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 joao-aires/agent-skills-public --skill ai-operationsgit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/ai-operations)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/ai-operations"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-operations/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/joao-aires/agent-skills-public/ai-operations"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/ai-operations.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 | $0.01055 |
| Opus 5.5 | $0.00022 | $0.00422 |
| Sonnet 5.5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
ai-operations 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 yesterday.
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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operate AI capabilities against user outcomes
Use the accepted task, architecture, authority and operating constraints. This method owns AI-specific operational decisions and evidence, not SDK initialization, a monitoring vendor or all incident/deployment procedures. Reuse established service operations and seek relevant reliability, capacity, security or delivery expertise when available; absence does not remove responsibility for the affected outcome. Planning an operating change does not authorize live mutation or data export.
Define meaningful operating signals
Begin at the user task and follow the work needed to finish it. Record enough to tell whether the request was admitted, the model responded, a tool acted, and the intended result was completed. These events can disagree: a provider response may be valid while the task fails, and a timeout may occur after a tool effect has already committed.
Use that separation to choose operating signals. Measure delays where they arise, preserve the identity of unfinished work, and distinguish execution failure from a quality judgment about a completed result. This makes it possible to diagnose a regression without treating every poor answer as a provider outage.
- Relate success/failure, latency and freshness to the actual user journey.
- Define useful denominators, time windows and candidate or approved targets; do not promise an SLO or quality threshold without acceptance.
- For interactive work, distinguish first useful output, full completion and interruption/cancellation behavior.
Make the deployed application, model/provider, prompt, tool/skill, retrieval/corpus and protocol configuration revisions identifiable. Correlate request/task, model, retrieval, tool and delegated work through supported execution context; retain gaps for opaque remote peers rather than inventing a complete trajectory. Choose signal detail and sampling for the decisions they support, including the risk of missing rare consequential failures.
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.
- yesterday Changed · +21 lines 3e5f960116d4
- 2d ago First seen · 46 lines · 55 tokens per session scan A 0bebe37e572c
ai-operations is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,055 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 2026-10-20.
Other skills, from other repositories
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
foundry-config-setup
Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.
google-cloud-solution-agentic-analytics-spark-knowledge-catalog
Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…
training-check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
nemo-automodel-launcher-config
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…