sd0x-harness: The harness layer for Claude Code — a reference implementation of harness engineering with hook-enforced dual

by sd0xdev · Claude Skill · ★ 196

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

Featured in: Claude Code Hooks, Subagents & Statusline

Security audit verdict: SAFE · quality 69/100

None of the 44 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

🧪 Tested by Agent Skills Hub

One of 12 tools we ran end to end on the same task for our Claude Code Hooks, Subagents & Statusline page (2026-10-10).

Result: A development workflow (edit guards, review loops), not a command guard. · stopped 0 of 8 risky actions with prompts skipped · with prompts kept: 7 of 8 stopped, 1 of 4 ordinary actions through without a prompt

See all 12 actions → · See the whole test →

agent-harnessclaude-codeclaude-code-plugincodexharness-engineeringskills

Quick Facts

Stars196
Forks28
LanguageJavaScript
CategoryClaude Skill
LicenseMIT
Quality Score69/100
Open Issues6
Last Updated2026-11-16
Created2026-01-30
Platformsclaude-code, codex, node
Est. Tokens~21k

About sd0x-harness

sd0x-dev-flow Language: English Español The harness layer for Claude Code. Let the model choose the path. Keep "done" verifiable. v4 gives Claude discretion inside a closed, test-pinned anchor set; hooks are digest-bound reminders that survive compaction, and Codex reviews independently. Full control plane on Claude Code. Skills-only distribution for Codex CLI and other compatible agents.

Compatible Skills

These tools work well together with sd0x-harness for enhanced workflows:

  • superloopy — semantic(0.32)+complementary+same_lang+similar_pop+shared_platform (61%)
  • better-harness — semantic(0.31)+complementary+same_lang+similar_pop+shared_platform (61%)
  • hyper-waterfall — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
  • oh-my-hi — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)
  • session-orchestrator — semantic(0.24)+complementary+same_lang+similar_pop+shared_platform (59%)

sd0x-harness alternative? Top 6 similar tools

Looking for a sd0x-harness alternative? If you're comparing sd0x-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.

  • bitrouter by bitrouter · ⭐ 239

    elastic inference for your agentic workloads

  • maestro by ReinaMacCredy · ⭐ 235

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • entroly by juyterman1000 · ⭐ 488

    Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, an

  • mcp-linker by milisp · ⭐ 345

    Manage MCP servers, skills and plugins across Claude Code, Codex, Cursor and more. Built-in marketplace, one-c

  • lacp by 0xNyk · ⭐ 308

    Local-first policy, evidence, memory, and recovery controls for Claude, Codex, Hermes, and other CLI coding ag

  • mcp by taskade · ⭐ 170

    🤖 Official Taskade MCP server and agent plugin. Connect Claude, Cursor, Codex and other MCP clients to your T

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. 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:

View on GitHub → Browse Claude Skill tools