI/Cotal · not measured

SubagentStop

Runs when a subagent finishes for code-reviewer tool calls, executing require-review-verdict.sh via sh. From vmobifystudio/app-dev-team.

vmobifystudio/app-dev-team · not measured