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/sehoon787/my-codex/subagent-stopgit clone --depth 1 https://github.com/sehoon787/my-codexGrade 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 2d 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.
What it actually says
{
"SubagentStop": [
{
"hooks": [
{
"type": "command",
"command": "node -e \"const fs=require('fs');const p=require('path');const d='.briefing/agents';if(fs.existsSync('.briefing/INDEX.md')){fs.mkdirSync(d,{recursive:true});const j=JSON.parse(fs.readFileSync(0,'utf8'));const at=j.agent_type||'unknown';var pm={explore:'research',executor:'implement','code-reviewer':'review','tdd-guide':'test',planner:'plan',debugger:'debug'};var phase=pm[at]||'';var sf='.briefing/state.json';var seq=0;try{var st=JSON.parse(fs.readFileSync(sf,'utf8'));seq=(parseInt(st.subagentSeq,10)||0)+1;st.subagentSeq=seq;fs.writeFileSync(sf,JSON.stringify(st,null,2)+'\\n')}catch(x){}var th=(j.description||j.name||'').replace(/[\\r\\n]+/g,' ').slice(0,120);const e={ts:new Date().toISOString(),agent_id:j.agent_id||'unknown',agent_type:at,phase:phase,seq:seq,task_hint:th};fs.appendFileSync(d+'/agent-log.jsonl',JSON.stringify(e)+'\\n')}\"",
"timeout": 5000
},
{
"type": "command",
"command": "node \"$HOME/.codex/hooks/session-sync.js\" subagent",
"timeout": 5000
},
{
"type": "command",
"command": "node -e \"console.log(JSON.stringify({hookSpecificOutput:{additionalContext:'VERIFICATION REQUIRED: Subagent finished. (1) Read changed files yourself, (2) Run tests/diagnostics to verify, (3) Only then mark task complete. Agent execution auto-logged to .briefing/agents/agent-log.jsonl.'}}))\"",
"timeout": 5000
}
]
}
]
}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.
- 2d ago First seen · 23 lines scan A 598dc7bf91f0
SubagentStop is a hook published in the GitHub repository sehoon787/my-codex (25 stars, last pushed 4d 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 2026-08-30.
Other hooks, from other repositories
Stop
Runs when the agent finishes a response, executing commit-session.sh. From HyperAITeam/CLITrigger.
SessionStart
Runs when a session starts on startup, executing load-recent-changes.sh. From HyperAITeam/CLITrigger.
SessionStart
Runs when a session starts on startup, resume, clear and compact, executing sidebar-control.sh via bash with --plugin-root and --plugin-data. From JaceHwang/codex-usage-sidebar.
SessionStart
Runs when a session starts, executing lifecycle.js via node. From KiwiGaze/codex-status-bar.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing update.js via node. From KiwiGaze/codex-status-bar.
PreToolUse
Runs before the agent uses a tool, executing update.js via node. From KiwiGaze/codex-status-bar.