agentmods.dev

PreToolUse

A pre-action check that runs before the coding agent uses commands, delegates work, edits files, or accesses the web.

In plain words
What is it for?
Use it to guard Bash commands, agent or task delegation, file edits, and web searches or fetches in an evolve-loop project.
Why use it?
It can stop an action when the project’s evolve-loop rules or limits are not satisfied, before the action happens.

Hook for Claude Code

5 2d ago A scan tokens not measured original Apache-2.0
View the source file mickeyyaya/evolve-loop
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/mickeyyaya/evolve-loop/pre-tool-use
Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop

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 · 49 lines

What it actually says

{
  "PreToolUse": [
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "B=\"$CLAUDE_PROJECT_DIR/go/bin/evolve\"; [ -x \"$B\" ] || B=\"$CLAUDE_PROJECT_DIR/go/evolve\"; \"$B\" guard ship --evolve-dir \"$CLAUDE_PROJECT_DIR/.evolve\""
        }
      ]
    },
    {
      "matcher": "Agent|Task",
      "hooks": [
        {
          "type": "command",
          "command": "B=\"$CLAUDE_PROJECT_DIR/go/bin/evolve\"; [ -x \"$B\" ] || B=\"$CLAUDE_PROJECT_DIR/go/evolve\"; \"$B\" guard phase --evolve-dir \"$CLAUDE_PROJECT_DIR/.evolve\""
        }
      ]
    },
    {
      "matcher": "Edit|Write",
      "hooks": [
        {
          "type": "command",
          "command": "B=\"$CLAUDE_PROJECT_DIR/go/bin/evolve\"; [ -x \"$B\" ] || B=\"$CLAUDE_PROJECT_DIR/go/evolve\"; \"$B\" guard role --evolve-dir \"$CLAUDE_PROJECT_DIR/.evolve\""
        }
      ]
    },
    {
      "matcher": "WebSearch|WebFetch|Bash",
      "hooks": [
        {
          "type": "command",
          "command": "B=\"$CLAUDE_PROJECT_DIR/go/bin/evolve\"; [ -x \"$B\" ] || B=\"$CLAUDE_PROJECT_DIR/go/evolve\"; \"$B\" guard quota --evolve-dir \"$CLAUDE_PROJECT_DIR/.evolve\""
        }
      ]
    },
    {
      "matcher": "Bash",
      "hooks": [
        {
          "type": "command",
          "command": "B=\"$CLAUDE_PROJECT_DIR/go/bin/evolve\"; [ -x \"$B\" ] || B=\"$CLAUDE_PROJECT_DIR/go/evolve\"; \"$B\" guard docdelete --evolve-dir \"$CLAUDE_PROJECT_DIR/.evolve\""
        }
      ]
    }
  ]
}
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 · 49 lines scan A 21ee4b9fae6b

Subscribe to this mod's changes

PreToolUse is a hook published in the GitHub repository mickeyyaya/evolve-loop (5 stars, last pushed 2d ago), licensed Apache-2.0. 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.

ai-agentsai-pipelineautonomous-codingclaude-codeclaude-code-plugincode-quality
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Write, Edit and MultiEdit tool calls, running an inline shell check. From get-tmonier/argot.

get-tmonier/argot · not measured

Stop

Runs when the agent finishes a response, executing dispatch.cjs, envrc-guarded-source.sh and context-auto-refresh.cjs via node (3 commands). From nguyenthienthanh/aura-frog.

nguyenthienthanh/aura-frog · not measured

SubagentStart

Runs when a subagent starts, executing agent_state.py via bash. From pillip/claude-dev-kit.

pillip/claude-dev-kit · not measured

TaskCompleted

Runs when a task is marked completed, executing task-completed.cjs via node. From nguyenthienthanh/aura-frog.

nguyenthienthanh/aura-frog · not measured

Notification

Runs when the agent sends a notification, running an inline shell check. From martinkup/symfony-profiler-optimization-advisor-bundle.

martinkup/symfony-profiler-optimization-advisor-bundle · not measured

SessionStart

Runs when a session starts, executing session-start.py via python3. From bcanfield/agentic-tech-debt.

bcanfield/agentic-tech-debt · not measured