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 skills add louisbrulenaudet/monorepo-template --skill run-appgit clone --depth 1 https://github.com/louisbrulenaudet/monorepo-templateWrote 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/skills/louisbrulenaudet/monorepo-template/run-app)<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/run-app"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/run-app/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/run-app"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/run-app.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00109 | $0.02078 |
| Opus 5.5 | $0.00044 | $0.00831 |
| Sonnet 5.5 | $0.00022 | $0.00416 |
| Haiku 4.5 | $0.00011 | $0.00208 |
Grade A, and why
run-app scanned grade A 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 11d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Inside the Claude Code sandbox this loop needs `sandbox.network.allowLocalBinding` and two settings `env` entries: a sandbox-writable `CLOUDFLARE_REGISTRY_PATH` (cf's dev registry, which it also hands to Wrangler and Min How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run and verify the apps
Run everything from the repository root. The smoke script discovers apps from apps/*/package.json (monorepo.role, monorepo.healthPath, monorepo.devPort), so a new app is covered without editing it.
Local loop
-
Start each dev server as its own background Bash task (never a bare
&). Both scripts arecf dev, which runs Vite:pnpm --filter=worker-api dev- ready when Vite printsLocal: http://localhost:8700/pnpm --filter=front-app dev- ready when Vite printsLocal: http://localhost:5174/
Wait with one capped
until grep -q 'localhost:<port>' …; do sleep 0.5; doneon each task's output file. If the SessionStart context reported a port as already listening, reuse that server instead of starting a second one. -
node .github/actions/lib/smoke.mjs --traces- every line must readok.--tracesprints the latest requests the gateway captured, newest first. -
Browser check (the SPA is only verified once it has rendered):
pnpm exec playwright-cli open http://localhost:5174 pnpm exec playwright-cli snapshot # Stack check card: status, version, latency, request id pnpm exec playwright-cli console error # expect no errors pnpm exec playwright-cli requests # /api/v1/health returned 200; an earlier [FAILED] net::ERR_ABORTED is StrictMode cancelling the first signal-bound fetch pnpm exec playwright-cli closeAlways type the
pnpm exec playwright-cliprefix. The binary is a repo devDependency and is not onPATH, and that exact prefix is whatsandbox.excludedCommandslets out of the sandbox: Chrome cannot start inside it. Nevercd, pipe, or redirect it, and chain steps with plain&&only: any other form runs it sandboxed, where it fails withEPERMon~/Library/Caches/ms-playwright/daemonor loses the session; read--raw/--jsonoutput from stdout instead. The upstreamplaywright-cliskill documents every other command - apply the same prefix to its examples. If the browser is missing on a new machine:pnpm exec playwright-cli install-browser chromium. -
Stop both background tasks when done.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago Changed · +19 lines 4658ce712d31
- 16d ago Changed e13c7b62bbb5
- 18d ago Changed d6dcd5c04839
- 19d ago Changed 6be8eea8b8dd
- 21d ago First seen · 53 lines · 109 tokens per session scan A 6dca0f978548
run-app is a skill published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed today), licensed Apache-2.0. It adds 109 tokens to every session and 2,078 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-28.
Other skills, from other repositories
Edge Computing Testing
Testing edge computing deployments including latency verification, edge function testing, CDN worker testing, and geo-distributed test execution.
testing-pyramid
Test Distribution Analysis Command 🧪.
visual-testing-loop
Automated visual testing closed-loop workflow. Use when building or iterating on frontend interfaces - automatically generates, serves, screenshots, analyzes, and iterates until quality criteria are met. Eliminates manual visual verification.
resume-ai-validator
A command-line tool for testing ResumeAI, a service that analyzes and improves résumés. It checks both the service's API and the user interface through complete user journeys.
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
mobile-automation
Control Android and iOS devices, emulators and simulators — launch apps, tap, swipe, type, take screenshots, read the accessibility tree. Use when a task involves a mobile device or app, mobile UI testing, or reproducing a bug on a phone.