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/brain-bootstrap/claude-code-brain-bootstrap/pre-tool-usegit clone --depth 1 https://github.com/brain-bootstrap/claude-code-brain-bootstrapGrade 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Write|Edit|MultiEdit",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PROJECT_DIR:-.}\"/.claude/hooks/config-protection.sh",
"timeout": 5
}
],
"description": "Block modifications to linter/formatter config files (biome.json, tsconfig, etc.)",
"id": "pre:edit:config-protection"
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PROJECT_DIR:-.}\"/.claude/hooks/rtk-rewrite.sh",
"timeout": 5
}
],
"description": "RTK: transparently rewrites commands for 60-90% output token savings (no-op if rtk not installed)",
"id": "pre:bash:rtk-rewrite"
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PROJECT_DIR:-.}\"/.claude/hooks/pre-commit-quality.sh",
"timeout": 30
}
],
"description": "Pre-commit quality gate: block secrets/debugger, warn console.log",
"id": "pre:bash:commit-quality"
},
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PROJECT_DIR:-.}\"/.claude/hooks/terminal-safety-gate.sh",
"timeout": 5
}
],
"description": "Block dangerous terminal patterns: interactive editors, bare psql, docker exec -it, standalone sleep",
"id": "pre:bash:terminal-safety"
},
{
"matcher": "*",
"hooks": [
{
"type": "command",
"command": "\"${CLAUDE_PROJECT_DIR:-.}\"/.claude/hooks/suggest-compact.sh",
"timeout": 5
}
],
"description": "Suggest /compact at strategic intervals (50 tool calls)",
"id": "pre:all:suggest-compact"
},
{
"matcher": "Glob|Grep",
"hooks": [
{
"type": "command",
"command": "[ -f graphify-out/grapWhat 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 · 76 lines scan A be9f7763b093
PreToolUse is a hook published in the GitHub repository brain-bootstrap/claude-code-brain-bootstrap (11 stars, last pushed 4mo 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
SessionStart
Runs when a session starts, executing set-plugin-root.sh via bash. From serpro69/claude-toolbox.
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing validate-bash.sh. From serpro69/claude-toolbox.
SubagentStop
Runs when a subagent finishes, running an inline shell check. From lukaszraczylo/claude-mnemonic.
PostToolUse
Runs after a tool call finishes, running an inline shell check. From lukaszraczylo/claude-mnemonic.
SessionStart
Runs when a session starts, running an inline shell check. From lukaszraczylo/claude-mnemonic.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, running an inline shell check. From lukaszraczylo/claude-mnemonic.