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 runxhq/runx --skill schema-checkgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/schema-check)<a href="https://agentmods.dev/skills/runxhq/runx/schema-check"><img src="https://agentmods.dev/badge/skills/runxhq/runx/schema-check/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/runxhq/runx/schema-check"><img src="https://agentmods.dev/badge/skills/runxhq/runx/schema-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00678 |
| Opus 5.5 | $0.00015 | $0.00271 |
| Sonnet 5.5 | $0.00008 | $0.00136 |
| Haiku 4.5 | $0.00004 | $0.00068 |
Grade A, and why
schema-check 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
- Native
data.digestbinds the exact current schema, proposed schema, and sample set before any judgment, so the verdict is tied to specific bytes. - 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.
- Native
data.validatecompiles 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. - The policy decides the verdict. Breaking changes are refused unless
breaking_allowedis explicitly true, and policyrequired_fieldsmust exist in the proposed contract. - A compatible verdict emits a
proposalwith the three digests and changed paths, gated on a schema publisher or human approver. A refused verdict emits no proposal.live_write_performedis 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.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.
What ships with it
8 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.
- 4d ago First seen · 66 lines · 38 tokens per session scan A b29b3dcd62bb
schema-check is a skill published in the GitHub repository runxhq/runx (104 stars, last pushed today), licensed Apache-2.0. It adds 38 tokens to every session and 678 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-18.
Other skills, from other repositories
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
cw-gates
Use before claiming any Codewhale change is done, green, or ready to land: the focused-to-broad verification ladder, the budget checks CI enforces, and the rules for what counts as a passing test.
webapp-testing
Start/reuse a local app, wait for readiness, inspect rendered state/console/network, act from observed selectors, and verify with evidence.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, or before committing or creating PRs.
developing-openrig
Use when changing OpenRig's own source in a clone of the openrig repository: finding which package or file owns a behaviour, choosing which tests to run, testing a change without disturbing the OpenRig daemon your own session runs on, judging whether a diff touches a high-risk area, or preparing a pull request. Not…
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.