Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/j4flmao/agent-skillsnpx agentmods add skills/j4flmao/agent-skills/data-versioningWrote 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/j4flmao/agent-skills/data-versioning)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/data-versioning"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-versioning/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/j4flmao/agent-skills/data-versioning"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-versioning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00119 | $0.05978 |
| Opus 5 | $0.00060 | $0.02989 |
| Sonnet 5 | $0.00024 | $0.01196 |
| Haiku 4.5 | $0.00012 | $0.00598 |
Grade A, and why
data-data-versioning 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 8d 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 — 587 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Data Versioning
Purpose
Implement data versioning with DVC or LakeFS for reproducibility, branching, diff, rollback, and experiment tracking across data pipelines and ML workflows.
Agent Protocol
Trigger
Exact user phrases: "data versioning", "DVC", "LakeFS", "data lineage", "Git-like for data", "data reproducibility", "data branching", "data diff", "data snapshot", "experiment reproducibility", "data rollback", "data version control".
Input Context
- Data storage platform (S3, GCS, ADLS, MinIO)
- ML/analytics pipeline framework
- Existing Git workflow for code
- Team size and collaboration patterns
- Experiment tracking needs
- Compliance requirements for data lineage
Output Artifact
Data versioning strategy with DVC or LakeFS, branching model, experiment reproducibility workflow, data diff and rollback procedures.
Response Format
# Versioning tool selection
# Branching model
# DVC/LakeFS configuration
# Experiment tracking setup
# Data diff + rollback workflow
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Versioning tool selected (DVC vs LakeFS) with rationale
- Branching model defined for data development
- DVC or LakeFS configured with remote storage
- Data diff and rollback procedures documented
- Experiment reproducibility workflow established
- Data lineage tracked from source to output
- CI/CD integration for data versioning
Max Response Length
350 lines of configuration.
Workflow
Step 1: Select Versioning Tool
| Tool | Best For | Model | Storage |
|---|---|---|---|
| DVC | ML experiments, small-medium data, file-based | Pointer files in Git | S3/GCS/SSH/local |
| LakeFS | Large data lakes, production pipelines, tabular data | Git-like semantics on object store | S3/GCS/ADLS |
Default: DVC for ML/experimentation workflows (datasets up to 100GB). LakeFS for enterprise data lakes, large-scale pipelines, and production branching. Use both if ML + data lake.
What ships with it
10 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.
- references/data-versioning-branching.md 3.0 KB
- references/data-versioning-delta-lake.md 17 KB
- references/data-versioning-gc-retention.md 3.2 KB
- references/data-versioning-lineage-tracking.md 15 KB
- references/data-versioning-strategy.md 920 B
- references/data-versioning-tools.md 3.2 KB
- references/delta-lake-time-travel.md 901 B
- references/dvc-patterns.md 3.4 KB
- references/lakefs-patterns.md 6.0 KB
- references/nessie-iceberg-versioning.md 4.3 KB
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.
- 8d ago First seen · 587 lines · 119 tokens per session scan A feb8ee3ff084
data-data-versioning is a skill published in the GitHub repository j4flmao/agent-skills (23 stars, last pushed 6d ago), licensed MIT. It adds 119 tokens to every session and 5,978 once invoked, about $0.0006 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 2026-09-03.
Other skills, from other repositories
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
resolver
Git merge conflicts - resolve without losing intent.
release-management
Automates GitHub releases with semantic versioning, changelog generation from merged PRs, and gh CLI integration. Supports draft, prerelease, and standard release workflows with task-tracked multi-phase execution. Use when creating releases, tagging versions, or publishing changelogs.
github-release-management
Comprehensive GitHub release orchestration with AI swarm coordination for automated versioning, testing, deployment, and rollback management.
lakefs-versioning
Use when lakeFS data versioning — Git-like branching for data lakes, atomic commits, time travel, CI/CD. Use when working with lakefs versioning.
cargo-release
PM-invocable protocol for Cargo publish and release operations in the trusty-tools Rust monorepo: semver rules, 10-step release sequence, macOS codesign safety, and cross-crate dependency ordering.