metadata-validator

metadata-validator is a skill for Claude Code, Codex from lowtidebuild/contract-review. It costs 0 tokens per session (402 once invoked), scanned A, original, Apache-2.0.

A set of validators for checking ingestion packages, their metadata files, and possible leaks of privileged content.

In plain words
What is it for?
Validating manifests and packages, checking text structure and numbering, and scanning files for privilege markers in English and Korean.
Why use it?
It catches invalid structure, missing or wrongly typed metadata, package problems, and confidential legal or strategy notes before publication.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/lowtidebuild/contract-review/metadata-validator
Any agent
npx skills add lowtidebuild/contract-review --skill metadata-validator
Clone the repo
git clone --depth 1 https://github.com/lowtidebuild/contract-review

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 metadata-validator

README.md
[![agentmods](https://agentmods.dev/badge/skills/lowtidebuild/contract-review/metadata-validator.svg)](https://agentmods.dev/skills/lowtidebuild/contract-review/metadata-validator)
Your own site
<a href="https://agentmods.dev/skills/lowtidebuild/contract-review/metadata-validator"><img src="https://agentmods.dev/badge/skills/lowtidebuild/contract-review/metadata-validator.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00402
Opus 5 $0.00000 $0.00201
Sonnet 5 $0.00000 $0.00080
Haiku 4.5 $0.00000 $0.00040

Measured 5d ago against content hash b9c732f7cb39, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

metadata-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 5d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/check-privilege-leak.py, scripts/validate-manifest.py, scripts/validate-package.py), 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.

.claude/skills/metadata-validator/SKILL.md · 48 lines

What it actually says

metadata-validator Skill

Validate ingestion package integrity, manifest schemas, and detect privileged content.

Capabilities

  1. Manifest Validation (scripts/validate-manifest.py)

    • Validates manifest.yaml against metadata-schema.yaml
    • Checks required fields, data types, enum values, patterns
    • Usage: python3 validate-manifest.py <manifest_path>
  2. Package Validation (scripts/validate-package.py)

    • Checks complete ingestion package integrity
    • Validates: normalized text, structural parse, manifest, clauses, numbering
    • Applies hard-fail and soft-fail conditions
    • Usage: python3 validate-package.py <package_dir>
    • Exit codes: 0=valid, 1=hard fail, 2=soft fail
  3. Privilege Leak Detection (scripts/check-privilege-leak.py)

    • Scans for internal comments, attorney-client privilege markers, strategy notes
    • Supports English and Korean patterns
    • Usage: python3 check-privilege-leak.py <file_or_dir>
    • Exit codes: 0=clean, 2=found but isolable, 3=found and cannot isolate

When to Use

  • WF1 Step 8 (Validation & Risk Check): run all three validators
  • Before publishing any asset to approved/
  • When checking external-safe eligibility

Hard-Fail Conditions

These cause QUARANTINE:

  • Normalized text is absent or empty
  • Structural parse output is missing
  • Three or more required manifest fields are missing
  • Privileged content detected and cannot be isolated
  • Source file is corrupt or unreadable

Soft-Fail Conditions

These cause STAGING (human review):

  • Unmapped clauses ≥ 30%
  • Defined term extraction failed
  • Governing law is ambiguous
  • Near-duplicate conflict unresolved
  • Freshness-sensitive clause lacks last_legal_refresh_date
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. 5d ago First seen · 48 lines · 0 tokens per session scan A b9c732f7cb39

Subscribe to this mod's changes

metadata-validator is a skill published in the GitHub repository lowtidebuild/contract-review (40 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 402 tokens. 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens