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/vertz-dev/vertz/full-testgit clone --depth 1 https://github.com/vertz-dev/vertzWhat 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 | $0.00417 |
| Opus 5 | $0.00000 | $0.00209 |
| Sonnet 5 | $0.00000 | $0.00083 |
| Haiku 4.5 | $0.00000 | $0.00042 |
Grade C, and why
full-test scanned grade C with 1 finding 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 today.
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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf ~/vertz-dev/vertz-benchmarks/packages/<pkg>/dist What it actually says
Run the full end-to-end validation suite to ensure nothing is broken across the entire project.
Execute the following steps in order, reporting results as you go:
1. Turbo Quality Gates (all packages)
Run from the repository root:
npx turbo run lint typecheck test build
Report: total tasks passed/total, any failures (note if pre-existing on main).
2. Integration Tests
Run from packages/integration-tests:
vtz test
Report: tests passed/total.
3. Task-Manager E2E (Playwright)
Run from examples/task-manager:
npx playwright test
Report: passed, flaky, failed, skipped counts.
4. Benchmarks E2E (Playwright)
The benchmarks app lives in the separate repo at ~/vertz-dev/vertz-benchmarks/.
Important: If the change touches @vertz/ui-compiler, @vertz/ui, @vertz/ui-server, or @vertz/cli, copy the updated dist first:
rm -rf ~/vertz-dev/vertz-benchmarks/packages/<pkg>/dist
cp -r packages/<pkg>/dist/ ~/vertz-dev/vertz-benchmarks/packages/<pkg>/dist/
Then run from ~/vertz-dev/vertz-benchmarks/benchmarks/vertz:
vtzx playwright test
Report: passed/total.
5. Summary Table
After all steps, produce a summary table:
| Suite | Result | Notes |
|---|---|---|
| Turbo quality gates | X/Y passed | ... |
| Integration tests | X/Y passed | ... |
| Task-manager e2e | X passed, Y flaky, Z failed | ... |
| Benchmarks e2e | X/Y passed | ... |
Flag any failure that is NOT pre-existing on main as a blocker that must be fixed before merging.
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.
- today First seen · 61 lines · 0 tokens per session scan C 2411318da02c
full-test is a command published in the GitHub repository vertz-dev/vertz (45 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 417 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.
Other commands, from other repositories
review-rules
Review the current diff against xmcp review standards.
adk-ts-starter-sync
Synchronize shared boilerplate content across all starter template READMEs in apps/starter-templates//README.md.
adk-ts-changelog
Generate changelog entries and community release notes for ADK-TS from git history and changesets.
adk-ts-docs-audit
Audit the ADK-TS monorepo documentation for consistency issues. Scan all READMEs, doc pages, and content files. Do NOT make any changes — only report findings.
triage
Triage Linear issue with comprehensive analysis.
release
Perform a full release: generate release notes, bump version, commit, tag, and push.