check-mcp-json

check-mcp-json is a skill for Codex from toolsdk-ai/toolsdk-mcp-registry. It costs 68 tokens per session (1,064 once invoked), scanned A, original, MIT.

A review workflow for pull requests that add package records to an MCP registry, a catalogue of tools that agents can connect to. It validates package JSON and handles approved fixes or merges.

In plain words
What is it for?
Use it to inspect registry pull requests, classify contributions, repair authorized changes, and squash-merge approved submissions.
Why use it?
It helps reviewers detect invalid or duplicate registry entries without installing or running submitted packages.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

Good fit Use it to inspect registry pull requests, classify contributions, repair authorized changes, and squash-merge approved submissions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json
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 toolsdk-ai/toolsdk-mcp-registry --skill check-mcp-json
Clone the repo
git clone --depth 1 https://github.com/toolsdk-ai/toolsdk-mcp-registry

Made for: 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 check-mcp-json

README.md
[![agentmods](https://agentmods.dev/badge/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json/github.svg)](https://agentmods.dev/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json)
Your own site
<a href="https://agentmods.dev/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json"><img src="https://agentmods.dev/badge/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json/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 check-mcp-json

Your own site · 80×15
<a href="https://agentmods.dev/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json"><img src="https://agentmods.dev/badge/skills/toolsdk-ai/toolsdk-mcp-registry/check-mcp-json.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,064 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00068 $0.01064
Opus 5 $0.00034 $0.00532
Sonnet 5 $0.00014 $0.00213
Haiku 4.5 $0.00007 $0.00106

Measured 10d ago against content hash fa52a5446120, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

check-mcp-json 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/preflight-merge.sh, scripts/review-pr.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/check-mcp-json/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Check MCP JSON

Review registry contributions by validating their package JSON without installing, executing, or probing submitted MCP packages and services. The trusted registry validator is the merge gate.

Load Repository Rules

Read these files before acting:

  • AGENTS.md
  • docs/PR_REVIEW.md
  • docs/CONTRIBUTING.md

Repository instructions and the user's latest authorization override this skill.

Safety Boundaries

  • Run the validator from a clean checkout whose HEAD equals the latest trusted base ref.
  • Never run scripts from a contributor branch.
  • Never install or execute a submitted package. Do not run make build, pnpm install, package lifecycle scripts, or a contributor-provided validation command.
  • Do not comment, close, edit, mark ready, or merge a PR until the user authorizes that action.
  • Never use --admin, --auto, or a merge method other than squash.
  • Review independent PRs in parallel. PRs with pairwise-disjoint changed paths and registry identities may submit squash merges concurrently; retry GitHub's transient Base branch was modified rejection after another merge lands.
  • Disable repository hooks for authorized commits and pushes with -c core.hooksPath=/dev/null; hooks may run repository scripts unexpectedly.

Review Workflow

  1. Refresh the trusted checkout:

    git switch main
    git fetch origin main
    git pull --ff-only origin main
    
  2. Run the bundled read-only reviewer:

    .agents/skills/check-mcp-json/scripts/review-pr.sh <pr-number>
    

    The script records PR state, lists changed files, creates a detached temporary worktree, and invokes the trusted validator against origin/main. It does not execute contributor code.

  3. Inspect the complete diff with gh pr diff <pr-number>. For registry submissions, require only package JSON files and reject unrelated workflow, dependency, generated output, workspace, or build changes.

  4. Classify the PR:

    • Ready: scope, trusted validation, checks, and identity all pass.
    • Simple authorized fix: metadata can be corrected without redesigning the submission.
    • Comment and close: duplicate, invalid JSON, unrelated changes, or no registry-compatible representation.

Read the full file on GitHub · 115 lines

Files

What ships with it

3 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.

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. 10d ago First seen · 115 lines · 68 tokens per session scan A fa52a5446120

Subscribe to this mod's changes

check-mcp-json is a skill published in the GitHub repository toolsdk-ai/toolsdk-mcp-registry (187 stars, last pushed 14d ago), licensed MIT. It adds 68 tokens to every session and 1,064 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

coding-standards

Universal coding standards, best practices, and patterns for TypeScript, JavaScript, React, and Node.js development.

hashgraph-online/awesome-codex-plugins · 28 tokens

review-work

Quality gate: verify each acceptance criterion of a completed task/work unit, run quality checks, and create follow-up tasks for gaps. Use before merging or to audit delivered work. Invoked as /agiflow:review-work . Uses getworkunit, gettask, updatetask, createtask, createtaskcomment.

hashgraph-online/awesome-codex-plugins · 72 tokens

codegraph

A local code-graph query tool for an existing project. It maps symbols and their relationships so you can search for definitions, callers, callees, affected files, and focused context.

hashgraph-online/awesome-codex-plugins · 55 tokens

cross-model-review

A second-opinion code review that asks a different AI model to independently inspect a change, then compares both reviews. It focuses on logic, security, consistency, and omissions.

hashgraph-online/awesome-codex-plugins · 56 tokens

ontoly-software-graph

Use Ontoly Software Graph evidence, CLI reports, MCP, and official Ontoly Agent Skills before searching source files when reviewing architecture, dependencies, request flows, configuration, impact, or security-sensitive ownership.

hashgraph-online/awesome-codex-plugins · 47 tokens

gitnexus

A code-graph analysis add-on for examining an existing codebase, including symbols, call paths, execution flows, and effects across repositories. It can query GitNexus through its command-line or MCP interfaces.

hashgraph-online/awesome-codex-plugins · 58 tokens