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.
npx agentmods add hooks/bullish0x/goal-cc/stopgit clone --depth 1 https://github.com/bullish0x/goal-ccWrote 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.
[](https://agentmods.dev/hooks/bullish0x/goal-cc/stop)<a href="https://agentmods.dev/hooks/bullish0x/goal-cc/stop"><img src="https://agentmods.dev/badge/hooks/bullish0x/goal-cc/stop.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
Stop scanned grade A with 1 finding 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 4d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
"command": "node -e \"const fs=require('fs'),path=require('path'),cp=require('child_process');let input='';process.stdin.on('data',d=>input+=d);process.stdin.on('end',()=>{let data={};try{data=JSON.parse(input||'{}')}cat What it actually says
{
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "node -e \"const fs=require('fs'),path=require('path'),cp=require('child_process');let input='';process.stdin.on('data',d=>input+=d);process.stdin.on('end',()=>{let data={};try{data=JSON.parse(input||'{}')}catch{}const roots=[process.cwd(),process.env.CLAUDE_PROJECT_DIR,process.env.PWD,data.cwd].filter(Boolean);for(const root of roots){let dir=path.resolve(root);for(;;){const helper=path.join(dir,'.claude','scripts','goal-helper.mjs');if(fs.existsSync(helper)){const r=cp.spawnSync(process.execPath,[helper,'stop-hook'],{input,encoding:'utf8'});if(r.stdout)process.stdout.write(r.stdout);if(r.stderr)process.stderr.write(r.stderr);process.exit(r.status == null ? 0 : r.status)}const parent=path.dirname(dir);if(parent===dir)break;dir=parent}}console.error('goal-helper.mjs not found');process.exit(1)})\""
}
]
}
]
}What else settings.json configures
This page is one entry in a file that holds 2. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 4d ago First seen · 12 lines scan A db56f44db295
Stop is a hook published in the GitHub repository bullish0x/goal-cc (6 stars, last pushed 3mo 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 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing update-check.js via node. From KevinZai/commander.
CwdChanged
Runs on the CwdChanged event, executing rot-router.ps1 and prover-remind.ps1 with --stdin (2 commands). From Nova-Violet-Role/RoT-MoE.
Stop
Runs when the agent finishes a response, running python3. From dbc-oduffy/coordinator-claude.
SessionStart
Runs when a session starts on startup, clear and compact, executing smart-install.js and bun-wrapper.cjs via node (4 commands). From nhevers/MoltBrain.
Notification
Runs when the agent sends a notification, executing notification.sh via bash. From prime-radiant-inc/claude-plugin-cxdb-integration.
Stop
Runs when the agent finishes a response, executing find-node.sh via bash (14 commands). From speson/not-my-reforge.