What is json-comparator?

A checker that compares JSON—structured text commonly used by APIs and configuration files—with an expected example or JSON Schema, a set of rules for valid data.

Validating API responses, JSON configuration, nested objects, and data contracts, with options to ignore selected differences.

It identifies missing, extra, changed, or incorrectly ordered data without requiring a custom comparison script.

json-comparator — Skill for Claude Code and Codex by EE-WILL-I

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.

Any agent

npx skills add EE-WILL-I/simple-data-comparator-mcp --skill json-comparator

Clone the repo

git clone --depth 1 https://github.com/EE-WILL-I/simple-data-comparator-mcp

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/ee-will-i/simple-data-comparator-mcp/json-comparator.svg)](https://agentmods.dev/skills/ee-will-i/simple-data-comparator-mcp/json-comparator)

Your own site

<a href="https://agentmods.dev/skills/ee-will-i/simple-data-comparator-mcp/json-comparator"><img src="https://agentmods.dev/badge/skills/ee-will-i/simple-data-comparator-mcp/json-comparator.svg" alt="Measured on agentmods" height="20"></a>

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 913 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00049	$0.00913
Opus 5	$0.00024	$0.00456
Sonnet 5	$0.00010	$0.00183
Haiku 4.5	$0.00005	$0.00091

Measured 7d ago against content hash 70d33123ac12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

json-comparator 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 7d 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/json-comparator/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

JSON Comparator

Compare actual JSON against an expected template or JSON Schema using the validate-json MCP tool (simple-data-comparator-mcp server).

Workflow

Discover the tool — call GetMcpTools for the comparator MCP server, then invoke validate-json.
Prepare strings — both actual and template must be valid JSON strings (serialize objects before calling).
Call the tool with actual (received data) and template (expected data or schema).
Check isError in the MCP response:
- false → validation passed
- true → read difference lines and explain mismatches to the user
Retry with options (strictMode, ignoreProps, ignoreSimilar, etc.) as needed.

Parameters

Parameter	Default	Purpose
`actual`	required	JSON string to validate
`template`	required	Expected JSON template, or JSON Schema when `useJsonSchema` is `true`
`strictMode`	`false`	`true` = fail on extra fields not in template
`ignoreArrayOrder`	`false`	Sort arrays before comparing
`ignoreProps`	—	Property names stripped from both sides (e.g. `["timestamp"]`)
`ignoreSimilar`	`false`	Pass when values differ but JS types match
`useJsonSchema`	`false`	Treat `template` as JSON Schema (Ajv)

Default (strictMode: false) ignores extra fields in actual. Use strictMode: true for strict contract testing.

Interpreting results

Pass: Validation passed.

Fail:

Validation failed.
Differences:
[mismatch] age expected=30 actual=25
[missing] status expected="active" actual=undefined
[extra] city actual="NYC" expected=undefined
[schema_error] / is missing required property: age
[duplicate_key] "name" appears multiple times in the JSON

Paths use dot notation and [index] for arrays (e.g. users[0].email).

Parse error: JSON parse error: ... — fix JSON syntax before re-validating.

Example calls

Read the full file on GitHub · 101 lines

Files

What ships with it

1 file 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/json-comparator.md 6.1 KB

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.

7d ago First seen · 101 lines · 49 tokens per session scan A 70d33123ac12

Subscribe to this mod's changes

json-comparator is a skill published in the GitHub repository EE-WILL-I/simple-data-comparator-mcp (0 stars, last pushed 27d ago), licensed MIT. It adds 49 tokens to every session and 913 once invoked, about $0.0002 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

json-comparator