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/infinri/writ/subagent-startgit clone --depth 1 https://github.com/infinri/WritGrade 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- UserPromptSubmit — 86% identical, 6 lines differ
What it actually says
{
"SubagentStart": [
{
"matcher": "",
"hooks": [
{
"type": "command",
"command": "bash ${CLAUDE_PLUGIN_ROOT}/hooks/scripts/writ-subagent-start.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.
- 2d ago First seen · 13 lines scan A 5fa70e78ef21
SubagentStart is a hook published in the GitHub repository infinri/Writ (189 stars, last pushed 18d 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, running kin stop-guard (2 commands). From jmcentire/kindex.
PostToolUse
Runs after a tool call finishes for Edit, Write, Bash and Read tool calls, executing world-model-capture.js via node. From SaravananJaichandar/world-model-mcp.
PreToolUse
Runs before the agent uses a tool for Edit and Write tool calls, executing world-model-validate.js via node. From SaravananJaichandar/world-model-mcp.
SessionStart
Runs when a session starts, executing world-model-session.js via node. From SaravananJaichandar/world-model-mcp.
PreCompact
Runs before the context is compacted, running kin compact-hook --emit-context. From jmcentire/kindex.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, running kin prompt-check. From jmcentire/kindex.