SubagentStop

A completion check that runs when a helper agent finishes. It uses a shell command to confirm that the agent saved its report to disk.

In plain words
What is it for?
Verifying that review or research helpers left a report file before their work is treated as complete.
Why use it?
A helper agent’s answer can disappear when its working context ends; checking the saved file gives the main agent something it can inspect.

Hook

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/romerma/mstack/subagent-stop
Clone the repo
git clone --depth 1 https://github.com/romerma/mstack
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

SubagentStop 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.

hooks/hooks.json · 18 lines

What it actually says

{
  "SubagentStop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/bin/mstack",
          "args": [
            "hook",
            "subagent-stop"
          ],
          "timeout": 10,
          "description": "Confirm the subagent left its report on disk. A review subagent once went idle without writing one; the analysis lived only in its working context, which the parent never sees, so it would have vanished silently. A reply is not evidence, the file is."
        }
      ]
    }
  ]
}
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 · 18 lines scan A 430ead516d7e

Subscribe to this mod's changes

SubagentStop is a hook published in the GitHub repository romerma/mstack (1 stars, last pushed 8d 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.