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 CATWILLgh/MAINFRAME --skill mainframe-infrastructuregit 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-infrastructure)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-infrastructure"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-infrastructure/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/catwillgh/mainframe/mainframe-infrastructure"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-infrastructure.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 | $0.00036 | $0.01030 |
| Opus 5.5 | $0.00014 | $0.00412 |
| Sonnet 5.5 | $0.00007 | $0.00206 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
mainframe-infrastructure 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 14d 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.
- Raw HTTP calls must follow `mainframe-curl-requests`. How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infrastructure work
Operate only within the target and authority established by the current task. This skill does not grant permission to deploy, restart, delete, change data, expand access, or contact an unrelated environment.
Establish the target
- Resolve the project root from version control, using the working directory only when no repository exists.
- If
.agents/infrastructure.jsonexists, read it as a non-secret orientation map. It is neither live state nor authority. - Resolve the exact environment, platform instance, and resource. Stop on an ambiguity that could affect infrastructure or data.
- Read only project references applicable to the requested operation. Reject stale, missing, or project-escaping reference paths instead of guessing.
- Resolve credential names through the configured credential index and
use
mainframe-secretsfor value delivery.
Read infrastructure-map.md before creating or changing the map. Use infrastructure.example.json as a shape, never as evidence about a real project.
Establish current reality
The map provides orientation. Repository configuration and bounded live observations establish current state. Inspect the applicable Dockerfile, Compose, IaC, CI/CD, environment template, deployment, and runbook files. For a remote task, perform only the smallest authorized read that distinguishes live state from stale documentation.
When verified reality conflicts with the map, reality controls the active task. Repair the map only when repository edits are in scope. Never refresh a verification date merely because a file was read.
Use current primary documentation for version-sensitive platform, CLI, configuration, database, and API behavior.
Load only the applicable branch
- Test-pipeline design, required checks, GitHub Actions or GitLab CI: load
mainframe-testingfor its CI references. Keep runner provisioning and live deployment ownership here.
What ships with it
13 files 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.
- assets/infrastructure.example.json 765 B
- references/containers.md 1.7 KB
- references/data-stores.md 1.8 KB
- references/dokploy.md 2.4 KB
- references/dokploy/applications.md 1.2 KB
- references/dokploy/backups.md 1.3 KB
- references/dokploy/compose.md 1.1 KB
- references/dokploy/databases.md 1.2 KB
- references/dokploy/domains-tls.md 1.2 KB
- references/dokploy/safety.md 1.4 KB
- references/dokploy/servers.md 1.2 KB
- references/infrastructure-map.md 1.7 KB
- references/verification.md 1.6 KB
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.
- 14d ago Changed 931ccdfa9df9
- 15d ago Changed · +18 lines · +12 tokens per session f3bb04e6903b
- 20d ago Changed · -28 tokens per session 32ea991937e6
- 1mo ago Changed · -18 lines · -27 tokens per session 035741268ed9
- 1mo ago First seen · 103 lines · 79 tokens per session scan A 766cf9b8518c
mainframe-infrastructure is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 8d ago), licensed MIT. It adds 36 tokens to every session and 1,030 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
devops
CI/CD, container orchestration, cloud architecture, monitoring, infrastructure security, and platform automation skills. Docker, Kubernetes, Terraform, GitHub Actions. Triggers on: CI/CD, Docker, Kubernetes, Terraform, deploy, monitoring, infra, GitOps, observability, SRE.
ci-debug-workflow
Debug failing CI pipelines, containers, and reproduce bugs locally. Use when CI is red, containers won't start, or need to reproduce bugs.
github-actions-templates
Create production-ready GitHub Actions workflows for automated testing, building, and deploying applications. Use when setting up CI/CD with GitHub Actions, automating development workflows, or creating reusable workflow templates.
devops-engineer
Creates Dockerfiles, configures CI/CD pipelines, writes Kubernetes manifests, and generates Terraform/Pulumi infrastructure templates. Handles deployment automation, GitOps configuration, incident response runbooks, and internal developer platform tooling. Use when setting up CI/CD pipelines, containerizing…
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.