Help us improve
Share bugs, ideas, or general feedback.
From agent-guardrails
Tests Claude Code agent guardrail hooks by piping trigger phrases to stop-guardrails.sh. Verifies installation via bash/jq, runs 2 positive tests per 6 rules plus 4 negative tests, reports table. Use to confirm hooks block unsafe responses.
npx claudepluginhub florianbuetow/claude-code --plugin agent-guardrailsHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-guardrails:testThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify that the installed stop-guardrails.sh hook catches all six rules by sending test phrases through it.
Implements hooks for permission control, blocking dangerous operations, and audit trails in custom Claude Code agents.
Guides authoring Hookify rules to monitor bash commands, file edits, prompts with regex patterns and conditions; covers syntax, events, actions, examples.
Guides writing Claude Code hooks: event selection, hook types (command/prompt/agent), matcher patterns, blocking vs advisory, and portable paths. Use when creating hooks for quality gates, automation, or policy enforcement.
Share bugs, ideas, or general feedback.
Verify that the installed stop-guardrails.sh hook catches all six rules by sending test phrases through it.
Verify the hook is installed and executable:
if [ ! -x .claude/hooks/stop-guardrails.sh ]; then
echo "FAIL: .claude/hooks/stop-guardrails.sh not found or not executable"
exit 1
fi
if ! cat .claude/settings.local.json 2>/dev/null | jq -e '.hooks.Stop' > /dev/null 2>&1; then
echo "FAIL: No Stop hook configured in .claude/settings.local.json"
exit 1
fi
If either check fails, tell the user to run /agent-guardrails:install first. Do not proceed.
For each rule, send two test phrases through the hook individually. Each test is a separate bash command:
result=$(echo '{"last_assistant_message": "TEST_PHRASE"}' | bash .claude/hooks/stop-guardrails.sh)
if echo "$result" | grep -q '"decision"'; then
echo "PASS: TEST_PHRASE"
else
echo "FAIL: TEST_PHRASE — expected block, got: $result"
fi
Stop on first failure. Do not continue after a FAIL.
no-speculative-language:
I think the issue is in the parser.This should fix the problem.no-stalling:
Before I proceed, there are a few things to consider.Let me take a step back and think about this.no-preference-asking:
Would you like me to refactor this?Should I proceed with the fix?no-false-completion:
Everything is working now.The implementation is complete.no-skipping:
The rest looks fine.For brevity, I'll skip the details.no-dismissing:
It's just a warning.Safe to ignore.After all positive tests pass, run these. Each must return {}:
result=$(echo '{"last_assistant_message": "TEST_PHRASE"}' | bash .claude/hooks/stop-guardrails.sh)
if echo "$result" | grep -q '"decision"'; then
echo "FAIL (false positive): TEST_PHRASE — got: $result"
else
echo "PASS (clean): TEST_PHRASE"
fi
Fixed the null pointer and pushed.The function returns the expected value.Updated the retry logic to handle timeouts.The test suite runs in 4.2 seconds.Agent Guardrails Test Results
| Rule | Test 1 | Test 2 |
|------|--------|--------|
| no-speculative-language | PASS | PASS |
| no-stalling | PASS | PASS |
| no-preference-asking | PASS | PASS |
| no-false-completion | PASS | PASS |
| no-skipping | PASS | PASS |
| no-dismissing | PASS | PASS |
| Negative tests | 4/4 clean |
All N tests passed.
If any test failed, show which phrase and rule failed and stop there.