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/iii-experimental/agentos/pre-tool-usegit clone --depth 1 https://github.com/iii-experimental/agentosGrade B, and why
PreToolUse scanned grade B with 2 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 3d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
"command": "curl -s -X POST http://localhost:3111/api/memory/store -H 'Content-Type: application/json' -d '{\"agentId\":\"claude-code\",\"content\":\"File modified: $TOOL_INPUT_file_path\",\"role\":\"system\"}'", Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
"command": "curl -s -X POST http://localhost:3111/api/memory/store -H 'Content-Type: application/json' -d '{\"agentId\":\"claude-code\",\"content\":\"File modified: $TOOL_INPUT_file_path\",\"role\":\"system\"}'", What it actually says
{
"PreToolUse": [
{
"matcher": "^(Write|Edit)$",
"description": "Track file changes for agent memory",
"hooks": [
{
"type": "command",
"command": "curl -s -X POST http://localhost:3111/api/memory/store -H 'Content-Type: application/json' -d '{\"agentId\":\"claude-code\",\"content\":\"File modified: $TOOL_INPUT_file_path\",\"role\":\"system\"}'",
"timeout": 3000,
"continueOnError": true
}
]
}
]
}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.
- 3d ago First seen · 16 lines scan B 0c22e137b5be
PreToolUse is a hook published in the GitHub repository iii-experimental/agentos (162 stars, last pushed 3mo 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 B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
SessionEnd
Runs when a session ends, executing sessionend_lead_cleanup.py. From spacegrowth/claude-relay.
PreToolUse
Runs before the agent uses a tool, running claude-hook. From bobmatnyc/claude-mpm.
PreToolUse
Runs before the agent uses a tool for Write, Edit, MultiEdit and Bash tool calls, executing pyproject_protection.py, no_root_files_hook.py and auto_format_hook.py (3 commands). From namastexlabs/automagik-hive.
PreToolUse
Runs before the agent uses a tool for Edit, Write, MultiEdit and Bash tool calls, executing pretool_route_guard.py and pretool_bash_gate.py (2 commands). From spacegrowth/claude-relay.
SessionStart
Runs when a session starts, executing session-start.mjs via node. From anilcancakir/claude-code-plugin.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.