AgentLint is an open-source repository linting, validation, and workflow enforcement harness developed by 0xmariowu. It is designed to enforce structural consistency, security hygiene, and verification gates across repositories utilizing AI agent workflows and automated pipelines. In day-to-day operations, AgentLint operates as both a command-line utility and an automated GitHub Action distributed via the GitHub Marketplace. It inspects repository configurations, branch protection templates, and test-pairing setups while integrating with agent configurations (such as Claude plugins) and isolated execution environments like E2B for testing agent scenarios. AgentLint differentiates itself from general-purpose linters by focusing on fail-closed automation gates for agentic development. Rather than allowing unconfigured branch protection or unasserted check contexts to silently pass, it strictly verifies check-run satisfaction, blocks template configuration drift, and enforces safe dependency execution defaults like --ignore-scripts. The tool is distributed under an open-source repository model on GitHub, providing tagged releases and GitHub Action integrations for automated CI/CD pipelines.
GitHub Action Integration — Integrates directly into GitHub CI/CD workflows via the GitHub Marketplace. - Fail-Closed Branch Protection Gating — Enforces strict check requirements during releases and merges to prevent unverified bypasses. - Template Drift Guards — Verifies synchronization between local branch protection templates and active GitHub check contexts. - Test Pairing Validation — Enforces check-test pairing across pull requests and squash-merged commits. - Claude Plugin Support — Includes repository configuration structures (.claude-plugin) for Anthropic Claude integration. - E2B Sandbox Integration — Supports running behavioral scenarios and subprocess verification within isolated E2B environments. - Safe Execution Defaults — Defaults to flags like --ignore-scripts during setup and execution to prevent unsafe lifecycle scripts.
Use cases
Use Case: CI/CD Quality Gating for Agent PRs Maintainers add AgentLint as a GitHub Action to ensure automated agent contributions and team PRs satisfy required check contexts and test pairing before merging to the main branch.
Use Case: Branch Protection and Release Hardening DevOps teams run AgentLint during release pipelines to detect template drift between branch protection YAML definitions and live GitHub repository settings, failing closed if checks are missing.
Use Case: Agent Scenario Testing in Sandboxes Developers configure AgentLint with E2B environments to run automated behavioral checks and scenario tests on agent tools without risking local system modifications.
Who it is for
AgentLint is built for DevOps engineers, open-source maintainers, and developers managing repositories with automated AI agent workflows and strict CI/CD pipelines. It is not designed for developers looking for an interactive conversational coding agent, but rather for those needing quality and security harness tooling to govern agentic contributions.
Install guide
Installation Add AgentLint to your GitHub Actions workflow or install the CLI tool locally using Node.js packaging: bash # Install CLI locally (standard Node.js package method) npm install -g agentlint Or reference it directly in your .github/workflows/agentlint.yml: yaml name: AgentLint on: [push, pull_request] jobs: lint: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: 0xmariowu/AgentLint@v1
First Run Initialize repository configurations and branch protection templates: bash agentlint setup Configure optional environment keys if running sandbox scenarios: bash export E2B_API_KEY="your-e2b-api-key"
Example Session Run the test registry consistency and drift check: bash # Run consistency checks against templates and test pairings agentlint check
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agent Runbook — Agent Runbook is an open-source contract-based multi-agent skill framework developed by KnoxOps. It acts as an orchestrator and compiler that…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Context Bridge — Context Bridge is an open-source CLI agent harness and context orchestration utility developed by serdardb. It is built to facilitate…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…