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 MLOps-Courses/agentops-open-course --skill agentops-coursegit clone --depth 1 https://github.com/MLOps-Courses/agentops-open-courseWrote 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/mlops-courses/agentops-open-course/agentops-course)<a href="https://agentmods.dev/skills/mlops-courses/agentops-open-course/agentops-course"><img src="https://agentmods.dev/badge/skills/mlops-courses/agentops-open-course/agentops-course/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/mlops-courses/agentops-open-course/agentops-course"><img src="https://agentmods.dev/badge/skills/mlops-courses/agentops-open-course/agentops-course.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 | $0.00073 | $0.00623 |
| Opus 5.5 | $0.00029 | $0.00249 |
| Sonnet 5.5 | $0.00015 | $0.00125 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
agentops-course 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 29d 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentOps Patterns
Getting an agent to answer correctly once is a demo. AgentOps is keeping it correct, safe, affordable, and observable as it runs against real traffic. These skills are operational patterns extracted from one completed reference agent, each with a file you can read and a repeatable check or evidence path.
When to use
- You have built an agent and now have to operate it.
- You want to know which AgentOps skill covers a given concern.
- You want the worked, open-source reference behind these patterns.
The patterns
Each pattern is a sibling skill, named rather than linked: installing this skill alone puts no siblings on disk, so a relative path would be a dead link. Install one with npx skills add MLOps-Courses/agentops-open-course --skill <name>, or read them all at https://github.com/MLOps-Courses/agentops-open-course/tree/main/skills
agentops-telemetry— trace, meter, and log the agent with OpenTelemetry; content off by default.agent-guardrails— PII redaction, injection spotlighting, human approval on writes, a kill-switch.agent-resilience— deadlines, bounded retries, a circuit breaker, and a validated model fallback.agent-token-budget— per-session token ceilings and cost attribution.agent-least-privilege— split into least-privilege specialists so injection has nothing to call.agent-evaluation— deterministic validation gates plus model-backed trajectory, grounding, and cost evidence.agent-incident-response— the detect→triage→mitigate→review→prevent loop for the agent as a workload.
How they fit together
Build and instrument first (telemetry), harden the boundaries (guardrails, least privilege), bound the failure modes (resilience, token budget), collect behavior evidence (evaluation), and operate the running system (incident response) — feeding every real failure back into the smallest repeatable check or evidence path.
The full course
These patterns are distilled from the AgentOps Open Course, a free, open-source course that builds, evaluates, secures, deploys, and operates one production-shaped agent with an open-source stack (Google ADK, agentgateway, kagent, MLflow, OpenTelemetry, Prometheus, Grafana, Ollama). Repository: MLOps-Courses/agentops-open-course. Site: https://agentops-open-course.fmind.dev/
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.
- 29d ago Changed · -4 lines fe5f61d0faec
- 1mo ago First seen · 39 lines · 73 tokens per session scan A eac6822fbaec
agentops-course is a skill published in the GitHub repository MLOps-Courses/agentops-open-course (2 stars, last pushed yesterday), licensed MIT. It adds 73 tokens to every session and 623 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
skill-release-gate
Evaluate an Agent Skill bundle for structural integrity, trigger quality, artifact improvement, script correctness, safety, installed-tree integrity, and target-host portability before release.
migration-review
Review database migration files when a change adds or modifies paths under migrations/. Use it before merge to collect forward, rollback, locking, and data-safety evidence.
orchard-release
Check deployment evidence and recovery conditions.
mirrord-prev-env
Help users create and manage mirrord preview environments — running a modified service as an isolated pod in a shared Kubernetes cluster, scoped by an environment key and HTTP/queue traffic filtering, so teams can validate and review changes against real traffic without affecting live services. Use when a developer…
mirrord-operator
Help users install and configure the mirrord Operator for team/enterprise environments. Use when users ask about operator setup, Helm installation, cloud API key or license configuration, air-gapped/offline licensing, enabling features (queue splitting, DB branching, preview environments, multi-cluster), internal…
orchard-review
Review a release proposal.