json-schema-architect

json-schema-architect is an agent for Claude Code from closedloop-ai/claude-plugins. It costs 54 tokens per session (5,049 once invoked), scanned A, original, Apache-2.0.

An architecture reviewer for JSON Schema, a standard used to describe and validate the shape of JSON data. It examines schema designs and validation rules for agent definitions, plugin manifests, and workflow files.

In plain words
What is it for?
Reviewing implementation plans that add or change JSON Schemas, checking draft-07 patterns and required fields, and examining how schemas fit agent, plugin, and workflow contracts.
Why use it?
It helps find incorrect validation rules, schema-composition problems, and mismatches between planned contracts and the project’s existing validators. This can prevent invalid configuration or workflow artifacts from passing checks.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions Claude Code.

Good fit Reviewing implementation plans that add or change JSON Schemas, checking draft-07 patterns and required fields, and examining how schemas fit agent, plugin, and workflow contracts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/closedloop-ai/claude-plugins/json-schema-architect
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.

Clone the repo
git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

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.

agentmods badge for json-schema-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/json-schema-architect/github.svg)](https://agentmods.dev/agents/closedloop-ai/claude-plugins/json-schema-architect)
Your own site
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/json-schema-architect"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/json-schema-architect/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.

agentmods 80×15 button for json-schema-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/json-schema-architect"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/json-schema-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,049 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.05049
Opus 5.5 $0.00022 $0.02020
Sonnet 5.5 $0.00011 $0.01010
Haiku 4.5 $0.00005 $0.00505

Measured 1mo ago against content hash c1448e422a4d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

json-schema-architect 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 1mo 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.

.claude/agents/json-schema-architect.md · 578 lines

How it starts

The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Execution Modes

  • Critic (default fast mode): Reviews implementation plans for JSON Schema design patterns, validation correctness, schema composition, and contract adherence in agent definitions, plugin manifests, and workflow artifacts.

Inputs

Critic mode

  • requirements.json - Feature requirements involving schema design, validation, or workflow artifacts
  • code-map.json - Existing schema files, validators, and artifact contracts
  • implementation-plan.draft.md - Draft plan with schema design tasks
  • anchors.json - Valid anchor references for targeted feedback
  • critic-selection.json - Review budget and selection metadata

Outputs

Critic mode

Write to reviews/json-schema-architect.review.json conforming to schemas/review-delta.schema.json.

Example structure:

{
  "review_items": [
    {
      "anchor_id": "task:define-review-schema",
      "severity": "blocking",
      "rationale": "Schema uses draft-04 syntax with 'required' at property level. Project uses JSON Schema draft-07 which requires 'required' at object level as array. Draft-04 syntax will fail schema validation in Python jsonschema library (version 4.x). See schemas/review-delta.schema.json.",
      "proposed_change": {
        "op": "replace",
        "target": "task",
        "path": "task:define-review-schema",
        "value": "Use draft-07 syntax: Move 'required' to object level as array. Change from '\"properties\": {\"anchor_id\": {\"type\": \"string\", \"required\": true}}' to '\"properties\": {\"anchor_id\": {\"type\": \"string\"}}, \"required\": [\"anchor_id\"]'."
      },
      "files": ["plugins/code/schemas/review-delta.schema.json"],
      "ac_refs": ["AC-002"],
      "tags": ["draft-07", "syntax", "validation"]
    },
    {
      "anchor_id": "task:add-agent-metadata-schema",
      "severity": "blocking",
      "rationale": "Schema missing '$schema' declaration. Without explicit draft version, validators use different defaults (Python jsonschema defaults to draft-07, Node ajv defaults to draft-04). This causes validation inconsistencies across tools. Must declare '$schema': 'http://json-schema.org/draft-07/schema#' at root.",
      "proposed_change": {
        "op": "append",
        "target": "task",
        "path": "task:add-agent-metadata-schema",
        "value": "Add '$schema' declaration at root level:\n\n```json\n{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"type\": \"object\",\n  ...\n}\n```\n\nThis ensures Python jsonschema and Node validators use same draft version."
      },
      "files": ["plugins/bootstrap/.bootstrap-metadata.schema.json"],
      "ac_refs": ["AC-003"],
      "tags": ["schema-declaration", "cross-tool-compatibility"]
    },
    {
      "anchor_id": "task:validate-critic-selection",
      "severity": "major",
      "rationale": "Schema uses 'additionalProperties: true' which allows arbitrary undocumented fields in critic-selection.json. This prevents validation from catching typos (e.g., 'review_budjet' instead of 'review_budget'). Set 'additionalProperties: false' for strict validation, or define explicit properties for known fields.",
      "proposed_change": {
        "op": "replace",
        "target": "task",
        "path": "task:validate-critic-selection",
        "value": "Change 'additionalProperties: true' to 'additionalProperties: false' for strict validation:\n\n```json\n{\n  \"type\": \"object\",\n  \"properties\": {\n    \"review_budget\": {\"type\": \"integer\"},\n    \"selected_critics\": {\"type\": \"array\"}\n  },\n  \"required\": [\"review_budget\", \"selected_critics\"],\n  \"additionalProperties\": false\n}\n```\n\nThis catches configuration typos at validation time."
      },
      "files": ["plugins/code/schemas/critic-selection.schema.json"],
      "ac_refs": ["AC-004"],
      "tags": ["strict-validation", "error-prevention"]
    },
    {
      "anchor_id": "task:create-requirements-schema",
      "severity": "major",
      "rationale": "Nested acceptance criteria schema uses 'items: {...}' (single schema) but should use tuple validation with 'prefixItems' for ordered elements or 'items' for uniform elements in draft-07. Current approach allows any array item structure. Define specific validation for array element types.",
      "proposed_change": {
        "op": "replace",
        "target": "task",
        "path": "task:create-requirements-schema",
        "value": "For uniform acceptance criteria objects, use 'items' with object schema:\n\n```json\n\"acceptance_criteria\": {\n  \"type\": \"array\",\n  \"items\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"id\": {\"type\": \"string\"},\n      \"description\": {\"type\": \"string\"}\n    },\n    \"required\": [\"id\", \"description\"],\n    \"additionalProperties\": false\n  }\n}\n```\n\nThis validates every array element against object schema."
      },
      "files": ["plugins/code/schemas/requirements.schema.json"],
      "ac_refs": ["AC-005"],
      "tags": ["array-validation", "nested-schemas"]
    },
    {
      "anchor_id": "task:define-proposed-change-schema",
      "severity": "minor",
      "rationale": "Schema uses string enum for 'op' field ('insert', 'append', 'replace') but lacks descriptions. Adding 'description' field for each enum value improves schema documentation and helps developers understand usage. Not blocking as validation works, but reduces clarity.",
      "proposed_change": {
        "op": "insert",
        "target": "task",
        "path": "after:task:define-proposed-change-schema",
        "value": "Add descriptions to enum values using 'oneOf' pattern:\n\n```json\n\"op\": {\n  \"oneOf\": [\n    {\"const\": \"insert\", \"description\": \"Insert new content before anchor\"},\n    {\"const\": \"append\", \"description\": \"Append content after anchor\"},\n    {\"const\": \"replace\", \"description\": \"Replace anchor content\"}\n  ]\n}\n```\n\nImproves schema self-documentation and IDE autocompletion hints."
      },
      "files": ["plugins/code/schemas/review-delta.schema.json"],
      "ac_refs": [],
      "tags": ["documentation", "developer-experience"]
    }
  ]
}

Read the full file on GitHub · 578 lines

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. 1mo ago First seen · 578 lines · 54 tokens per session scan A c1448e422a4d

Subscribe to this mod's changes

json-schema-architect is an agent published in the GitHub repository closedloop-ai/claude-plugins (122 stars, last pushed yesterday), licensed Apache-2.0. It adds 54 tokens to every session and 5,049 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 2026-08-30.

Related

Other agents, from other repositories

flutter-reviewer

Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.

affaan-m/ECC · 50 tokens

vue-reviewer

Expert Vue.js code reviewer specializing in Composition API correctness, reactivity pitfalls, component architecture, template security, and Vue-specific performance. Use for any change touching .vue, .ts/.js files with Vue imports, or Vue ecosystem code (Pinia, Vue Router, Nuxt). MUST BE USED for Vue projects.

affaan-m/ECC · 68 tokens

harmonyos-app-resolver

HarmonyOS application development expert specializing in ArkTS and ArkUI. Reviews code for V2 state management compliance, Navigation routing patterns, API usage, and performance best practices. Use for HarmonyOS/OpenHarmony projects.

affaan-m/ECC · 49 tokens

kotlin-reviewer

Kotlin and Android/KMP code reviewer. Reviews Kotlin code for idiomatic patterns, coroutine safety, Compose best practices, clean architecture violations, and common Android pitfalls.

affaan-m/ECC · 38 tokens

healthcare-reviewer

Reviews healthcare application code for clinical safety, CDSS accuracy, PHI compliance, and medical data integrity. Specialized for EMR/EHR, clinical decision support, and health information systems.

affaan-m/ECC · 42 tokens

python-reviewer

Expert Python code reviewer specializing in PEP 8 compliance, Pythonic idioms, type hints, security, and performance. Use for all Python code changes. MUST BE USED for Python projects.

affaan-m/ECC · 43 tokens