forgd-ai

Forgd Verdict — DevOps skill for Claude Code

DevOps community

Data loss prevention for Claude: finds secrets and personal data in prompts and responses, blocks prompts through inference hooks, and scans Compliance API history.

How to install Forgd Verdict

This entry records only its repository, not the path inside it, so there is no exact command to give. Open forgd-ai/forgd-verdict and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Forgd Verdict does

Data loss prevention for Claude: finds secrets and personal data in prompts and responses, blocks prompts through inference hooks, and scans Compliance API history. Self-hosted on Azure, AWS or Google Cloud.

Alternatives in DevOps

Claude2api — Claude2API 是基于 Go + Docker 构建的 Claude.ai API 兼容网关、账号池与网页镜像服务，支持 OpenAI Chat Completions、Responses 和 Anthropic 71 ★
Cover — Keep private data, internal infrastructure and secrets out of cloud coding agents without breaking your workfl 42 ★
Chaos — Design, run, and debug Chaos Engineering experiments on Kubernetes using Litmus Chaos v3 and Chaos Mesh v2. Co 40 ★

README

forgd-verdict

[![ci](https://github.com/forgd-ai/forgd-verdict/actions/workflows/ci.yml/badge.svg)](https://github.com/forgd-ai/forgd-verdict/actions/workflows/ci.yml) [![licence: Apache-2.0](https://img.shields.io/badge/licence-Apache--2.0-blue.svg)](LICENSE)

forgd-verdict is data loss prevention for an organization's use of Claude. It finds secrets and personal data (API keys, credentials, national IDs, card numbers and similar) in what people and agents send to Claude and in what comes back, and it can block a prompt before it reaches the model.

Before inference: Anthropic's inference hooks call the verdict server with each prompt, and it answers allow or deny. On Claude Code, a hook does the same before a tool runs.
After the fact: it scans conversation history from the Compliance API, telemetry pushed over OpenTelemetry, and Managed Agents sessions, where it cannot block. It records what it found, and can join those findings to the live verdicts.
Findings: each is stored as a detector name, a location and a one-way digest, never the matched value.
Dashboard and connector: a dashboard shows coverage, findings and latency across every surface. An optional read-only connector lets a security team query the same findings from Claude. The connector is experimental: it has not yet been run against a real Claude organization or identity provider.

You deploy it into your own cloud, against your own Claude organizations: Azure, AWS or Google Cloud, on managed containers or Kubernetes. Findings are written to storage in that cloud. Either fork this repository and deploy from the fork, or keep a repository of your own deployment files that runs a published release (the images, the Helm chart, the Terraform modules and the PyPI package); [docs/DEPLOY-FROM-RELEASES.md](docs/DEPLOY-FROM-RELEASES.md) says when to choose which and has a skeleton for the second.