No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by hoangnb24 · Claude Skill · ★ 1.2k
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is repository-harness safe to install? View the security audit →
repository-harness Turn any software repo into an agent-ready workspace. is a repository-level operating harness for Claude Code, Codex, Cursor, and other coding agents. It gives agents the missing project context they need before they change code: where to start, what the product contract says, how risky the work is, what proof is required, and which decisions future agents should inherit. The app is what users touch. The harness is what agents touch. Why Star This Repo Star this repo if you want practical, reusable patterns for making AI-assisted software development more reliable, inspectable, and easier for humans to steer. This project is exploring a simple idea: Coding agents do not only need better prompts. They need better repositories. The Problem Most repos are built for humans reading code in a familiar codebase. Coding agents usually enter with only a chat prompt and a shallow snapshot of files. That leads to common failure modes: The agent edits code before understanding product intent. Important constraints live only in chat history or in someone's head. Validation expectations are vague or discovered too late.
| Stars | 1,243 |
| Forks | 440 |
| Language | Rust |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 67.5346371354039/100 |
| Last Updated | 2026-10-04 |
| Created | 2026-05-05 |
| Platforms | claude-code, codex, rust |
| Est. Tokens | ~24k |
These tools work well together with repository-harness for enhanced workflows:
Looking for a repository-harness alternative? If you're comparing repository-harness with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Professional context and harness engineering for Claude Code and OpenAI Codex. Build production-grade software
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
Claude Code learns from your corrections: self-correcting memory that compounds over 50+ sessions. Context eng
The definitive resource for Agent Skills - modular capabilities revolutionizing AI agent architecture
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, com
Explore other popular claude skill tools:
repository-harness is Turn any repo into an agent-ready workspace for Claude Code, Codex, Cursor, and other coding agents.. It is categorized as a Claude Skill with 1.2k GitHub stars.
repository-harness is primarily written in Rust. It covers topics such as agents-md, ai-agents, ai-assisted-development.
You can find installation instructions and usage details in the repository-harness GitHub repository at github.com/hoangnb24/repository-harness. The project has 1.2k stars and 440 forks, indicating an active community.
repository-harness is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to repository-harness on Agent Skills Hub include pilot-shell, ok-skills, pro-workflow. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: