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 commands/kamiazya/scopes/rungit clone --depth 1 https://github.com/kamiazya/scopesWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00596 |
| Opus 5 | $0.00000 | $0.00298 |
| Sonnet 5 | $0.00000 | $0.00119 |
| Haiku 4.5 | $0.00000 | $0.00060 |
Grade A, and why
run scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Tests
Execute tests with the configured test-runner agent.
Usage
/testing:run [test_target]
Where test_target can be:
- Empty (run all tests)
- Test file path
- Test pattern
- Test suite name
Quick Check
# Check if testing is configured
test -f .claude/testing-config.md || echo "❌ Testing not configured. Run /testing:prime first"
If test target provided, verify it exists:
# For file targets
test -f "$ARGUMENTS" || echo "⚠️ Test file not found: $ARGUMENTS"
Instructions
1. Determine Test Command
Based on testing-config.md and target:
- No arguments → Run full test suite from config
- File path → Run specific test file
- Pattern → Run tests matching pattern
2. Execute Tests
Use the test-runner agent from .claude/agents/test-runner.md:
Execute tests for: $ARGUMENTS (or "all" if empty)
Requirements:
- Run with verbose output for debugging
- No mocks - use real services
- Capture full output including stack traces
- If test fails, check test structure before assuming code issue
3. Monitor Execution
- Show test progress
- Capture stdout and stderr
- Note execution time
4. Report Results
Success:
✅ All tests passed ({count} tests in {time}s)
Failure:
❌ Test failures: {failed_count} of {total_count}
{test_name} - {file}:{line}
Error: {error_message}
Likely: {test issue | code issue}
Fix: {suggestion}
Run with more detail: /testing:run {specific_test}
Mixed:
Tests complete: {passed} passed, {failed} failed, {skipped} skipped
Failed:
- {test_1}: {brief_reason}
- {test_2}: {brief_reason}
5. Cleanup
# Kill any hanging test processes
pkill -f "jest|mocha|pytest" 2>/dev/null || true
Error Handling
- Test command fails → "❌ Test execution failed: {error}. Check test framework is installed."
- Timeout → Kill process and report: "❌ Tests timed out after {time}s"
- No tests found → "❌ No tests found matching: $ARGUMENTS"
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 · 109 lines · 0 tokens per session scan A 5fe2ed591b89
run is a command published in the GitHub repository kamiazya/scopes (2 stars, last pushed 9mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 596 tokens. 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 commands, from other repositories
review.v1
Review code changes: /review [commit|branch|PR].
diagnose-deeptrace
Run a ZDX deep trace diagnostics session — start, analyze, or clean up deep traces for a user's device.
troubleshoot-user
Cross-product troubleshooting of user connectivity across ZCC, ZDX, ZPA, and ZIA.
audit-ssl
Audit ZIA SSL inspection rules -- list rules by action (INSPECT, DONOTINSPECT, DONOTDECRYPT, BLOCK), identify bypasses, and assess risk.
investigate-incident
Investigate security incidents using Z-Insights analytics -- threats, firewall actions, shadow IT, and web traffic.
create-access-rule
Create a ZPA access policy rule with v2 conditions for application access control.