OpenAPI Spec Validator

OpenAPI Spec Validator is a skill for Claude Code, Codex from theshubh007/agent-skill-finder. It costs 78 tokens per session (726 once invoked), scanned A, original, MIT.

A validator for OpenAPI 3.x and Swagger 2.0 files, which describe the endpoints and data structures of a web API.

In plain words
What is it for?
Use it to check YAML or JSON specifications, report errors with their paths and severity, and optionally verify references, responses, and examples in strict mode.
Why use it?
It finds schema mistakes and configuration problems before an API specification is used to generate or document software.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is asf query "validate my openapi spec at ./api/openapi.yaml".

Good fit Use it to check YAML or JSON specifications, report errors with their paths and severity, and optionally verify references, responses, and examples in strict mode.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/theshubh007/agent-skill-finder
agentmods
npx agentmods add skills/theshubh007/agent-skill-finder/openapi-spec-validator

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.

agentmods badge for OpenAPI Spec Validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/theshubh007/agent-skill-finder/openapi-spec-validator/github.svg)](https://agentmods.dev/skills/theshubh007/agent-skill-finder/openapi-spec-validator)
Your own site
<a href="https://agentmods.dev/skills/theshubh007/agent-skill-finder/openapi-spec-validator"><img src="https://agentmods.dev/badge/skills/theshubh007/agent-skill-finder/openapi-spec-validator/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 OpenAPI Spec Validator

Your own site · 80×15
<a href="https://agentmods.dev/skills/theshubh007/agent-skill-finder/openapi-spec-validator"><img src="https://agentmods.dev/badge/skills/theshubh007/agent-skill-finder/openapi-spec-validator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 726 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 $0.00078 $0.00726
Opus 5.5 $0.00031 $0.00290
Sonnet 5.5 $0.00016 $0.00145
Haiku 4.5 $0.00008 $0.00073

Measured 2mo ago against content hash 814a0679104e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

OpenAPI Spec Validator 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 2mo 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/openapi-spec-validator/SKILL.md · 91 lines

What it actually says

What this skill does

Parses an OpenAPI 3.x or Swagger 2.0 spec file and runs full schema validation using the official OpenAPI JSON Schema. Returns every error with the JSON path where it occurred, a human-readable message, and the severity level. In strict mode, also validates that all $ref references resolve and that every endpoint has at least one documented response.

Inputs

  • spec_path — path to the .yaml, .yml, or .json spec file
  • strict — when true, enables additional checks: unresolved $ref, undocumented endpoints, missing example values (default: false)

Outputs

  • errors — list of {path, message, severity} objects for spec violations (severity: error)
  • warnings — list of {path, message, severity} objects for best-practice issues (severity: warning)
  • error_count — number of error-severity violations
  • valid — true when error_count == 0

Common errors caught

Error Example path
Missing required field #/paths/~1users/get/responses
Invalid $ref #/components/schemas/User/properties/id
Wrong type for parameter #/paths/~1items/get/parameters/0/schema
Security scheme not defined #/paths/~1admin/get/security/0
Response schema missing type #/paths/~1users/post/responses/200/content

Example

# validate a spec file
asf query "validate my openapi spec at ./api/openapi.yaml"
{
  "errors": [
    {
      "path": "#/paths/~1users/get/responses",
      "message": "Required property 'responses' is missing",
      "severity": "error"
    }
  ],
  "warnings": [],
  "error_count": 1,
  "valid": false
}

Notes

  • Supports OpenAPI 3.0.x, 3.1.x, and Swagger 2.0
  • Use strict: true in CI pipelines to enforce documentation completeness
  • YAML and JSON formats both supported; auto-detected from file extension
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. 2mo ago First seen · 91 lines · 78 tokens per session scan A 814a0679104e

Subscribe to this mod's changes

OpenAPI Spec Validator is a skill published in the GitHub repository theshubh007/agent-skill-finder (12 stars, last pushed 6mo ago), licensed MIT. It adds 78 tokens to every session and 726 once invoked, about $0.0003 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

OpenAPI Spec Validator compared with skills from other repositories

OpenAPI Spec Validator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
OpenAPI Spec Validatortheshubh007/agent-skill-finderSkill126mo agoMITA78Claude Code, Codex
mcp-tool-developersickn33/agentic-awesome-skillsSkill50ktodayMITA38Claude Code
mem0-oss-to-platformmem0ai/mem0Skill69k9d agoApache-2.0A217Claude Code, Codex
azure-mgmt-botservice-dotnetmicrosoft/skillsSkill3.2k2d agoMITA78Claude Code
fastapi-router-pymicrosoft/skillsSkill3.2k2d agoMITA46Claude Code
api-designericrisco/rsc-harnessSkill611todayMITA105Claude Code, Codex
migrate-segw-to-raparc-mcp/arc-1Skill262yesterdayMITA106Claude Code