Stop

A set of commands that run automatically when an agent finishes a response. They create session summaries, resolve pending routing results, periodically distill rules, and check for toolkit drift.

In plain words
What is it for?
Use it to summarize sessions, finish pending routing work, trigger periodic rule updates, and warn about hook, documentation, or routing changes.
Why use it?
It automates end-of-session maintenance and can surface changes that may leave the toolkit inconsistent.

Hook for Claude Code

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/notque/vexjoy-agent/stop
Clone the repo
git clone --depth 1 https://github.com/notque/vexjoy-agent

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

Stop 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 yesterday.

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 · 35 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "python3 \"$HOME/.claude/hooks/session-summary.py\"",
          "description": "Generate session summary and save metrics",
          "timeout": 10000
        },
        {
          "type": "command",
          "command": "python3 \"$HOME/.claude/hooks/routing-outcome-stop-fallback.py\"",
          "description": "Resolve still-pending routing outcomes at session end (autonomous runs with no next user turn)",
          "timeout": 3000
        },
        {
          "type": "command",
          "command": "python3 \"$HOME/.claude/hooks/rules-distill-trigger.py\"",
          "description": "Auto-trigger rules distillation every 7 days",
          "timeout": 5000
        },
        {
          "type": "command",
          "command": "python3 \"$HOME/.claude/hooks/stop-drift-guard.py\"",
          "description": "Advisory: re-wake the session when this session's changes introduce toolkit drift (hook smoke-test, doc-count, or routing-manifest drift) so it can be fixed before CI",
          "timeout": 20000,
          "asyncRewake": true,
          "rewakeMessage": "Toolkit drift guard found drift in this session's changes — fix the drift below (or acknowledge it), then continue with the user's original request or continue waiting for their reply. This is supplementary, not a replacement for your previous response:",
          "rewakeSummary": "Toolkit drift guard found drift to review"
        }
      ]
    }
  ]
}
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. yesterday First seen · 35 lines scan A 1322249468f8

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository notque/vexjoy-agent (417 stars, last pushed 2d 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.