agentmods.dev

Stop

A stop hook is an automatic action that runs when an AI agent finishes replying. This one runs two Python scripts for routing and ledger checks.

In plain words
What is it for?
It is for triggering the `dag-tripwire.py` and `ledger-tripwire.py` scripts after agent responses.
Why use it?
It performs those checks automatically at the end of each response, so they do not depend on someone remembering to run them.

Hook

5 6d ago A scan tokens not measured original MIT
View the source file Buckeyes22/subagent-model-routing
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/buckeyes22/subagent-model-routing/stop
Clone the repo
git clone --depth 1 https://github.com/Buckeyes22/subagent-model-routing
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.

plugins/subagent-model-routing-claude/hooks/hooks.json · 22 lines

What it actually says

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/dag-tripwire.py\"",
          "statusMessage": "dag-routing tripwire"
        }
      ]
    },
    {
      "hooks": [
        {
          "type": "command",
          "command": "python3 \"${CLAUDE_PLUGIN_ROOT}/hooks/ledger-tripwire.py\"",
          "statusMessage": "subagent-model-routing ledger tripwire"
        }
      ]
    }
  ]
}
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 · 22 lines scan A 40d7203927cd

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository Buckeyes22/subagent-model-routing (5 stars, last pushed 6d 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.

Multi-Agentai-agentsclaude-codellm-routingopenai-codexopencode
Related

Other hooks, from other repositories

PostToolUse

Runs after a tool call finishes for hivemind_find, mcp__plugin_swarm_swarm-tools__hivemind_find, skills_use, Skill, swarmmail_init, mcp__plugin_swarm_swarm-tools__swarmmail_init, hivemind_store, mcp__plugin_swarm_swarm-tools__hivemind_store, swarm_complete and TaskUpdate tool calls, running swarm claude track-tool…

joelhooks/swarm-tools · not measured

PreToolUse

Runs before the agent uses a tool for Edit, Write, swarm_complete, TaskCreate and TaskUpdate tool calls, running swarm claude pre-edit (3 commands). From joelhooks/swarm-tools.

joelhooks/swarm-tools · not measured

SubagentStart

Runs when a subagent starts for coordinator and worker tool calls, running swarm claude coordinator-start (2 commands). From joelhooks/swarm-tools.

joelhooks/swarm-tools · not measured

PostToolUse

Runs after a tool call finishes, running an inline shell check. From ladiossoop5star/open_magi.

ladiossoop5star/open_magi · not measured

SessionStart

Runs when a session starts, running swarm claude session-start. From joelhooks/swarm-tools.

joelhooks/swarm-tools · not measured

SubagentStop

Runs when a subagent finishes, running swarm claude subagent-stop. From joelhooks/swarm-tools.

joelhooks/swarm-tools · not measured