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-contractsWrote 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-contracts)<a href="https://agentmods.dev/skills/j4flmao/agent-skills/data-contracts"><img src="https://agentmods.dev/badge/skills/j4flmao/agent-skills/data-contracts.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 | $0.00109 | $0.04634 |
| Opus 5 | $0.00055 | $0.02317 |
| Sonnet 5 | $0.00022 | $0.00927 |
| Haiku 4.5 | $0.00011 | $0.00463 |
Grade A, and why
data-data-contracts 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 — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Data Contracts
Purpose
Design and enforce data contracts between producers and consumers covering schema, semantics, SLA, ownership, versioning, and compatibility — with automated enforcement in CI/CD pipelines.
Agent Protocol
Trigger
Exact user phrases: "data contract", "data agreement", "schema contract", "producer consumer", "schema evolution", "compatibility", "data SLA", "dbt contracts", "data product contract", "contract testing", "breaking change schema".
Input Context
- Data producers (source systems, pipelines, data products)
- Data consumers (analysts, ML models, dashboards, downstream systems)
- Current schema management approach
- Data platform and transformation tools
- Compliance and governance requirements
Output Artifact
Data contract specification with schema, SLA terms, ownership; CI/CD enforcement pipeline with compatibility checks; versioning strategy.
Response Format
# Contract schema definition
# Semantic type definitions
# SLA configuration
# CI/CD enforcement pipeline
# Version compatibility matrix
No preamble. No postamble. No explanations. No filler/hedging/transitions. Compress output — why use many token when few do trick.
Completion Criteria
- Contract schema defined with columns, types, constraints
- Semantic types documented per field
- SLA terms defined (freshness, volume, quality)
- Ownership and escalation assigned
- Contract versioning scheme established
- CI/CD enforcement pipeline configured
- Schema compatibility checks automated
- Breaking change detection and notification workflow
Max Response Length
350 lines of configuration.
Workflow
Step 1: Define Contract Schema
contract:
version: "1.2.0"
dataset: analytics.fct_orders
schema:
columns:
- name: order_id
type: STRING
required: true
unique: true
semantic_type: ORDER_ID
tags: [PII, FINANCIAL]
- name: customer_id
type: STRING
required: true
semantic_type: CUSTOMER_ID
- name: total_amount
type: DECIMAL(18,2)
required: true
semantic_type: MONETARY_VALUE
constraints:
minimum: 0
maximum: 100000
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/contract-definition.md 4.1 KB
- references/contract-enforcement.md 4.9 KB
- references/contract-examples.md 3.7 KB
- references/contract-integration-patterns.md 5.0 KB
- references/contract-lifecycle-management.md 901 B
- references/contract-migration-strategies.md 5.5 KB
- references/contract-monitoring-enforcement.md 913 B
- references/data-contracts-governance.md 13 KB
- references/data-contracts-schema-evolution.md 14 KB
- references/schema-evolution-policies.md 4.1 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.
- 4d ago First seen · 538 lines · 109 tokens per session scan A 9aaeaf8b3f2a
data-data-contracts is a skill published in the GitHub repository j4flmao/agent-skills (22 stars, last pushed yesterday), licensed MIT. It adds 109 tokens to every session and 4,634 once invoked, about $0.0005 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
eval-loop
Conduct a local Publisher evaluation loop in five steps: scrape/run, eval, diagnose, improve, checkpoint. You are the conductor: import cases into the file ledger, spawn a blind answerer, then run eval-answer, eval-diagnose, and eval-improve. Persistence is plain files under the model package's evals/ directory…
eval-improve
Make the smallest safe Malloy model edit that closes a diagnosed model-owned gap, with a probe receipt for every factual claim. Use after eval-diagnose, or when asked to fix a model so an agent can discover the right answer. Never accepts its own edit; the acceptance check belongs to eval-loop. Does not decide whether…
eval-judge
Decide whether ONE answer matches its golden, and say whether you believe the golden. Read this before emitting any verdict. Covers containment, column pairing, nearmatch, refusals, and the goldstatus judgement. Use when scoring an attempt in an evaluation run; never to conduct a run (eval-loop), diagnose a failure…
eval-diagnose
Diagnose why a scored answer failed and who owns the fix, then cluster the failures by shared root cause. Walk dataset, agent-call, getcontext/model, getcontext/retrieval, construction, then model-definition. Append issue events to the file ledger, linked by traceId, one per cluster. Use after eval-answer, when…
eval-answer
Score one analytical answer against a verified golden, and score which of the entities the golden depends on retrieval delivered to the answerer. Run the contamination checklist, re-execute the submitted query yourself, then spawn a judge subagent per skill:eval-judge. Append attempt, toolcall, score, and…
data-mesh-expert
Expert-level data mesh architecture, domain-oriented ownership, data products, federated governance, and self-serve platforms. Use when the user mentions architecture, domain driven, data products, governance, or platform, or when the task involves Data Mesh Principles, Domain-Oriented Data Ownership, Data as a…