data-contract

A written agreement for a dataset, database table, file feed, or event stream that explains its fields, quality promises, owner, allowed changes, and personal-data classification.

In plain words
What is it for?
Use it to document data shared between teams, with partners, or with machine-learning models. It helps define field meanings, units, allowed values, freshness, completeness, validity, and schema changes.
Why use it?
It prevents downstream users from silently relying on data whose meaning, timing, or quality has changed. It also makes it clear who is responsible and which changes would break users.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/sananthanarayan/skilldrop/data-contract
Any agent
npx skills add sananthanarayan/skilldrop --skill data-contract
Clone the repo
git clone --depth 1 https://github.com/sananthanarayan/skilldrop

Made for: Claude Code, Codex.

Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,694 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00096 $0.01694
Opus 5 $0.00048 $0.00847
Sonnet 5 $0.00019 $0.00339
Haiku 4.5 $0.00010 $0.00169

Measured 2d ago against content hash 61fa57668f47, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

data-contract 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 2d 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.

skills/data-contract/SKILL.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

data-contract

Treats a dataset, table, or topic as a product with an owner and a guarantee — the agreement a producing team makes to everyone reading their data. Distinct from api-contract-draft (synchronous request/response + webhook interfaces): this governs data at rest and in motion — the warehouse table, the Kafka topic, the daily export — where the failure mode isn't a 500, it's a downstream model silently trained on a column whose meaning changed last Tuesday.

How to respond

  1. Establish producer, consumers, and the asset. What dataset (table / topic / file feed), who produces it, and who consumes it — because the consumer list is what makes a change "breaking". Ask at most 2 questions, spent on the asset's update mechanism (batch / streaming / CDC) and whether any consumer is outside the producing team's control (another team, a partner, a trained model). A dataset with unknown consumers can't have a contract — surfacing that is the first value.

  2. Specify schema with semantics, not just types. Types prevent crashes; semantics prevent silent wrongness. Every field gets: name, type, nullability, unit or allowed-values, and a one-line meaning. ✅ "amount — int64, not null, minor currency units (cents), the net charged after discounts" — ❌ "amount — integer" (cents or dollars? gross or net? the model that assumed dollars is now off by 100×). Mark every field's [required] vs [optional] and whether null is a valid value distinct from absent.

  3. Set quality guarantees as measurable SLAs (catalog in reference.md) — each with a threshold, a check, and a breach action:

    • Freshness — max acceptable lag ("partition for day D lands by 06:00 D+1")
    • Completeness — expected volume / no gaps ("row count within ±10% of trailing-7-day median; no missing partitions")
    • Validity — % rows passing field constraints ("≥99.9% of email rows match the format")
    • Uniqueness — the key that's actually unique ("event_id unique; duplicates are a contract breach, not a dedup hint")
    • Distribution — drift bounds on the columns consumers depend on ("country cardinality and null-rate within historical band") A quality SLA without a breach action ("page the producer" / "quarantine the partition" / "alert consumers") is a wish; name the action.

Read the full file on GitHub · 68 lines

Files

What ships with it

5 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.

Changes

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.

  1. 2d ago First seen · 68 lines · 96 tokens per session scan A 61fa57668f47

Subscribe to this mod's changes

data-contract is a skill published in the GitHub repository sananthanarayan/skilldrop (2 stars, last pushed 18d ago), licensed MIT. It adds 96 tokens to every session and 1,694 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 2026-08-31.

Related

Other skills, from other repositories

cognee-community

Use when the user needs something that ships outside cognee core — community database adapters (Qdrant, Milvus, Weaviate, Redis, Pinecone, FalkorDB, Memgraph, DuckDB, NetworkX, …), data-source connectors (Slack, Gmail, Notion, Confluence, Google Drive), custom tasks/pipelines/retrievers (Exa, ScrapeGraph, codify)…

topoteretes/cognee · 106 tokens

bigquery-ai-ml

Skill for BigQuery AI and Machine Learning queries using standard SQL and AI. functions (preferred over dedicated tools).

google/adk-python · 31 tokens

data-quality-frameworks

Implement data quality validation with Great Expectations, dbt tests, and data contracts. Use when building data quality pipelines, implementing validation rules, or establishing data contracts.

foryourhealth111-pixel/Vibe-Skills · 37 tokens

fabriciq-ontology-cli

Manages Fabric IQ Ontology items, including entity and relationship types, data bindings, and definition updates, plus schema, lineage, grounding, and graph-walk exploration. Use for ontology modelling and traversal. For natural-language questions over a Power BI report use fabriciq.

microsoft/skills-for-fabric · 60 tokens

lineage-diff

Compare column-level lineage between two versions of a SQL query to show added, removed, and changed data flow edges.

AltimateAI/altimate-code · 28 tokens

dbt-bigquery

Expert guidance for creating, modifying, and optimizing dbt pipelines for BigQuery. Use this skill whenever user asks for generating or modifying a dbt model or project. Activate this skill when the user - Creates, modifies, or troubleshoots dbt models or pipelines - Needs to optimize SQL within a dbt project - Is…

gemini-cli-extensions/data-agent-kit-starter-pack · 88 tokens