DataChain is a Python library and data-processing system that turns files from cloud storage or local filesystems into typed, versioned datasets that can be queried and processed. Teams use it to build repeatable pipelines for unstructured data, with optional knowledge-base and agent features that help coding agents understand and work with those datasets. The catalogue entries connect agents to DataChain's data workflows.
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 datachain-ai/datachain --skill jobsgit clone --depth 1 https://github.com/datachain-ai/datachainWrote 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/datachain-ai/datachain/jobs)<a href="https://agentmods.dev/skills/datachain-ai/datachain/jobs"><img src="https://agentmods.dev/badge/skills/datachain-ai/datachain/jobs.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01075 |
| Opus 5 | $0.00019 | $0.00537 |
| Sonnet 5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00108 |
Grade A, and why
datachain-jobs 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are now loaded with the datachain-jobs skill. Maintain a jobs analytics file at dc-knowledge/jobs/index.md. Follow the 3-step flow below exactly.
Step 1 — Check Staleness
python3 {skill_dir}/scripts/jobs.py --plan
- If
"studio_available": false→ report theerrormessage and stop. - If
"up_to_date": true→ skip to Step 3. - If
"up_to_date": false→ continue to Step 2.
Step 2 — Fetch & Write
python3 {skill_dir}/scripts/jobs.py --fetch [--days N] [--limit N] [--enrich]
- Use
--days Nfrom the user's request if stated (e.g. "last 7 days" →--days 7). Default:--days 30. - Add
--enrichonly when the question requires duration, workers, or cluster data ANDenriched: falsein an existing index — tell the user it makes one API call per terminal job. - If the script fails → report the error and stop.
Write dc-knowledge/jobs/index.md using EXACTLY this format:
---
generated: <generated from script output>
days_covered: <days_covered>
total_jobs: <filtered_count>
failed_count: <failed_count>
complete_count: <complete_count>
running_count: <running_count>
other_count: <other_count>
enriched: <true|false>
duration_note: "Wall-clock duration (submit→finish). Null when enriched=false or job still running."
truncated: <true|false>
---
## Clusters
| Name | Cloud | Max Workers | Default |
|------|-------|-------------|---------|
| <name> | <cloud_provider> | <max_workers> | <yes if is_default else no> |
## Jobs
| Date | ID | Name | Status | User | Workers | Duration | Cluster | Python |
|------|----|------|--------|------|---------|----------|---------|--------|
| <created_display> | <id> | <name> | <status> | <created_by> | <workers> | <duration_str or —> | <cluster_name or —> | <python_version or —> |
Section rules:
- Omit
## Clustersif theclustersarray is empty. - Duration cell:
duration_strvalue (e.g."9000s") when known,—when null. - Workers: always a number (
workersfield, defaults to 1). - Cluster, Python: use
—when null. - Date column:
created_display(YYYY-MM-DD HH:MMUTC). - Rows: newest-first (already sorted by script).
- If
truncated: true, add after the table:_(Results truncated at <limit> jobs. Use --limit N for more.)_
What ships with it
3 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.
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 · 105 lines · 38 tokens per session scan A 63fa13826547
datachain-jobs is a skill published in the GitHub repository datachain-ai/datachain (2,819 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 1,075 once invoked, about $0.0002 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
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
last30Days
Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
comet-design
A workflow guide for turning an existing software change into a detailed technical design document. It builds on earlier proposal and design files and defines implementation risks, tests, and edge cases.
comet-hotfix
A quick workflow for fixing an existing bug in Comet, a tool that manages structured code changes. It moves through opening the change, building, checking, and archiving it.
comet-verify
Comet Phase 4: Verify and Close. Invoke with /comet-verify. Verify implementation matches design, handle development branch.