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/openrouterlabs/spawn/pre-tool-usegit clone --depth 1 https://github.com/OpenRouterLabs/spawnGrade A, and why
PreToolUse 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
{
"PreToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "bun .claude/scripts/enforce-worktree.ts"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bun .claude/scripts/pre-merge-check.ts"
}
]
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "bash -c 'INPUT=$(cat); CMD=$(echo \"$INPUT\" | jq -r \".tool_input.command // empty\"); echo \"$CMD\" | grep -qE \"gh pr (merge|ready)\" || exit 0; WT=$(echo \"$CMD\" | grep -oE \"/tmp/spawn-worktrees/[a-zA-Z0-9._/-]+\" | head -1); if [ -n \"$WT\" ] && [ -d \"$WT/packages/cli\" ]; then ROOT=\"$WT\"; else ROOT=$(git rev-parse --show-toplevel 2>/dev/null); fi; if [ -z \"$ROOT\" ] || [ ! -d \"$ROOT/packages/cli\" ]; then echo \"WARNING: Could not find spawn repo for pre-merge checks\" >&2; exit 0; fi; cd \"$ROOT/packages/cli\" || exit 2; echo \"Pre-merge gate: running biome check + bun test in $ROOT/packages/cli ...\" >&2; bunx @biomejs/biome check src/ 2>&1 || { echo \"BLOCKED: biome check failed — fix lint/format issues before merging\" >&2; exit 2; }; bun test 2>&1 || { echo \"BLOCKED: tests failed — fix failures before merging\" >&2; exit 2; }; echo \"Pre-merge checks passed\" >&2'"
}
]
}
]
}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 · 31 lines scan A ac5ec173f43e
PreToolUse is a hook published in the GitHub repository OpenRouterLabs/spawn (233 stars, last pushed 1mo 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 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 lycheemem_hook.py via python3. From LycheeMem/LycheeMem.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From mudrii/openclaw-dashboard.
PermissionRequest
Runs when the agent asks permission for an action, executing on-permission-request.py via python3. From autonomous-ai/autonomous-os.
PreToolUse
Runs before the agent uses a tool for Edit, Write, Read and Bash tool calls, executing block-dist.sh, enforce-bun.sh and no-truncated-schema-proof.sh via bash with --show-toplevel (3 commands). From lobu-ai/lobu.
PreCompact
Runs before the context is compacted, executing memx-hook.mjs via node. From NeoLi00/memX.
SubagentStop
Runs when a subagent finishes, executing memx-hook.mjs via node. From NeoLi00/memX.