Stop

A stop hook that runs a shell command when the coding agent finishes a response. A shell command is a system instruction executed outside the agent’s normal conversation.

In plain words
What is it for?
Use it to trigger an end-of-response check, extract the latest user message from the transcript, add a notification title, and post the result to a configured endpoint.
Why use it?
It can automatically inspect the latest transcript entry and send selected response information to a notification service.

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/backpaper0/claude-code-in-devcontainer-example/stop
Clone the repo
git clone --depth 1 https://github.com/backpaper0/claude-code-in-devcontainer-example

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 B 2 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade B, and why

Stop scanned grade B with 2 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.

Sends data to an external URLmediumData exfiltration

A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.

"command": "jq -r '.transcript_path' | xargs -I{} cat {} | jq -c 'select(.type == \"user\" and (has(\"toolUseResult\") | not) and (.message.content | type == \"string\")) | { body: .message.content }' | tail -n 1 | jq -c

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

"command": "jq -r '.transcript_path' | xargs -I{} cat {} | jq -c 'select(.type == \"user\" and (has(\"toolUseResult\") | not) and (.message.content | type == \"string\")) | { body: .message.content }' | tail -n 1 | jq -c
.claude/settings.json · 13 lines

What it actually says

{
  "Stop": [
    {
      "matcher": "",
      "hooks": [
        {
          "type": "command",
          "command": "jq -r '.transcript_path' | xargs -I{} cat {} | jq -c 'select(.type == \"user\" and (has(\"toolUseResult\") | not) and (.message.content | type == \"string\")) | { body: .message.content }' | tail -n 1 | jq -c --arg title \"${NOTIFICATION_TITLE}\" '. + { title: $title }' | curl --connect-timeout 5 -X POST \"${NOTIFICATION_ENDPOINT}\" -H 'Content-Type: application/json' -d @-"
        }
      ]
    }
  ]
}
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 · 13 lines scan B 0952a0b7374a

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository backpaper0/claude-code-in-devcontainer-example (5 stars, last pushed 6mo ago), licensed MIT. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.