agentmods.dev

PreToolUse

PreToolUse is a hook for coding agents from architonixlabs/RepoOrch. Its token cost is not measured, scanned A, original, MIT.

A pre-command safety check that examines Bash commands before an agent runs them and blocks commands matching listed write-like or destructive patterns.

In plain words
What is it for?
Use it before Bash tool calls in agent or specialist contexts to catch commands such as file deletion or moving, in-place editing, Git commits and pushes, resets, cleanup, and permission changes.
Why use it?
It reduces the chance that an automated agent changes files, Git history, permissions, or other repository state unexpectedly.

Hook

Part of the repo-orchestrator plugin — 3 skills, 8 commands, 2 agents, 2 hooks shipped together

One of 2 entries in hooks.json — they are configured in one file and arrive together.

not rated 3 2mo ago A scan tokens not measured original MIT
View the source file architonixlabs/RepoOrch
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/architonixlabs/repoorch/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/architonixlabs/RepoOrch

Or install repo-orchestrator, the plugin that ships this one along with the rest of its 3 skills, 8 commands, 2 agents, 2 hooks.

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 PreToolUse

README.md
[![agentmods](https://agentmods.dev/badge/hooks/architonixlabs/repoorch/pre-tool-use.svg)](https://agentmods.dev/hooks/architonixlabs/repoorch/pre-tool-use)
Your own site
<a href="https://agentmods.dev/hooks/architonixlabs/repoorch/pre-tool-use"><img src="https://agentmods.dev/badge/hooks/architonixlabs/repoorch/pre-tool-use.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. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

PreToolUse 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 4d 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 · 14 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "node -e \"const cmd=(JSON.parse(process.env.CLAUDE_TOOL_INPUT||'{}')).command||'';const banned=[/\\brm\\s/,/\\bmv\\s/,/\\bcp\\s.*-[^-]*r/i,/\\bsed\\s+-i/,/\\btee\\s/,/\\btruncate\\s/,/git\\s+commit/,/git\\s+push/,/git\\s+add/,/git\\s+reset/,/git\\s+checkout\\s+--/,/git\\s+clean/,/\\bchmod\\s/,/\\bchown\\s/,/\\bmkdir\\s/,/\\btouch\\s/,/\\bwrite\\b/i,/\\bnpx\\s+.*rm/,/>\\s*[^&]/];const hit=banned.find(r=>r.test(cmd));if(hit){process.stdout.write(JSON.stringify({decision:'block',reason:'repo-orchestrator safety: write-like command blocked in specialist/subagent context: '+cmd.slice(0,120)}));process.exit(0);}\"",
          "async": false
        }
      ]
    }
  ]
}
Same file

What else hooks.json configures

This page is one entry in a file that holds 2. 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. 4d ago First seen · 14 lines scan A f0d38f91ceda

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository architonixlabs/RepoOrch (3 stars, last pushed 2mo 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 2026-08-31.

Securityagent-teamsai-agentsclaude-codeclaude-code-plugindevtoolsmicroservices
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Edit, Write and MultiEdit tool calls, executing plugin-dev-guard.sh. From odere-pro/claude-calibration.

odere-pro/claude-calibration · not measured

PostToolUse

Runs after a tool call finishes for Write, Edit, MultiEdit, ExitPlanMode, Agent, Write, Edit, MultiEdit, NotebookEdit, Agent, Workflow, Skill, Agent and Workflow tool calls, running python3 (6 commands). From dbc-oduffy/coordinator-claude.

dbc-oduffy/coordinator-claude · not measured

SubagentStart

Runs when a subagent starts, running python3. From dbc-oduffy/coordinator-claude.

dbc-oduffy/coordinator-claude · not measured

Stop

Runs when the agent finishes a response, running python3. From dbc-oduffy/coordinator-claude.

dbc-oduffy/coordinator-claude · not measured

SubagentStop

Runs when a subagent finishes, running python3. From dbc-oduffy/coordinator-claude.

dbc-oduffy/coordinator-claude · not measured

SessionEnd

Runs when a session ends, running python3. From dbc-oduffy/coordinator-claude.

dbc-oduffy/coordinator-claude · not measured