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-collaborationnpx skills add MLOps-Courses/mlops-coding-skills --skill mlops-collaborationgit 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-collaboration)<a href="https://agentmods.dev/skills/mlops-courses/mlops-coding-skills/mlops-collaboration"><img src="https://agentmods.dev/badge/skills/mlops-courses/mlops-coding-skills/mlops-collaboration.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 | $0.00050 | $0.01484 |
| Opus 5 | $0.00025 | $0.00742 |
| Sonnet 5 | $0.00010 | $0.00297 |
| Haiku 4.5 | $0.00005 | $0.00148 |
Grade A, and why
mlops-collaboration 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MLOps Collaboration
Goal
To transform a private project into a public, collaborative resource by establishing Governance (License, Code of Conduct, branch rulesets), Documentation (README, AGENTS, Contributing), Standardization (Templates, Workstations), and Release Management.
Prerequisites
- Language: Python 3.14
- Platform: GitHub
- Context: Open sourcing or team collaboration.
Instructions
1. Repository Governance
Set the rules of engagement.
- License: Pick an SPDX identifier and commit the full text. Declare it in
pyproject.tomlaslicense = "MIT"pluslicense-files = ["LICENSE.txt"](PEP 639), and make sure the file itself carries its title and copyright line — a bare license body with noCopyright (c) <year> <author>is legally ambiguous. - Code of Conduct: Add
CODE_OF_CONDUCT.mdto foster a safe community. - Branch Protection (concretely): commit
.github/rulesets/main.jsonand apply it withmise run install:rulesets. A ruleset in the repository is reviewable, diffable, and restorable; a setting clicked in the web UI is none of those. A useful baseline blocks deletion and non-fast-forward pushes, requires linear history, requires a pull request, and requires the CI status check to pass.- Make the task idempotent: look the ruleset up by name and
PUTover it when it exists,POSTonly when it does not. A plainPOSTcreates a duplicate ruleset on every run. - The required status check must name the CI job id exactly. If you rename the job, the ruleset waits forever for a context that no longer reports.
- Make the task idempotent: look the ruleset up by name and
- Review: Automate preliminary reviews with tools like Gemini Code Assist (
.gemini/config.yaml). - Ignore: Comprehensive
.gitignore(exclude secrets, data, virtualenvs, and local MLflow state such asmlflow.dbandmlartifacts/).
2. Comprehensive Documentation
Make the project usable and understandable.
- README.md: The landing page for humans (Badges, Hook, Quickstart, commands).
- AGENTS.md: The landing page for AI assistants — project overview, setup and core commands, definition of done, conventions and idioms, repository layout, in that order. Keep both files in sync with reality; when a command changes, both change in the same commit.
- Describe the real stack: state the versions a newcomer will actually install — Python 3.14, MLflow 3.15 on a SQL tracking store (
sqlite:///mlflow.dblocally, not the deprecated file store), Ruff 0.16,ty0.0.69,uv,mise. A README that documents last year's stack costs more time than no README. - MkDocs: Use for full documentation sites (API ref, tutorials) when
README.mdgets too long. - CONTRIBUTING.md: Guide for developers — environment setup, branch naming, PR process, and the exact local gate (
mise run all) they must pass before opening a pull request. - CHANGELOG.md: Generate from Conventional Commits with
git-cliff(replaces Commitizen); commit the rendered file.
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 · 79 lines · 50 tokens per session scan A 1ca655c2e24a
mlops-collaboration is a skill published in the GitHub repository MLOps-Courses/mlops-coding-skills (22 stars, last pushed 25d ago), licensed MIT. It adds 50 tokens to every session and 1,484 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
repo-recap
Generate a comprehensive repo recap (PRs, issues, releases) for sharing with team. Pass "en" or "fr" as argument for language (default fr).
finishing-a-development-branch
当实现完成、所有测试通过、需要决定如何集成这份工作时使用.
release-archivist
Close out a spec-superflow change with verification, summary, and archive readiness. Invoke when implementation is complete, verification is underway, or the user asks for a final wrap-up.
codex-issue-coordinator
Coordinates a large batch of GitHub issues through separate Codex worker threads, tested pull requests, review loops, and gated merges. Use when the user asks one Codex thread to manage several coding sessions or complete a parent issue, milestone, or issue batch.
context-mode-ops
Manage context-mode GitHub issues, PRs, releases, and marketing with parallel subagent army. Orchestrates 10-20 dynamic agents per task. Use when triaging issues, reviewing PRs, releasing versions, writing LinkedIn posts, announcing releases, fixing bugs, merging contributions, validating ENV vars, testing adapters…
t-prd
Create or update draft PRD and user stories for a feature.