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/optave/ops-codegraph-tool/pre-tool-usegit clone --depth 1 https://github.com/optave/ops-codegraph-toolGrade 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 yesterday.
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:
- PostToolUse — 94% identical, 59 lines differ
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/snapshot-pre-bash.sh\"",
"timeout": 5
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/check-readme.sh\"",
"timeout": 10
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/guard-git.sh\"",
"timeout": 10
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/guard-pr-body.sh\"",
"timeout": 10
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/commitlint-local.sh\"",
"timeout": 10
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$p/.claude/hooks\" ] || exit 0; bash \"$p/.claude/hooks/pre-commit.sh\"",
"timeout": 60
},
{
"type": "command",
"command": "p=\"${CLAUDE_PROJECT_DIR}\"; [ -d \"$p/.claude/hooks\" ] || p=\"$(git rev-parse --show-toplevel 2>/dev/null)\"; [ -d \"$pWhat 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.
- yesterday First seen · 64 lines scan A c055b118165a
PreToolUse is a hook published in the GitHub repository optave/ops-codegraph-tool (92 stars, last pushed 3d 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
PreToolUse
Runs before the agent uses a tool for Read, Grep, Glob and Bash tool calls, executing scala-semantic-guard.sh. From MercurieVV/ScalaSemantic.
PreToolUse
Runs before the agent uses a tool for Read, Edit, Write, MultiEdit, NotebookEdit, Bash, Grep and Glob tool calls, executing pre-tool-use.js and report-gate-hook.js via node (11 commands). From ch015/code-pentester.
Stop
Runs when the agent finishes a response, executing on-stop.js via node. From ch015/code-pentester.
PostToolUse
Runs after a tool call finishes for Edit, Write, MultiEdit and NotebookEdit tool calls, running sh "$CLAUDE_PROJECT_DIR/scripts/hook-check". From GhostlyGawd/codeweb.
PreToolUse
Runs before the agent uses a tool for Edit, Write, MultiEdit and NotebookEdit tool calls, running python3 "$CLAUDE_PROJECT_DIR/scripts/hook-protect". From GhostlyGawd/codeweb.
PostToolUse
Runs after a tool call finishes, running whyline-hook. From anishmoncivarghese/sonde.