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/mlops-courses/mlops-coding-skills/mlops-observabilitynpx skills add MLOps-Courses/mlops-coding-skills --skill mlops-observabilitygit clone --depth 1 https://github.com/MLOps-Courses/mlops-coding-skillsWrote 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/mlops-coding-skills/mlops-observability)<a href="https://agentmods.dev/skills/mlops-courses/mlops-coding-skills/mlops-observability"><img src="https://agentmods.dev/badge/skills/mlops-courses/mlops-coding-skills/mlops-observability.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 | $0.00051 | $0.01335 |
| Opus 5 | $0.00026 | $0.00668 |
| Sonnet 5 | $0.00010 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00134 |
Grade A, and why
mlops-observability 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 4d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Observability
Goal
To implement a "Glass Box" system where every result is Reproducible, every asset has Lineage, and system health is Monitored, Alerted on, and Explained.
Prerequisites
- Language: Python 3.14
- Context: Production monitoring and debugging.
- Platform Suggestion: MLflow 3.15, SHAP, Evidently, ...
Instructions
1. Guarantee Reproducibility
Consistency is key. For instance:
- Randomness: Set seeds for
random,numpy,torch,tensorflow. - Dependencies:
uv.lockis the reproducibility mechanism for Python. It records the exact resolved version and hash of every direct and transitive dependency, anduv sync --frozeninstalls exactly that — the same set on a laptop, in CI, and in the image. - Tools:
mise.lockdoes the same job for the binaries that are not Python packages (dprint,gitleaks,trivy,actionlint,zizmor, ...), recording version, URL, and checksum per platform. Commit both lockfiles; between them, "works on my machine" stops being a category of bug. - Builds:
mise run buildis a plainuv buildproducing a wheel and an sdist. Its reproducibility comes from the locked inputs above, not from a build flag — do not expectuv buildto pin anything by itself. - Environment: Ship the same locked set into a
dockerimage (uv sync --frozen), so the runtime matches what was tested. - Code: Track the git commit hash for every run, and fail the pipeline on a dirty working tree so a run can always be traced back to a commit.
2. Track Data Lineage
Know the origin of your data. For instance:
- Datasets: Create MLflow Datasets with
mlflow.data.from_pandas. - Logging: Log inputs to MLflow context with
mlflow.log_input. - Store: Keep tracking and registry on a SQL backend (
sqlite:///mlflow.dblocally, Postgres or a tracking server in production). Lineage queries are relational queries; the deprecated file store cannot answer them and does not support the model registry at all. - Versioning: Version data files (e.g.,
data/v1.csv) or use DVC. - Transformations: Log preprocessing parameters mapping data versions to model versions.
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.
- 4d ago First seen · 97 lines · 51 tokens per session scan A b3acea9e1635
mlops-observability is a skill published in the GitHub repository MLOps-Courses/mlops-coding-skills (22 stars, last pushed 24d ago), licensed MIT. It adds 51 tokens to every session and 1,335 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
chinese-documentation
中文文档排版参考——中英文空格、全半角标点、术语保留、链接格式、中文文案排版指北约定。仅在用户显式 /chinese-documentation 时调用，不要根据上下文自动触发。.
chinese-git-workflow
国内 Git 平台配置参考——Gitee、Coding.net、极狐 GitLab、CNB 的 SSH/HTTPS/凭据/CI 接入差异与镜像同步配置。仅在用户显式 /chinese-git-workflow 时调用，不要根据上下文自动触发。.
chinese-code-review
中文 review 沟通参考——话术模板、分级标注（必须修复/建议修改/仅供参考）、国内团队常见反模式应对。仅在用户显式 /chinese-code-review 时调用，不要根据上下文自动触发。.
chinese-commit-conventions
中文 commit 与 changelog 配置参考——Conventional Commits 中文适配、commitlint/husky/commitizen 中文模板、conventional-changelog 中文配置。仅在用户显式 /chinese-commit-conventions 时调用，不要根据上下文自动触发。.
systematic-debugging
Skill "systematic-debugging" from jnMetaCode/superpowers-zh, covering 系统化调试, 概述, 铁律, 何时使用 and 四个阶段.
dispatching-parallel-agents
当面对 2 个以上可以独立进行、无共享状态或顺序依赖的任务时使用.