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/sparq-org/sparq/pre-tool-usegit clone --depth 1 https://github.com/sparq-org/sparqWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/hooks/sparq-org/sparq/pre-tool-use)<a href="https://agentmods.dev/hooks/sparq-org/sparq/pre-tool-use"><img src="https://agentmods.dev/badge/hooks/sparq-org/sparq/pre-tool-use.svg" alt="Measured on agentmods" height="20"></a>Grade 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 6d 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 — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "hook_input=$(cat); guard=\"$CLAUDE_PROJECT_DIR/scripts/check-pr-arm-base.py\"; if [ -n \"$CLAUDE_PROJECT_DIR\" ] && [ -r \"$guard\" ] && guard_output=$(printf '%s' \"$hook_input\" | python3 \"$guard\") && [ -n \"$guard_output\" ]; then printf '%s\\n' \"$guard_output\"; elif printf '%s' \"$hook_input\" | grep -Eq 'gh[[:space:]]+pr[[:space:]]+merge'; then printf '%s\\n' '{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"permissionDecision\":\"deny\",\"permissionDecisionReason\":\"🤖 SPARQ arm guard: scripts/check-pr-arm-base.py could not run, so this gh pr merge cannot be proven not to be the release-plz Release PR. DENYING (fail-closed, #1135 - a crates.io version can never be unpublished). Restore the guard script, or have a maintainer merge by hand.\"}}'; else printf '%s\\n' '{\"hookSpecificOutput\":{\"hookEventName\":\"PreToolUse\",\"permissionDecision\":\"allow\",\"permissionDecisionReason\":\"🤖 SPARQ arm guard: guard script unavailable or failed and this is not a gh pr merge, so no arm is being gated; allowing (the stacked-base axis is fail-open by design).\"}}'; fi",
"timeout": 40,
"statusMessage": "Stacked-PR arm guard: checking PR base is main…"
},
{
"type": "agent",
"agent": "sparq-perf-reviewer",
"model": "claude-opus-5",
"timeout": 300,
"statusMessage": "PERFORMANCE-discretion gate: reviewing PR before arm…",
"prompt": "You are the sparq PERFORMANCE-discretion gate (the sparq-perf-reviewer agent). This is a PreToolUse hook on Bash. The tool call being gated is:\n\n$ARGUMENTS\n\nFIRST: inspect tool_input.command. If it is NOT a PR-arming command — i.e. it is NOT a `gh pr merge` that arms a PR for the merge train (look for `gh pr merge` with `--auto`) — then this is out of your scope: immediately ALLOW it untouched. Return exaWhat else settings.json configures
This page is one entry in a file that holds 3. Installing the file brings all of them; each is measured and scanned on its own page.
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.
- 6d ago First seen · 23 lines scan A 99e9e797ca4b
PreToolUse is a hook published in the GitHub repository sparq-org/sparq (10 stars, last pushed today), 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 2026-08-31.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From apache/superset.
PreToolUse
Runs before the agent uses a tool, executing pre-write.sh and pre-bash.sh (2 commands). From anthropics/claude-cookbooks.
PreCompact
Runs before the context is compacted for manual and auto tool calls, executing hook-handler.cjs via node (4 commands). From ruvnet/RuView.
SessionStart
Runs when a session starts, running an inline shell check. From Egonex-AI/Understand-Anything.
SessionStart
Runs when a session starts, executing hook-handler.cjs and auto-memory-hook.mjs via node (2 commands). From ruvnet/RuView.
SessionStart
Runs when a session starts, executing session-start.sh. From addyosmani/agent-skills.