case-dev

case-dev is a skill for Claude Code, Codex from CaseMark/casedotdev-starter-app. It costs 0 tokens per session (3,480 once invoked), scanned A, original, Apache-2.0.

An integration for Case.dev, a platform for legal applications that provides encrypted document storage, document search, AI models, OCR, transcription, and legal workflows.

In plain words
What is it for?
Use it to connect applications to Case.dev vaults, upload and search documents, digitize scanned files, transcribe depositions, run legal processing workflows, and deploy serverless functions.
Why use it?
It gives legal software one API connection for handling documents, extracting text and tables, transcribing recordings with speaker labels, and using AI models and legal prompts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to connect applications to Case.dev vaults, upload and search documents, digitize scanned files, transcribe depositions, run legal processing workflows, and deploy serverless functions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/casemark/casedotdev-starter-app/case-dev
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 CaseMark/casedotdev-starter-app --skill case-dev
Clone the repo
git clone --depth 1 https://github.com/CaseMark/casedotdev-starter-app

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 case-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/casemark/casedotdev-starter-app/case-dev/github.svg)](https://agentmods.dev/skills/casemark/casedotdev-starter-app/case-dev)
Your own site
<a href="https://agentmods.dev/skills/casemark/casedotdev-starter-app/case-dev"><img src="https://agentmods.dev/badge/skills/casemark/casedotdev-starter-app/case-dev/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 case-dev

Your own site · 80×15
<a href="https://agentmods.dev/skills/casemark/casedotdev-starter-app/case-dev"><img src="https://agentmods.dev/badge/skills/casemark/casedotdev-starter-app/case-dev.svg" alt="Reviewed on agentmods" width="80" 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 3,480 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 $0.00000 $0.03480
Opus 5.5 $0.00000 $0.01392
Sonnet 5.5 $0.00000 $0.00696
Haiku 4.5 $0.00000 $0.00348

Measured 2mo ago against content hash 607e51af23af, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

case-dev 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/case-dev/SKILL.md · 617 lines

How it starts

The opening of the file, as written. The whole thing — 617 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Case.dev SDK Skill

Purpose

This skill covers the Case.dev API platform integration for legal tech applications, including document vaults, AI models, OCR, transcription, and workflows.

Key Concepts

  • Vaults: Encrypted document storage with semantic search and RAG
  • LLMs: Unified gateway to 130+ AI models (Claude, GPT-4, CaseMark Core 1)
  • OCR: Production-grade document digitization with table extraction
  • Voice: Transcription with speaker diarization for depositions
  • Workflows: 700+ expert-crafted legal prompts and processing pipelines
  • Orbit Compute: Serverless functions and app deployments

Setup

Installation

# TypeScript/JavaScript
bun add git+ssh://[email protected]:stainless-sdks/router-typescript.git

# Once published to npm:
# bun add casedev

Environment Variables

# .env.local
CASE_API_KEY=sk_case_...
CASEDEV_API_KEY=sk_case_...

Initialize Client

// lib/case-dev/client.ts
import Casedev from 'casedev';

export const casedev = new Casedev({
  apiKey: process.env.CASEDEV_API_KEY!,
  environment: 'production', // or 'local' for development
});

Project Structure

/
├── app/
│   ├── api/
│   │   └── case-dev/
│   │       ├── upload/route.ts
│   │       ├── search/route.ts
│   │       └── analyze/route.ts
├── lib/
│   └── case-dev/
│       ├── client.ts
│       ├── vaults.ts
│       ├── llm.ts
│       └── ocr.ts
└── ...

Vaults - Document Storage

Create a Vault

// lib/case-dev/vaults.ts
import { casedev } from './client';

export async function createVault(name: string, description?: string) {
  const vault = await casedev.vault.create({
    name,
    description,
  });
  
  return vault;
}

Upload Document to Vault

export async function uploadDocument(
  vaultId: string,
  file: File,
  options?: {
    ocr?: boolean;
    semanticIndex?: boolean;
  }
) {
  const formData = new FormData();
  formData.append('file', file);
  formData.append('vault_id', vaultId);
  
  if (options?.ocr) {
    formData.append('ocr', 'true');
  }
  
  if (options?.semanticIndex) {
    formData.append('semantic_index', 'true');
  }
  
  const doc = await casedev.vault.upload(formData);
  
  return doc;
}

Read the full file on GitHub · 617 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. 2mo ago First seen · 617 lines · 0 tokens per session scan A 607e51af23af

Subscribe to this mod's changes

case-dev is a skill published in the GitHub repository CaseMark/casedotdev-starter-app (2 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 3,480 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 2026-08-31.

Related

Other skills, from other repositories

html-ppt-zhangzara-stencil-tablet

A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.

nexu-io/open-design · 49 tokens

treatment-plans

Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…

K-Dense-AI/scientific-agent-skills · 62 tokens

legal-hold

Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.

anthropics/claude-for-legal · 68 tokens

handbook-updates

Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.

anthropics/claude-for-legal · 52 tokens

terms-of-service

Draft terms of service and a companion privacy notice matched to the product's form and feature modules, not legal advice, delivered as a Word document.

genspark-ai/genoffice · 32 tokens

software-copyright-materials

A workflow for creating Chinese application materials for software copyright registration from a real software project.

Fokkyp/SoftwareCopyright-Skill · 98 tokens