Install
npm install -g harness-score # global binaryRepository 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.
Public files are loaded on demand from the repository. The atlas does not copy or modify them.
Screenshot
Platform support
| Platform | Runs here | On what evidence |
|---|---|---|
| Windows | Likely | Inferred from the language or runtime. Nothing in the project says so. |
| WSL2 | Likely | Inferred from the language or runtime. Nothing in the project says so. |
| macOS | Likely | Inferred from the language or runtime. Nothing in the project says so. |
| Linux | Likely | Inferred from the language or runtime. Nothing in the project says so. |
| Docker | No | No evidence of support anywhere in the project. |
Where it came from
No curated list names this project yet: the atlas found it through its own GitHub search, which adds fast-rising agentic repositories before a list catches up.
How it is classified
One topic, 1 harness. Each link is a prerendered page of everything else in that slice.
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…
- AI Agent Safety Starter Packel-zachariah/ai-agent-safety-starter-packFree repo preflight scanner for Claude Code, Codex, Cursor, and other AI coding-agent runs that flags agent instructions, MCP config, risky shell…
- Dippyldayton/Dippyby Lily Dayton - Auto-approve safe bash commands using AST-based parsing, while prompting for destructive operations. Solves permission fatigue…
- gate.catBGMLAI/gate.catDeterministic, fail-closed action veto for AI coding agents that blocks irreversible shell commands (rm -rf, DROP TABLE, terraform destroy) and…
- Gryphsafedep/gryphby SafeDep - Gryph is a security layer for AI coding agents. It hooks into Claude Code and enforces YAML policy rules that block, warn, or guide…
- NVIDIA OpenShellNVIDIA/OpenShellOpen-source policy-driven sandbox runtime for autonomous AI agents, announced at GTC 2026. Enforces security constraints at the kernel level via…
- repo-agent-scansunxiayi/repo-agent-instruction-security-scanLocal deterministic scanner for agent skills and repository instruction files (SKILL.md, AGENTS.md, CLAUDE.md, and IDE rules), with…
- whatileakedselan-ai/whatileakedLocal scanner for credentials a coding agent has already written to disk: Claude Code, Codex and Cursor transcripts plus instruction/memory files…