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/ardurai/ardur/subagent-startgit clone --depth 1 https://github.com/ArdurAI/ardurGrade 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 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.
This is a copy
72% identical to SessionStart — 8 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": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "${CLAUDE_PLUGIN_ROOT}/hooks/subagent_start"
}
]
}
]
}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 · 13 lines scan A 047e8d136f63
SubagentStart is a hook published in the GitHub repository ArdurAI/ardur (2 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 72% identical to SessionStart, differing in 8 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing on-file-change.js via node. From codesstar/loci.
SessionStart
Runs when a session starts, executing memory_session_start.mjs via node. From friedbotstudio/baseline.
PreToolUse
Runs before the agent uses a tool for Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and mcp__.* tool calls, executing run.sh via sh. From vaaraio/vaara.
PostToolUse
Runs after a tool call finishes for Bash, WebFetch, WebSearch, Write, Edit, NotebookEdit, Task, SendMessage and mcp__.* tool calls, executing run.sh via sh. From vaaraio/vaara.
SessionStart
Runs when a session starts, executing run.sh via sh. From vaaraio/vaara.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it for 为什么还是不行, 根本原因, 主要矛盾, 实践方案, 验证标准, 证据, 继续推进, 项目推进不动, 项目卡住, 开源, 没人用, research plan, root cause, primary contradiction, retrospective, experiment design, practice plan, validation criteria, evidence, no users, GitHub stars, open source and adoption tool calls…