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 sd0xdev · Claude Skill · ★ 188
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is sd0x-dev-flow safe to install? View the security audit →
sd0x-dev-flow Language: English Español The harness layer for Claude Code. Quality gates that AI can't skip. A reference implementation of AI Agent Harness Engineering for Claude Code — hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where it counts. 96 bundled · 96 public skills · 15 agents — 4% of Claude's context window What This Harness Does Harness engineering is the discipline of engineering everything around the LLM — tool loops, context management, hooks, state machines, safety layers — as opposed to training the model itself. Mitchell Hashimoto coined the term in Feb 2026; Anthropic engineering and Martin Fowler have published on it; [arXiv 2603.05344](https://arxiv.org/html/2603.0534
| Stars | 188 |
| Forks | 24 |
| Language | JavaScript |
| Category | Claude Skill |
| License | MIT |
| Quality Score | 73.0994358471049/100 |
| Open Issues | 7 |
| Last Updated | 2026-08-14 |
| Created | 2026-01-30 |
| Platforms | claude-code, codex, node |
| Est. Tokens | ~19k |
Looking for a sd0x-dev-flow alternative? If you're comparing sd0x-dev-flow 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.
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
The minimal interpretable model router that learns & adapts to your agent workflows
Empower agents with professional capabilities in specific fields (such as full-stack development, complex logi
🥇 The strongest free web search plugin for DeepSeek Harness, and the search bridge for every model without na
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an
Local-first policy, evidence, memory, and recovery controls for Claude, Codex, Hermes, and other CLI coding ag
Explore other popular claude skill tools:
sd0x-dev-flow is The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual review, state-machine gates that survive context compaction, and fail-closed safety where . It is categorized as a Claude Skill with 188 GitHub stars.
sd0x-dev-flow is primarily written in JavaScript. It covers topics such as agent-harness, claude-code, claude-code-plugin.
You can find installation instructions and usage details in the sd0x-dev-flow GitHub repository at github.com/sd0xdev/sd0x-dev-flow. The project has 188 stars and 24 forks, indicating an active community.
sd0x-dev-flow is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to sd0x-dev-flow on Agent Skills Hub include maestro, bitrouter, antigravity-skills. 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: