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/orenashkenazy/gh-review-loop/stopgit clone --depth 1 https://github.com/OrenAshkenazy/gh-review-loopGrade 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.
This is a copy
86% identical to PreToolUse — 17 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"Stop": [
{
"hooks": [
{
"type": "command",
"command": "if [ -n \"$GGRL_STATE_DIR\" ]; then s=\"$GGRL_STATE_DIR/loop-active\"; else s=\"$HOME/.config/gh-review-loop/loop-active\"; [ -f \"$s\" ] || s=\"$HOME/.config/gh-gemini-review-loop/loop-active\"; fi; [ -f \"$s\" ] || exit 0; exec python3 \"${GGRL_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT:-.}}/skills/gh-review-loop/scripts/loop_summary_hook.py\"",
"timeout": 70
}
]
}
]
}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.
- 3d ago First seen · 13 lines scan A cab8d8d3f616
Stop is a hook published in the GitHub repository OrenAshkenazy/gh-review-loop (5 stars, last pushed 5d 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. It is 86% identical to PreToolUse, differing in 17 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Edit, Write, MultiEdit and NotebookEdit tool calls, executing posttooluse-mark-source-edit.mjs via node. From jasonm4130/claude-skills.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing check-context-md-flag.mjs via node. From jasonm4130/claude-skills.
SessionStart
Runs when a session starts on startup, executing session-env.py via python3. From mishahanin/heading-os-marketplace.
PreToolUse
Runs before the agent uses a tool for Write, Edit, MultiEdit, NotebookEdit, Bash and PowerShell tool calls, executing firewall.py via python. From revenantworks/claude-skills.
PreToolUse
Runs before the agent uses a tool for Bash(git push*) tool calls, executing check-plugin-versions.sh. From acostanzo/quickstop.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing remind.sh via sh. From pehcastro/harness.