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 agents/callstackincubator/rozenite/metro-testinggit clone --depth 1 https://github.com/callstackincubator/rozeniteWhat 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 | $0.00312 |
| Opus 5 | $0.00000 | $0.00156 |
| Sonnet 5 | $0.00000 | $0.00062 |
| Haiku 4.5 | $0.00000 | $0.00031 |
Grade A, and why
metro-testing 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 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.
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.
What it actually says
Metro testing
- Metro-related changes (Metro config, middleware loaded by Metro, plugin
discovery, anything reachable from
metro.config.js) must be verified by actually running Metro inapps/playground(e.g.CI=1 pnpm --filter playground start), not just unit tests — Metro loads these packages as CJS, and build/test suites won't catch runtime failures like requiring an ESM-only dependency. - Watch Metro's startup log for errors (e.g.
ERR_REQUIRE_ESM) and confirm it reachesWaiting on http://localhost:8081before concluding the change is safe. packages/metro/src/__tests__/cjs-load.test.tsautomates the require-time half of this check: it spawns a realnodesubprocess (not Vitest's own module runner, which prefers each package'sdevelopmentexport condition and would silently mask the failure) torequire()the built@rozenite/tools/@rozenite/middleware/@rozenite/metroCJS bundles and runwithRozenite()end-to-end, exactly as Metro does. Run it withpnpm --filter @rozenite/metro run testafter building the packages it covers. It won't catch config-shape or bundling-time issues, so it doesn't replace running Metro for real inapps/playground.
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 · 21 lines · 0 tokens per session scan A 468bb7d21366
metro-testing is an agent published in the GitHub repository callstackincubator/rozenite (653 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 312 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 agents, from other repositories
debugger
Debugs errors, test failures, and unexpected behavior. Knows PromptScript architecture.
worktree-collaboration
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
issue-tracker
Predict issues and PRDs live in Consensys Jira.
domain
This document defines the canonical domain language for Vibelution so architecture work can use stable names for the same concepts. It is intentionally small: add terms when they become load-bearing in design or tests.
sdd-planner
Breaks a feature spec + design into atomic, ordered, testable tasks. Use AFTER spec.md and design.md exist and AFTER the researcher's report. Writes specs/ /tasks.md. Stack-agnostic.