Skip to content
Agentmart
Submit a tool

schema-check

Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable…

Skill by runxhq

IndexedApache-2.0★ 104
Write a review

Chalk Labs

Need help deploying schema-check?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/runxhq-schema-check

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable verdict with native digest evidence.

Use cases: documents, backend, data

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/schema-check

What's inside

Skill name
schema-check
Description
Check a proposed API or data contract against the current contract, real sample payloads, and a compatibility policy, and gate publication behind a refusable verdict with native digest evidence.
License
Apache-2.0
Instructions
62 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (9)

  • SKILL.md
  • allowed-removal-keeps-change-path.yaml · fixtures/
  • composes-in-graph.yaml · fixtures/
  • composed.graph · fixtures/support/
  • mark.svg
  • catalog.md · references/
  • mark-license.md · references/
  • run.yaml
  • schema-check.mjs

SKILL.md (first lines)

# Schema Check

Schema Check decides whether a proposed contract change can move forward
without silently breaking callers. It compares the current and proposed JSON
Schema contracts field by field, validates every supplied sample payload
against the proposed contract, applies the caller's compatibility policy, and
either refuses or emits a gated publish proposal. It never publishes anything
itself.

## Procedure

1. Native `data.digest` binds the exact current schema, proposed schema, and
   sample set before any judgment, so the verdict is tied to specific bytes.
2. Deterministic comparison walks both contracts: removed fields, type changes,
   fields that became required, new required fields, and narrowed enums are
   breaking; additive optional fields and expanded enums are notes.
3. Native `data.validate` compiles both schemas and validates every sample against
   each contract using JSON Schema 2020-12, with external retrieval disabled. Coverage is
   reported honestly: paths no sample exercises are flagged, not assumed
   covered.
4. The policy decides the verdict. Breaking changes are refused unless
   `breaking_allowed` is explicitly true, and policy `required_fields` must
   exist in the proposed contract.
5. A compatible verdict emits a `proposal` with the three digests and changed
   paths, gated on a schema publisher or human approver. A refused verdict
   emits no proposal. `live_write_performed` is always false.

Invalid requests refuse with `policy_result: invalid_input` and findings rather
than guessing. Missing required inputs fail at admission.

## Output

`schema_check` (`runx/schema-check.check.v1`) carries `decision`, `policy_result`,
`breaking_changes`, per-sample `validation_results`, `migration_notes`
including coverage, the gated `proposal` or null, and `validation`.

Inputs are `current_schema`, `proposed_schema`, `sample_payloads`, and
`compatibility_policy`.

## What compatibility means

Sample validity is not a proof that every existing caller remains compatible.
The inclusion comparison supports object properties, required fields, scalar
types, enums and boolean additionalProperties. It compares root constraints as
well as nested fields. A newly constrained enum and a newly closed object are
changes that may reject existing callers.

The native validator supports the full self-contained schema, including
minLength, numeric bounds, nested arrays, composition and local references. If
a changed contract uses constraints outside the inclusion comparison's supported
language, the result is refused with `compatibility.unsupported` findings, even
if its samples happen to pass or breaking changes are allowed. Identical schemas
need no inclusion inference but still compile and validate their samples.
Formats are annotations. This skill never fetches remote schemas.

For example, adding `minLength: 10` to a string with sample `"x"` fails native
validation; it cannot receive a compatible verdict. Missing required fields,
removed enum values and unknown comparison semantics remain visible. A proposal
is not publication approval. Its digests bind the exact proposed change; the
actual schema publisher owns authorization, publication and readback.

From runxhq/runx, Apache-2.0.

More from runxhq/runx

Signals

Stars
104
Forks
109
Open issues
16
Contributors
16
Last commit (this folder)
Oct 17, 2026 (13 days ago)
Last release
Oct 18, 2026 (12 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
Website
runx.ai
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from runxhq

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get schema-check running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying schema-check?

CallGet help
Cite this page

schema-check skill. Agent Mart. https://agentmart.dev/skills/runxhq-schema-check (last updated 2026-10-24)