A skill your agent uses when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning.

Apache-2.0Auto-check passedData & Analytics

Install Data Contracts

skills CLI
$ npx skills add hashgraph-online/awesome-codex-plugins --skill data-contracts -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hashgraph-online/awesome-codex-plugins data-contracts --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hashgraph-online/awesome-codex-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/lsshym/wingman.ai/skills/data-contracts .claude/skills/data-contracts && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
data-contracts
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
843 words
Files
5 (incl. references)
Skills in repo
686
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning.

  • Works in 9 steps: Identify the source shape from real… → Identify the receiver contract: What… → Decide ownership and stability → …
  • Source data and receiving code may disagree on fields
  • SKILL.md covers When To Use, Required Contract Checkpoint, Decision Protocol and Example Use Rule, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Data Contracts is an agent skill from hashgraph-online/awesome-codex-plugins. Use when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning. Trigger for real data wiring, mock replacement, field/schema/type mismatch, snakecase/camelCase, 接口对接, 字段对齐, 类型对不上. Do not use for styling, copy, imports, or no-boundary renames.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files, including reference files (for example `references/anti-patterns.md`, `references/examples-python.md` and `references/examples-typescript.md`).

It sits in Data & Analytics, covering Data governance. The repository describes itself as: A curated list of awesome OpenAI Codex / ChatGPT plugins, skills, and resources. The 1 Codex Marketplace. See live plugins at: https://hol.org/plugins/best-codex-plugins. The licence is Apache-2.0.

When your agent uses it

  • Source data and receiving code may disagree on fields
  • Business meaning
  • Real data wiring
  • Mock replacement

Example prompts

  • “/data-contracts”

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Identify the source shape from real evidence: Use schemas, samples, fixtures, migrations, source code, docs, generated types, or runtime…
  2. Identify the receiver contract: What code, type, schema, handler, model, form, config object, component, or downstream data model receives…
  3. Decide ownership and stability
  4. If meanings are identical
  5. If meanings differ: keep concepts separate. Do not rename, cast, narrow, or map by guess just to make types compile. A source status is…
  6. If source data is missing: do not add fields to the source type, fake defaults, placeholder values, or guessed fallbacks. Use a real…
  7. Choose one binding location: direct source use, local alias, parser/schema, adapter/mapper, repository boundary, domain model, request…
  8. Keep the change scoped to the data boundary: no UI redesign, handler rewrite, config behavior change, domain behavior change, or unrelated…
  9. Verify: Use the project's smallest useful proof: focused test, typecheck, schema parse, sample payload, fixture, integration check…

What it can do on your machine

Read from SKILL.md and the folder at commit 78497e5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Data Contracts loads about 1.6k tokens when it runs, and up to ~4.4k if it reads all its reference files. Until then it costs about 78 tokens; SKILL.md has 843 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~78
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hashgraph-online/awesome-codex-plugins at commit 78497e5, republished under its Apache-2.0 licence (© hashgraph-online). 843 words, ~1,631 tokens.

Download SKILL.mdSave it as .claude/skills/data-contracts/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
data-contracts
description
Use when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning. Trigger for real data wiring, mock replacement, field/schema/type mismatch, snake_case/camelCase, 接口对接, 字段对齐, 类型对不上. Do not use for styling, copy, imports, or no-boundary renames.

Data Contracts

Use this skill when real source data must be connected to receiving code and the field names, structure, optionality, enum values, or business meaning may differ.

Core principle: align the smallest boundary that owns the meaning. Same meaning plus local receiver usually means direct source usage. Same meaning plus stable receiver usually means one boundary translation. Different meaning or missing source data must stay visible.

When To Use

Use this when connecting one boundary to another:

  • API or generated client response -> UI, service, request builder, or domain model.
  • Database row -> domain entity.
  • Event or webhook payload -> handler input.
  • SDK/vendor response -> internal app model.
  • Config/env/CLI input -> runtime options.
  • Form state -> request DTO or view contract.
  • AI structured output -> parser, schema, tool input, or downstream data model.
  • Legacy type -> new type.

Do not use this for pure formatting, styling, copy edits, or refactors with no boundary contract.

Contract alignment is not permission to redesign the receiver. Do not change UI layout, visible copy, interactions, handler behavior, config behavior, domain behavior, or unrelated code unless the contract decision requires it.

Required Contract Checkpoint

Before changing code for a non-trivial boundary, identify:

  • Source: actual supplied shape from schema, sample, fixture, migration, source code, docs, or runtime payload.
  • Receiver: receiving code shape, type, schema, DTO, handler, model, form, config object, or interface.
  • Owner/source of truth: which side owns the business meaning, and why.
  • Gap: naming-only, semantic mismatch, missing field, structural mismatch, enum/value mismatch, optionality mismatch, or source conflict.
  • Binding location: direct source use, local alias, parser/schema, adapter/mapper, repository boundary, domain model, request builder, event handler, component interface, or config parser.
  • Verification: focused test, typecheck, schema parse, sample payload, fixture, integration check, compile step, or render path.

Keep the checkpoint concise. Do not expose private chain-of-thought; report only concrete contract facts and decisions when useful.

Decision Protocol

Perform this analysis internally. Do not ask the user at each step. Ask only when semantic ownership, source of truth, or behavior-changing contract decisions cannot be resolved from code, memory, schemas, or docs.

  1. Identify the source shape from real evidence: Use schemas, samples, fixtures, migrations, source code, docs, generated types, or runtime payloads. Do not infer fields from the receiver.
  2. Identify the receiver contract: What code, type, schema, handler, model, form, config object, component, or downstream data model receives the source?
  3. Decide ownership and stability:
    • Memory or current domain truth wins.
    • Explicit schema/spec/docs win over guesses.
    • Existing project architecture wins when it clearly owns the boundary.
    • Local, temporary, single-page, display-only, or component-owned receivers are usually flexible.
    • Shared domain models, public APIs, persisted shapes, exported SDK types, config objects used by startup, and widely used app types are stable.
    • If changing a receiver would ripple through many call sites, treat it as stable unless the user asked for that migration.
  4. If meanings are identical:
    • Local/temporary/display/single-use receiver: change the receiver to use source fields directly, or use local aliasing. Do not add an adapter just to preserve naming style such as camelCase over snake_case.
    • Stable/shared/public/domain/persisted receiver: convert once at the boundary that already owns external input or cross-contract translation.
  5. If meanings differ: keep concepts separate. Do not rename, cast, narrow, or map by guess just to make types compile. A source status is not a receiver workflowKind unless evidence proves the same business meaning.
  6. If source data is missing: do not add fields to the source type, fake defaults, placeholder values, or guessed fallbacks. Use a real alternate source, explicit absence, validation failure, deliberate contract change, or user confirmation.
  7. Choose one binding location: direct source use, local alias, parser/schema, adapter/mapper, repository boundary, domain model, request builder, event handler, component interface, or config parser. Avoid scattered call-site mapping.
  8. Keep the change scoped to the data boundary: no UI redesign, handler rewrite, config behavior change, domain behavior change, or unrelated refactor unless the contract decision requires it.
  9. Verify: Use the project's smallest useful proof: focused test, typecheck, schema parse, sample payload, fixture, integration check, compile step, or render path.
Show full SKILL.md (176 more words)Show less

Example Use Rule

If concrete code shape is needed after the checkpoint, read references/examples.md, then at most one matching language example.

Examples demonstrate boundary handling style: source shape, receiver shape, validation, explicit errors, and a focused verification.

Do not copy example domains, field names, enum values, architecture, or language into the project unless they match the existing code. Always follow the project's actual language, libraries, and patterns.

Do not write pseudocode into project files.

Ask The User When

  • Both sides use different terms that may represent different business concepts.
  • The change would alter a public API, stable domain model, persisted schema, or existing behavior.
  • No memory, docs, schema, fixture, code ownership pattern, or architecture identifies the source of truth.
  • You cannot tell whether the receiver is local/temporary or shared/stable.
  • The source lacks data for a distinct receiver concept.
  • Adding an adapter layer would be an architectural decision and the project has no precedent.

Common Mistakes

Read references/anti-patterns.md when fixing type errors, replacing mock data, mapping source fields, handling missing data, guessing aliases, or resolving enum/status/price/permission fields.

© hashgraph-online, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (references) in plugins/lsshym/wingman.ai/skills/data-contracts of hashgraph-online/awesome-codex-plugins.

  • SKILL.md
  • references/anti-patterns.md
  • references/examples-python.md
  • references/examples-typescript.md
  • references/examples.md

Open the folder on GitHubat commit 78497e5

Compare with similar skills

Data Contracts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Data Contracts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Data Contracts this skillhashgraph-online/awesome-codex-plugins1.2k—~1.6kAutomated safety check: PassApache-2.0
Jeecg Systemjeecgboot/skills239—~3.2kAutomated safety check: PassApache-2.0
Openalgo Chart Indicatormarketcalls/openalgo-charts140—~3.4kAutomated safety check: NotesApache-2.0
Data Quality Frameworkswshobson/agents40k11 repos~1.1kAutomated safety check: PassMIT
Tracing Downstream Lineageastronomer/agents4511 repos~1.2kAutomated safety check: PassApache-2.0
Tracing Upstream Lineageastronomer/agents4511 repos~1.1kAutomated safety check: PassApache-2.0

Similar skills

  • Jeecg System

    jeecgboot/skills

    JeecgBoot 系统主数据查询与管理。Use when user asks to query/create/manage system master data, or says "查询角色", "查询用户", "查询部门", "查询字典", "创建字典", "创建角色", "查岗位", "查职务", "查租户", "查数据源", "查定时任务", "系统主数据", "query…

    239 GitHub stars~3.2k tokensUpdated 21 days ago
    Data & AnalyticsAuto-check passed
  • Openalgo Chart Indicator

    marketcalls/openalgo-charts

    Add a built-in openalgo-charts indicator, restyle it, build a settings UI from its descriptor, or author a custom indicator with registerIndicator or the Tier-2 external-data contract.

    140 GitHub stars~3.4k tokensUpdated 7 days ago
    Data & AnalyticsAuto-check: notes
  • Sets up data quality checks with Great Expectations, dbt tests and data contracts, with checkpoints and pass-fail reports for pipelines.

    40k GitHub starsUsed in 11 repos~1.1k tokens
    Data & AnalyticsAuto-check passed
  • Trace downstream data lineage and impact analysis. An agent skill from astronomer/agents.

    451 GitHub starsUsed in 1 repo~1.2k tokens
    Data & AnalyticsAuto-check passed
  • Tracing Upstream Lineage

    astronomer/agents

    Trace upstream data lineage. An agent skill from astronomer/agents.

    451 GitHub starsUsed in 1 repo~1.1k tokens
    Data & AnalyticsAuto-check passed
  • Finds usable public datasets, judges whether the data can support a research idea, and checks train and test splits for leakage before results are trusted.

    641 GitHub stars~4.9k tokensUpdated 3 mo ago
    Data & AnalyticsAuto-check passed

More from hashgraph-online/awesome-codex-plugins

All 686 skills in this repo
  • Anime Reaction Gif

    hashgraph-online/awesome-codex-plugins

    Create original anime-style reaction stickers as looping GIFs and MP4 previews, using generated character pose sheets and timed key poses.

    1.2k GitHub stars~922 tokensUpdated today
    Auto-check passed
  • Calibredb

    hashgraph-online/awesome-codex-plugins

    Manage and query Calibre libraries with the calibredb CLI (local paths or Calibre Content server URLs).

    1.2k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Rust API Test Harness

    hashgraph-online/awesome-codex-plugins

    A skill your agent uses when adding, changing, testing, or debugging Rust HTTP APIs and services, especially when Codex needs black-box integration tests, random-port app startup, real database test…

    1.2k GitHub stars~1.7k tokensUpdated today
    Auto-check passed
  • Art

    hashgraph-online/awesome-codex-plugins

    Make a studio's game look like something at build time — a cover from a real frame of the game (free), painted covers, backdrops, textures and character plates from image models through the…

    1.2k GitHub stars~2.4k tokensUpdated today
    Auto-check passed
  • Game Balance Economy

    hashgraph-online/awesome-codex-plugins

    Balance game difficulty, resources, rewards, probability, progression, economies, and dominant strategies.

    1.2k GitHub stars~618 tokensUpdated today
    Auto-check passed
  • Manuscript Engagement Analytics

    hashgraph-online/awesome-codex-plugins

    Analyze nonfiction manuscripts for reader engagement signals, including heading-level word counts, slow starts, long slogs, weak takeaway titles, value pacing, beta-reader comment dropoff, and…

    1.2k GitHub stars~875 tokensUpdated today
    Auto-check passed

Questions about Data Contracts

What does Data Contracts do?

A skill your agent uses when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning. Data Contracts is an agent skill from hashgraph-online/awesome-codex-plugins. Use when source data and receiving code may disagree on fields, shape, optionality, enum values, or business meaning.

When should I use Data Contracts?

Data Contracts fits situations like: source data and receiving code may disagree on fields; business meaning; real data wiring; mock replacement.

How do I install Data Contracts in Claude Code?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill data-contracts -a claude-code`. Or copy the skill folder (plugins/lsshym/wingman.ai/skills/data-contracts in hashgraph-online/awesome-codex-plugins) into .claude/skills/data-contracts in your project. Claude Code loads it when a task matches its description.

How do I install Data Contracts in Codex?

Run `npx skills add hashgraph-online/awesome-codex-plugins --skill data-contracts -a codex`. Or copy the skill folder (plugins/lsshym/wingman.ai/skills/data-contracts in hashgraph-online/awesome-codex-plugins) into .agents/skills/data-contracts in your project. Codex loads it when a task matches its description.

Can I use Data Contracts in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hashgraph-online/awesome-codex-plugins --skill data-contracts -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/data-contracts, .gemini/skills/data-contracts, .github/skills/data-contracts and .opencode/skills/data-contracts in your project.

What does Data Contracts need to run?

SKILL.md names no scripts, command-line tools or credentials: Data Contracts is instructions for the agent only.

Does Data Contracts access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Data Contracts safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Data Contracts use?

Data Contracts is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Data Contracts use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Data Contracts?

Skills that share tags, products or a category with Data Contracts: Jeecg System (jeecgboot/skills, 239 stars), Openalgo Chart Indicator (marketcalls/openalgo-charts, 140 stars), Data Quality Frameworks (wshobson/agents, 40k stars) and Tracing Downstream Lineage (astronomer/agents, 451 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Data Contracts?

hashgraph-online (a GitHub organization) maintains it in hashgraph-online/awesome-codex-plugins, which has 1,242 GitHub stars. The repository holds 686 skills in this directory. The repository was last updated on October 8, 2026.

Source: hashgraph-online/awesome-codex-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.