AI Agent Safety Starter Pack

el-zachariah/ai-agent-safety-starter-pack

Free repo preflight scanner for Claude Code, Codex, Cursor, and other AI coding-agent runs that flags agent instructions, MCP config, risky shell patterns, package scripts, and secret-adjacent files before tool access

Python MIT

View on GitHub → Find it in the atlas

Install

git clone https://github.com/el-zachariah/ai-agent-safety-starter-pack.git

Repository reader

Explore before you clone

Read the project’s README, skills and supporting Markdown here. Rendered view is shown first; source is one click away when you need the exact text.

Fetched from GitHub
Open on GitHub
Loading the project’s README…

Public files are loaded on demand from the repository. The atlas does not copy or modify them.

Screenshot

Screenshot or social card for AI Agent Safety Starter Pack
GitHub's social card — no screenshot was found for this project, fetched from source rather than copied into this repository.

Platform support

Derived from the project's own README, install route, CI configuration and release assets — not from running it.
PlatformRuns hereOn what evidence
WindowsLikelyInferred from the language or runtime. Nothing in the project says so.
WSL2LikelyInferred from the language or runtime. Nothing in the project says so.
macOSLikelyInferred from the language or runtime. Nothing in the project says so.
LinuxLikelyInferred from the language or runtime. Nothing in the project says so.
DockerNoNo evidence of support anywhere in the project.

Where it came from

Named by 1 of the 39 lists the atlas merges.

  • AI Coding Tools (a4d)

How it is classified

One topic, 5 harnesses. Each link is a prerendered page of everything else in that slice.

Sandbox, Security & GovernanceClaude CodeClaude / AnthropicMCPCodex / OpenAICursor

Related in Sandbox, Security & Governance

Closest first — projects that plug into the same harnesses, then the ones the most lists agreed on.

  • Node9node9-ai/node9-proxySecurity and governance layer that checks every tool call from coding agents and MCP servers before it runs: credential jail, secret and PII…
  • Brood Boxstacklok/brood-boxRun AI coding agents (Claude Code, Codex, OpenCode) inside hardware-isolated microVMs with snapshot isolation, egress control, and MCP authorization
  • compassdshakes/compassby dshakes - Developer-grade Claude Code + Codex configuration: cost-tiered subagents, workflow commands, guardrail hooks, MCP parity, and an…
  • gate.catBGMLAI/gate.catDeterministic, fail-closed action veto for AI coding agents that blocks irreversible shell commands (rm -rf, DROP TABLE, terraform destroy) and…
  • NVIDIA OpenShellNVIDIA/OpenShellOpen-source policy-driven sandbox runtime for autonomous AI agents, announced at GTC 2026. Enforces security constraints at the kernel level via…
  • SkillPreflightagent-contracts/skill-preflightRead-only pre-install scanner for local and GitHub agent skills, with a 0-100 score across safety, permissions, token cost, and maintainability…
  • whatileakedselan-ai/whatileakedLocal scanner for credentials a coding agent has already written to disk: Claude Code, Codex and Cursor transcripts plus instruction/memory files…
  • Open AgentTh0rgal/orbSelf-hosted control plane for Claude Code with isolated container workspaces and real-time mission streaming