Repo Forensics

Repo Forensics is an open-source agent orchestration harness and repository security gating tool developed by Alex Greenshpan (alexgreensh). Designed to inspect codebase integrity and secure AI agent workflows, the project provides plugin architectures and security guardrails across multiple agent runtimes. In daily use, Repo Forensics operates as a cross-runtime integration layer supporting Claude (via Claude plugins), OpenAI Codex, Cursor, and OpenClaw agents. It integrates directly into the execution flow of these coding agents to enforce repository policies, perform automated forensic scans, and output standard diagnostic reports like SARIF files for downstream CI/CD pipelines. What sets Repo Forensics apart is its focus on agent security gating and tamper hardening. Rather than acting as a standalone conversational model, it acts as an orchestration and verification harness that enforces blocking gates and signature validations across different IDE and CLI agent ecosystems before untrusted or modified code paths can execute. The project is open source and hosted on GitHub under continuous active development, featuring release verification via cryptographic checksums and offline release signing keys.

Tags: AI, ai agent, cli, codebase, developer tools, OpenSource

Visit Repo Forensics

Key features

• Multi-agent plugin adapters — Native integration manifests and hooks for Claude, OpenAI Codex, Cursor, and OpenClaw agent environments. - SARIF reporting — Built-in SARIF export tooling (sarif_export.py) for standardized static analysis output and integration into security dashboards. - Tamper hardening & blocking gates — Modification-aware gates designed to halt execution and block untrusted changes within agent sessions. - Cryptographic release integrity — Checksum validation and signature verification routines to ensure agent plugin manifests are untampered. - Comprehensive test coverage — Production-grade harness verified against over 3,400 automated unit and integration tests.

Use cases

Use Case: Enforcing Security Gating on Cursor & Claude Agents Developers running autonomous coding tasks can configure Repo Forensics hooks to intercept agent file operations. If unexpected modifications or policy violations occur, the harness's blocking gate trips to stop automated execution before changes are saved.

Use Case: Exporting Agent Forensic Scans to CI/CD via SARIF DevOps and security teams can run repository forensics during pull request evaluations to generate standardized SARIF reports. These reports integrate into GitHub Advanced Security or other vulnerability dashboards for automated review.

Use Case: Validating Multi-Engine Agent Configurations Engineering teams managing mixed environments can maintain consistent verification rules across Claude, Codex, and Cursor plugin interfaces from a single shared configuration standard.

Who it is for

Repo Forensics is designed for DevSecOps engineers, maintainers, and security-conscious developers orchestrating multi-agent AI coding pipelines across Claude, Codex, and Cursor. It is less relevant for individual developers looking for a simple, single-prompt conversational chat interface.

Install guide

Installation Clone the repository directly from GitHub to configure the agent plugins: bash git clone https://github.com/alexgreensh/repo-forensics.git cd repo-forensics Note: Python 3.10+ is standard for running the bundled diagnostic and SARIF export scripts.

First Run Verify release signatures and check the health of installed agent plugins: bash python3 -m unittest discover tests/ python3 sarif_export.py --help Link the relevant plugin configuration (.claude-plugin, .cursor-plugin, or .codex-plugin) into your respective agent environment.

Example Session Generate a SARIF security report from repository analysis: bash python3 sarif_export.py --output results.sarif

Part of CLI Coding Agents

Categories: AI Coding Agents, Code Assistants, Developer Tools

Related CLI agents

• Grite — Grite is an open-source terminal coding agent harness developed by Neul Labs. Implemented in Rust, it provides a lightweight command-line…
• Mneme — Mneme is an open-source orchestration harness and memory governance framework developed by MnemeHQ designed to prevent architectural drift across the…
• Zosma QA — Zosma QA is an open-source testing-focused agent harness and orchestration framework created by Zosma AI. It provides scaffolding, structured prompt…
• Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
• Agent Memory System — Agent Memory System is an open-source agent orchestration harness developed by RavByte-AI. It provides structured memory retention and retrieval mechanisms…
• Flameox — Flameox is an open-source coding agent harness and orchestration framework maintained by morluto. Built to support hybrid development workflows across…