agentmods.dev

PostToolUse

A post-action security check that runs after selected tools finish, including Bash, web searches, web page fetching, and file-editing tools.

In plain words
What is it for?
It is for applying AgentGuards checks after Bash, web, writing, editing, and multi-file editing operations.
Why use it?
It can scan returned content or completed actions for unsafe material, data exposure, or other problems after the tool has run.

Hook

Part of the agentguards-claude-selfhosted plugin — 3 skills, 3 hooks shipped together

1 3d ago A scan tokens not measured original MIT
View the source file alelaguard/agentguards-plugins
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/alelaguard/agentguards-plugins/post-tool-use
Clone the repo
git clone --depth 1 https://github.com/alelaguard/agentguards-plugins

Or install agentguards-claude-selfhosted, the plugin that ships this one along with the rest of its 3 skills, 3 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

PostToolUse 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-selfhosted/hooks/hooks.json · 13 lines

What it actually says

{
  "PostToolUse": [
    {
      "matcher": "Bash|WebFetch|WebSearch|Write|Edit|MultiEdit",
      "hooks": [
        {
          "type": "command",
          "command": "python3 \"${CLAUDE_PLUGIN_ROOT}/scripts/agentguards_hook.py\" PostToolUse"
        }
      ]
    }
  ]
}
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 · 13 lines scan A 7a1418f04bb6

Subscribe to this mod's changes

PostToolUse is a hook published in the GitHub repository alelaguard/agentguards-plugins (1 stars, last pushed 3d 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.

GuardrailsSecurityai-securityclaude-codeclaude-code-plugincodexllm-security
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool, executing atr_scan.py via python3. From Agent-Threat-Rule/agent-threat-rules.

Agent-Threat-Rule/agent-threat-rules · not measured

PostToolUse

Runs after a tool call finishes for Edit, Write and NotebookEdit tool calls, executing ruff_on_edit.py via python3. From guardana/guardana.

guardana/guardana · not measured

BeforeTool

Runs on the BeforeTool event, executing cli.js via node with --harness. From ilyautov/cordon.

ilyautov/cordon · not measured

AfterTool

Runs on the AfterTool event, executing cli.js via node with --harness. From ilyautov/cordon.

ilyautov/cordon · not measured

AfterAgent

Runs on the AfterAgent event, executing cli.js via node with --harness. From ilyautov/cordon.

ilyautov/cordon · not measured

PreToolUse

Runs before the agent uses a tool for Bash tool calls, executing check_action.py. From kernora-ai/agent-sec.

kernora-ai/agent-sec · not measured