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-self-monitoringgit 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-self-monitoring)<a href="https://agentmods.dev/skills/catwillgh/mainframe/mainframe-self-monitoring"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-self-monitoring/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-self-monitoring"><img src="https://agentmods.dev/badge/skills/catwillgh/mainframe/mainframe-self-monitoring.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 | $0.00055 | $0.00620 |
| Opus 5.5 | $0.00022 | $0.00248 |
| Sonnet 5.5 | $0.00011 | $0.00124 |
| Haiku 4.5 | $0.00006 | $0.00062 |
Grade A, and why
mainframe-self-monitoring 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Embedded system diagnostics
Build a useful operator view in the receiving application's stack and design system. Start with observation; add container mutations and data browsing only where the requested product needs them and their separate permissions are defined. Do not automatically install Docker access, database explorers, a metrics platform or a different frontend/backend framework. This method is not a replacement for external monitoring: a failed application cannot reliably report its own outage.
Inspect existing health checks, telemetry, identities, tenants, resource ownership, deployment and operator workflows. Establish the exact target environment and which users may see each class of information. Reuse current instrumentation, clients and authorization. Development authority does not grant permission to restart production resources, delete images, browse unrelated data or expose a privileged daemon socket.
Read for the current decision
- Signals: bounded collection, health semantics, freshness, units, missing data and failure isolation.
- Docker and Compose: optional runtime adapter, actual target identity, scope enforcement, actions and configuration display.
- Data previews: optional PostgreSQL, Redis and Kafka inspection with explicit cost, disclosure and access boundaries.
- Interface and verification: operator journey, truthful actions, tests and actual UI/runtime acceptance.
Use the relevant backend/frontend engineering method and mainframe-testing for
implementation checks. Use mainframe-infrastructure for actual platform access
or changes, mainframe-k3s for Kubernetes operations and mainframe-clickhouse
for that database's query safety. Use mainframe-notifications only if this work
also requires event-driven outbound alerts.
Complete the slice
Define a small typed server contract for each enabled capability: authorized resource identity, observation time, freshness, status, optional value/unit and safe error. Enforce authorization and resource scope server-side for every request, including direct IDs and background jobs. UI visibility is not a guard. Separate metadata, logs/data and mutations; an authenticated account is not sufficient permission for host-wide information.
What ships with it
4 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.
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.
- 9d ago First seen · 58 lines · 55 tokens per session scan A 82a0dd2767b4
mainframe-self-monitoring is a skill published in the GitHub repository CATWILLgh/MAINFRAME (2 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 620 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-07.
Other skills, from other repositories
minions
PM Ops — orchestrator of the minions AI subagent team. Single entry point: decomposes requests, delegates to minions- subagents in parallel or sequence, aggregates output.
optimize-goal
Use when the user wants to review, critique, tighten, or enhance an existing goal.md file (a written spec/prompt authored for a /goal command instead of typed into chat) before it gets executed — including requests like "review this goal.md", "enhance my goal.md", "optimize this goal", or sharing a goal.md file and…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cmux-architecture
Skill "cmux-architecture" from manaflow-ai/cmux, covering cmux architecture, package architecture, layers, file organization and documentation.