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/echovic/boss-skill/pre-tool-usegit clone --depth 1 https://github.com/echoVic/boss-skillGrade C, and why
PreToolUse scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
"description": "Intercept dangerous shell commands (rm -rf, git push --force, DROP TABLE, etc.)", What it actually says
{
"PreToolUse": [
{
"matcher": "Write|Edit",
"hooks": [
{
"type": "command",
"command": "boss hooks run \"pre:write:artifact-guard\" \"scripts/hooks/pre-tool-write.js\" \"standard,strict\"",
"timeout": 5
}
],
"description": "Protect execution.json and validate stage status before artifact writes",
"id": "pre:write:artifact-guard"
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "boss hooks run \"pre:bash:dangerous-cmd-guard\" \"scripts/hooks/pre-tool-bash.js\" \"standard,strict\"",
"timeout": 5
}
],
"description": "Intercept dangerous shell commands (rm -rf, git push --force, DROP TABLE, etc.)",
"id": "pre:bash:dangerous-cmd-guard"
}
]
}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 · 28 lines scan C d3052f6ad2fd
PreToolUse is a hook published in the GitHub repository echoVic/boss-skill (553 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 C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
SessionStart
Runs when a session starts, executing session-start.sh via bash. From choucrifahed/agent-plugins.
PreToolUse
Runs before the agent uses a tool for mcp__.*__(get_data_from_fields, get_sql_from_fields, initiate_analysis), mcp__.*__(create_object, update_object, create_entity, import_tables, create_context_item, update_context_item), mcp__.*__(list_entities, get_entity, get_field, search_model, list_databases, list_schemas…
SessionStart
Runs when a session starts, running an inline shell check. From n24q02m/imagine-mcp.
Stop
Runs when the agent finishes a response, executing stop.sh via bash. From kage-core/Kage.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing pre-release-block.sh. From sachinshelke/codevira.
PostToolUse
Runs after a tool call finishes for Write and Edit tool calls, executing format_and_lint.sh. From supabase/supabase.