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/softspark/ai-toolkit/subagent-stopgit clone --depth 1 https://github.com/softspark/ai-toolkitGrade A, and why
SubagentStop 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 yesterday.
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.
What it actually says
{
"SubagentStop": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "AI_TOOLKIT_DIR=\"${CLAUDE_PLUGIN_ROOT}\" \"${CLAUDE_PLUGIN_ROOT}/hooks/subagent-stop.sh\""
}
]
}
]
}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.
- yesterday First seen · 13 lines scan A 6e3a1d0bd270
SubagentStop is a hook published in the GitHub repository softspark/ai-toolkit (167 stars, last pushed 3d ago), licensed Apache-2.0. 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.
Other hooks, from other repositories
SubagentStart
Runs when a subagent starts, executing subagent-start-warmstart.py via python3. From notque/vexjoy-agent.
SubagentStart
Runs when a subagent starts, executing inject.sh. From HuskyDanny/OnPoint.
SubagentStart
Runs when a subagent starts, executing run-hook.cmd. From gustavo-meilus/superpipelines.
Stop
Runs when the agent finishes a response, executing session-summary.py, routing-outcome-stop-fallback.py, rules-distill-trigger.py and stop-drift-guard.py via python3 (4 commands). From notque/vexjoy-agent.
Stop
Runs when the agent finishes a response, executing dag-tripwire.py and ledger-tripwire.py via python3 (2 commands). From Buckeyes22/subagent-model-routing.
PreToolUse
Runs before the agent uses a tool for Bash, Edit, Write, NotebookEdit, WebFetch and Skill tool calls, executing scope_guard.py and subagent_report.py via python3 (2 commands). From thermiteau/maverick.