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 skills/catwillgh/mainframe/mainframe-ops-app-server-safetynpx skills add CATWILLgh/MAINFRAME --skill mainframe-ops-app-server-safetygit clone --depth 1 https://github.com/CATWILLgh/MAINFRAMEWrote 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/catwillgh/mainframe/mainframe-ops-app-server-safety)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-ops-app-server-safety"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-ops-app-server-safety.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.01554 |
| Opus 5 | $0.00039 | $0.00777 |
| Sonnet 5 | $0.00016 | $0.00311 |
| Haiku 4.5 | $0.00008 | $0.00155 |
Grade A, and why
mainframe-ops-app-server-safety 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 6d 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.
This is a copy
94% identical to ops-app-server-safety — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Server safety: no duplicate long-running processes
A preflight before launching dev servers, application processes, and container stacks. Discovery does not grant permission to stop a process or mutate a Compose project; use only the authority supplied by the active task.
Rule
Before launching a long-running process, establish its expected working directory, command or Compose project, and port or service when known. Reuse an already-running matching instance unless the task requires a restart or a configuration/image change. Never stop a process merely because its name or port looks similar.
Preflight — native processes
Applies to: dev servers like vite, next dev, nodemon, uvicorn, gunicorn, flask run, rails s, custom application servers.
-
Check the port if known.
- macOS / Linux:
lsof -nP -iTCP:<PORT> -sTCP:LISTEN - One line per visible listener with PID and command name. Empty output means no listener was visible at that instant; it is not durable ownership of the port.
- macOS / Linux:
-
Check the process by command (fallback or in addition).
- macOS / Linux:
ps -ef | grep -E 'vite|next dev|nodemon|uvicorn|gunicorn|flask run|rails s' | grep -v grep - If multiple projects on the host could host similar processes, disambiguate by working directory:
ps -o pid,command -p <PID>andlsof -p <PID> | grep cwd.
- macOS / Linux:
-
Prove ownership before acting. Confirm the PID's working directory and full command. A regex match alone may belong to another project or session. A project-provided PID file or process manager is valid evidence when the repository actually uses one.
Preflight — Docker Compose
Applies to any docker compose up invocation.
- Resolve the intended Compose file, project name, and working directory. Do not let an incidental current directory select the target.
- Check existing containers for this compose project.
- Run the resolved project command with
ps --status running --services. - One or more service-name lines means those services are running. The default table output is not a valid emptiness check because it includes a header even when there are no matching containers.
- Run the resolved project command with
- Choose by intended change.
- No restart or configuration change: use the running services.
- Restart with unchanged Compose configuration: use
docker compose restart [SERVICE...]. - Changed configuration or image: use
docker compose up -d [SERVICE...]with the project's normal build or pull policy. Compose reconciles changed services;restartdoes not apply configuration changes. - Use
docker compose downonly when removal of the project's containers and networks is explicitly intended. It is not the default restart primitive.
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.
- 6d ago First seen · 131 lines · 78 tokens per session scan A b47679b65bca
mainframe-ops-app-server-safety is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 1,554 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to ops-app-server-safety, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
docker
You are working with Docker. Apply these conventions.
devops-cicd
Build robust CI/CD pipelines with GitHub Actions, Docker containers, infrastructure as code, deployment strategies (blue-green, canary), and monitoring. Automate everything from commit to production.
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
deploy-docker-compose
Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…
coding-agents-hooks-authoring
To author, register, and test Rosetta hooks, add a SemanticKind, or debug a hook that won't fire.
openai-docs
Use when the user asks how to build with OpenAI products or APIs, asks about Codex itself or choosing Codex surfaces, needs up-to-date official documentation with citations, help choosing the latest model for a use case, latest/current/default-model prompting guidance, or model upgrade and prompt-upgrade guidance; use…