Stop

Stop is a hook for coding agents from spinningrachel/career-engine. Its token cost is not measured, scanned A, original, MIT.

A stop-of-response hook that runs a token-usage logging script after the agent finishes. A hook is an automatic action attached to an event.

In plain words
What is it for?
Use it to log token usage and flag pipeline turns that pause while actively processing roles or application documents.
Why use it?
It records usage after each response and checks whether a career pipeline stopped mid-run for an improper reason.

Hook

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the career-engine plugin — 29 skills, 17 agents, 1 hook shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add spinningrachel/career-engine
Claude Code
/plugin install career-engine

Or install career-engine, the plugin that ships this one along with the rest of its 29 skills, 17 agents, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for Stop

README.md
[![agentmods](https://agentmods.dev/badge/hooks/spinningrachel/career-engine/stop.svg)](https://agentmods.dev/hooks/spinningrachel/career-engine/stop)
Your own site
<a href="https://agentmods.dev/hooks/spinningrachel/career-engine/stop"><img src="https://agentmods.dev/badge/hooks/spinningrachel/career-engine/stop.svg" alt="Measured on agentmods" height="20"></a>
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 3d 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 · 16 lines

How it starts

The opening of the file, as written. The whole thing — 16 lines — stays where its author put it; the contents beside it link to each section on GitHub.

{
  "Stop": [
    {
      "hooks": [
        {
          "type": "command",
          "command": "bash \"${CLAUDE_PLUGIN_ROOT}/scripts/log-token-usage.sh\""
        },
        {
          "type": "prompt",
          "prompt": "You are checking a just-finished Claude Code turn for one specific, narrow failure mode documented in the career-engine plugin's CLAUDE.md as the 'mid-run scope-check anti-pattern': a career-engine pipeline run (orchestrator, intake, or edit) pausing or stopping mid-run to ask about scope, cost, run length, or call volume, instead of continuing to process its queue. Read last_assistant_message. Only flag a violation if BOTH hold: (1) the message shows clear evidence a pipeline run is actually EXECUTING in this session — it reports real pipeline tool activity from this run, such as a fetched Notion role queue, spawned career-coach/cv-writer/letter-writer/gatekeeper subagents, gatekeeper rounds on a specific role's draft, or writes to a run-scoped `_pipeline`/`_intake_pipeline` directory, `state.json`, or `halted-roles.json`. Merely MENTIONING the plugin, its files, its agents, or its pipeline steps is NOT evidence of a run, and neither is run output the USER pasted into chat for discussion: a session that is editing the plugin's markdown, debugging its doctrine, running QA, answering questions about how the pipeline works, or discussing its design is a development conversation, and a developer's question awaiting the user's answer in such a session is always legitimate — never auto-continue past it. AND (2) instead of calling a tool to advance the queue, or reporting one specific hard blocker (a real error, a missing required config key, or a role hitting its documented revision cap and being flagged to halted-roles.json per the flag-and-deliver policy), the message pauses, hedges, asks how to proceed, or narrates a rationale for stopping early because the run feels large, long, or expensive. If both hold, respond {\"ok\": false, \"reason\": \"

Read the full file on GitHub · 16 lines

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. 3d ago First seen · 16 lines scan A cf2143f05660

Subscribe to this mod's changes

Stop is a hook published in the GitHub repository spinningrachel/career-engine (4 stars, last pushed 22d 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.