harness-forge — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 001TMF · Claude Skill · ★ 76

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

🔒 Is harness-forge safe to install? View the security audit →

About harness-forge

Turn Claude Code into its own Meta-Harness — evolve the scaffolding around a fixed model, natively. -555) Harness Forge is a Claude Code skill that runs an end-to-end harness-optimization loop — propose → score → keep the Pareto-best → repeat — to improve the code around a fixed model: its memory, retrieval, context construction, summarization, prompt templates, and tool-selection logic. The model never changes; the scaffolding gets better. It is a native reimplementation of the method in Meta-Harness: End-to-End Optimization of Model Harnesses (Lee, Nair, Zhang, Lee, Khattab & Finn, 2026). The original reference repo ships 1,260 lines of Python ( + ) whose job is to drive a headless Claude: spawn a session, parse its output, track tool calls, log everything, loop. Inside Claude Code, that runtime already exists as first-class tools. So Harness Forge keeps only the irre

agent-skillsagentsclaude-codeclaude-skillllmmeta-harnesspareto-optimizationprompt-optimization

Quick Facts

Stars76
Forks7
LanguagePython
CategoryClaude Skill
LicenseMIT
Quality Score68.039501918338/100
Last Updated2026-06-14
Created2026-06-14
Platformsclaude-code, python
Est. Tokens~12k

harness-forge alternative? Top 6 similar tools

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

  • prompt-architect by ckelsoe · ⭐ 299

    Claude Code skill that transforms vague prompts into structured, expert-level prompts using 7 research-backed

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

  • claudepro-directory by JSONbored · ⭐ 217

    HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve

  • mcp-image by shinpr · ⭐ 161

    MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Support

  • claude-code-settings by nokonoko1203 · ⭐ 93

    Best Practices for Claude Code Configuration

  • openclaw-optimization-guide by OnlyTerp · ⭐ 377

    Make your OpenClaw AI agent faster, smarter, and cheaper. Speed optimization, memory architecture, context man

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular Python Agent Tools

Frequently Asked Questions

What is harness-forge?

harness-forge is Turn Claude Code into its own Meta-Harness — a skill that evolves the scaffolding around a fixed model (memory, retrieval, context, prompts) via a native propose→score→Pareto loop. Native reimplementa. It is categorized as a Claude Skill with 76 GitHub stars.

What programming language is harness-forge written in?

harness-forge is primarily written in Python. It covers topics such as agent-skills, agents, claude-code.

How do I install or use harness-forge?

You can find installation instructions and usage details in the harness-forge GitHub repository at github.com/001TMF/harness-forge. The project has 76 stars and 7 forks, indicating an active community.

What license does harness-forge use?

harness-forge is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to harness-forge?

The top alternatives to harness-forge on Agent Skills Hub include prompt-architect, skill-conductor, claudepro-directory. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

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:

View on GitHub → Browse Claude Skill tools