agentmods.dev

Stop

A finish-response hook that runs two shell checks when an agent completes a response. The checks record session token use and the tools used during the session.

In plain words
What is it for?
Use it to trigger session-token and session-tool logs whenever the agent finishes a response.
Why use it?
It provides an automatic end-of-response record without requiring the agent to run those checks manually. This can make session usage and activity easier to inspect.

Hook

14 3d ago A scan tokens not measured original MIT
View the source file Raven-Scout/scout-plugin
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/raven-scout/scout-plugin/stop
Clone the repo
git clone --depth 1 https://github.com/Raven-Scout/scout-plugin
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 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.

hooks/hooks.json · 18 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/engine/bin/scoutctl hook session-tokens",
          "timeout": 10
        },
        {
          "type": "command",
          "command": "${CLAUDE_PLUGIN_ROOT}/engine/bin/scoutctl hook session-tool-log",
          "timeout": 15
        }
      ]
    }
  ]
}
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 · 18 lines scan A 2560421c8ab2

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository Raven-Scout/scout-plugin (14 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 2026-08-30.

Autonomous Agentsagenticai-agentanthropicclaude-codeclaude-code-plugin
Related

Other hooks, from other repositories

PreToolUse

Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit, Write, Edit, MultiEdit, Agent, Task, Skill and Bash tool calls, executing run-hook.cmd (8 commands). From kenmulford/milestone-driver.

kenmulford/milestone-driver · not measured

SessionStart

Runs when a session starts on compact, executing run-hook.cmd. From kenmulford/milestone-driver.

kenmulford/milestone-driver · not measured

Stop

Runs when the agent finishes a response, executing audit.py via python3. From richer-richard/cc-research.

richer-richard/cc-research · not measured

SessionStart

Runs when a session starts, running bunx @desplega.ai/agent-swarm@latest hook. From desplega-ai/agent-swarm.

desplega-ai/agent-swarm · not measured

SessionEnd

Runs when a session ends, executing claude-session-end.ps1. From orwa-mahmoud/nightshift.

orwa-mahmoud/nightshift · not measured

SessionStart

Runs when a session starts on startup, clear and compact, executing preflight.sh. From jdanigo/hydraia.

jdanigo/hydraia · not measured