Borrowing it
Nothing to install: this file belongs to skills/agentic-workflows-that-read-the-room. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/skills/agentic-workflows-that-read-the-room/main/.github/prompts/manage-mona-site.prompt.mdgit clone --depth 1 https://github.com/skills/agentic-workflows-that-read-the-roomWrote 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/commands/skills/agentic-workflows-that-read-the-room/manage-mona-site)<a href="https://agentmods.dev/commands/skills/agentic-workflows-that-read-the-room/manage-mona-site"><img src="https://agentmods.dev/badge/commands/skills/agentic-workflows-that-read-the-room/manage-mona-site/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/commands/skills/agentic-workflows-that-read-the-room/manage-mona-site"><img src="https://agentmods.dev/badge/commands/skills/agentic-workflows-that-read-the-room/manage-mona-site.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 | $0.00022 | $0.00421 |
| Opus 5 | $0.00011 | $0.00211 |
| Sonnet 5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
manage-mona-site 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 5d 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.
What it actually says
Manage Mona's Astro site
Manage the Astro website in the site/ directory for this repository.
Inputs
- The first argument should be one of:
start,stop, orrestart. - Use port
4321unless I explicitly provide another port.
Shared rules
- Only act inside this repository.
- Use host
0.0.0.0when starting the site so it works locally and in GitHub Codespaces. - Only stop a process when you have the exact PID.
- Never use
pkill,killall, or other name-based process termination. - If a process on the requested port does not appear to be this repository's Astro site, stop and ask me before killing it.
Behavior
If I ask for start
- Check whether the site is already running on the requested port.
- If it is already this Astro site, tell me it is running and report the URL.
- Otherwise, start the Astro dev server from
site/. - Verify the homepage responds over HTTP.
If I ask for stop
- Find the exact PID listening on the requested port.
- If nothing is listening, tell me the site is already stopped.
- If the listener is this Astro site, stop it.
- Verify the port is no longer listening.
If I ask for restart
- Find and stop the exact PID currently listening on the requested port, if any.
- Start the Astro dev server again from
site/. - Verify the homepage responds over HTTP.
Response format
- Keep the response short.
- Always say what action you took.
- If the site is running, include the exact URL to open.
- If you used a PID, mention it.
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.
- 5d ago First seen · 53 lines · 22 tokens per session scan A b7f9039e424e
manage-mona-site is a command published in the GitHub repository skills/agentic-workflows-that-read-the-room (70 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 421 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-10.
Other commands, from other repositories
fdk-react-create
Create a new Platform 3.0 React Meta app (default UI stack). Uses fdk create react-starter-template or react-meta skeletons with DEW components, metaConfig in manifest.json, and React Router.
debug-ui
Debug a UI issue end-to-end using browser telemetry evidence capture, DOM analysis, and root cause classification.
webperf
Run a web performance audit on a Blazor / ASP.NET Core front end via the web-performance-auditor persona.
fdk-react-migrate
Migrate an existing Platform 3.0 vanilla JS app to React Meta framework. Preserves server/config; adds metaConfig, DEW, React structure, and React Router.
test-feature
Test a React Native feature on the running simulator/emulator. Verifies UI, user flows, and internal state. Generates a persistent Maestro test file.
interactive-dev
Start a persistent interactive development session with natural language browser control, auto-error monitoring, and full dev tool access.