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/aawwcc/ape/subagent-startgit clone --depth 1 https://github.com/AAWWCC/apeGrade A, and why
SubagentStart 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.
This is a copy
84% identical to PreToolUse — 16 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
{
"SubagentStart": [
{
"hooks": [
{
"type": "command",
"command": "node --input-type=module -e \"import{join}from'node:path';import{pathToFileURL}from'node:url';const r=process.env.PLUGIN_ROOT,c=process.env.CLAUDE_PLUGIN_ROOT,p=r||c;if(!p)throw new Error('APE hook could not resolve its plugin root');if(r){delete process.env.CLAUDECODE;delete process.env.CLAUDE_CODE;delete process.env.CLAUDE_PLUGIN_ROOT;delete process.env.CLAUDE_PROJECT_DIR}else{process.env.CLAUDECODE='1';delete process.env.CLAUDE_CODE;delete process.env.CODEX_CWD}await import(pathToFileURL(join(p,'dist','ape-hooks.bundle.mjs')))\"",
"commandWindows": "node --input-type=module -e \"import{join}from'node:path';import{pathToFileURL}from'node:url';const r=process.env.PLUGIN_ROOT,c=process.env.CLAUDE_PLUGIN_ROOT,p=r||c;if(!p)throw new Error('APE hook could not resolve its plugin root');if(r){delete process.env.CLAUDECODE;delete process.env.CLAUDE_CODE;delete process.env.CLAUDE_PLUGIN_ROOT;delete process.env.CLAUDE_PROJECT_DIR}else{process.env.CLAUDECODE='1';delete process.env.CLAUDE_CODE;delete process.env.CODEX_CWD}await import(pathToFileURL(join(p,'dist','ape-hooks.bundle.mjs')))\"",
"timeout": 30,
"statusMessage": "Binding APE stage ticket"
}
]
}
]
}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 · 15 lines scan A 06818318b5b5
SubagentStart is a hook published in the GitHub repository AAWWCC/ape (0 stars, last pushed 2d 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 84% identical to PreToolUse, differing in 16 lines, and is treated as a copy.
Other hooks, from other repositories
SubagentStart
Runs when a subagent starts, executing capture-subagent.js via node. From SetraTheXX/Codex-Engineering-Workflow-Pack.
SubagentStop
Runs when a subagent finishes, executing capture-subagent.js via node. From SetraTheXX/Codex-Engineering-Workflow-Pack.
SubagentStop
Runs when a subagent finishes, running tlive hook subagent-stop. From y49/tlive.
SubagentStart
Runs when a subagent starts, executing run-hook.sh. From st0012/cctop.
SubagentStop
Runs when a subagent finishes, executing run-hook.sh. From st0012/cctop.
SubagentStop
Runs when a subagent finishes, executing subagent-stop.sh with --show-toplevel. From joris887/exosuit.