A set of checks that runs before the agent edits files or uses shell commands. It blocks edits to generated files and secret files, rejects commands that bypass checks, and runs a test-first gate.

Use it to enforce rules around protected files, secret files, bypass flags, and required checks before editing or running commands.

It prevents risky edits and skipped safeguards before they reach the project.

PreToolUse — Hook by recomposesh

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/recomposesh/recompose/pre-tool-use

Clone the repo

git clone --depth 1 https://github.com/recomposesh/recompose

Made for: Claude Code.

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 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.

.claude/settings.json · 33 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Edit|Write",
      "hooks": [
        {
          "type": "command",
          "command": "f=$(jq -r '.tool_input.file_path // empty'); case \"$f\" in *pnpm-lock.yaml) echo 'pnpm-lock.yaml is generated - run pnpm commands instead of editing it' >&2; exit 2;; *.env.example) ;; *.env|*.env.*) echo '.env files hold secrets - the user edits these by hand' >&2; exit 2;; *.pem|*.key|*.p12|*/id_rsa*|*/id_ed25519*) echo 'key material is never edited by Claude' >&2; exit 2;; esac"
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "c=$(jq -r '.tool_input.command // empty'); case \"$c\" in *--no-verify*|*--no-gpg-sign*) echo 'hook bypass flags are blocked - fix the failing gate instead of skipping it' >&2; exit 2;; esac"
        }
      ]
    },
    {
      "matcher": "Edit|Write|NotebookEdit",
      "hooks": [
        {
          "type": "command",
          "command": "node \"${CLAUDE_PROJECT_DIR}/.claude/workflows/hooks/launch-gate.mjs\"",
          "timeout": 120,
          "statusMessage": "test-first gate"
        }
      ]
    }
  ]
}

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.

2d ago First seen · 33 lines scan A ecc800d93c14

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository recomposesh/recompose (25 stars, last pushed 5d 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.

Security Testing

PreToolUse

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other hooks, from other repositories

PostToolUse

SessionStart

SessionStart

PreToolUse

PreToolUse

SessionStart