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 kju4q · Agent Tool · ★ 71
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is q-agent-harness safe to install? View the security audit →
q-agent-harness Starter kit for building an agent harness that helps AI agents write, test, fix, and ship software more reliably. This repo is built around three ideas: A map Guardrails Feedback loops If an agent cannot find the right context, it guesses. If an agent has no boundaries, it makes risky moves. If an agent cannot see what broke, it cannot improve its own work. What is harness engineering? Harness engineering is the work of building the environment around an AI agent so it can do useful software work on purpose. That environment usually includes: repo docs and architecture notes agent instructions tool permissions and approval points coding and schema boundaries tests and UI validation logs, metrics, and traces The goal is not to write the perfect prompt. The goal is to make good behavior easier for the agent than bad behavior. The 3-part framework Map Give the agent a clear model of the system: what the product does how the repo is organized where business rules live how modules are allowed to depend on each other where to find important scripts, tests, and docs See docs/repo-structure.md.
| Stars | 71 |
| Forks | 11 |
| Language | Python |
| Category | Agent Tool |
| Quality Score | 62.0794577390357/100 |
| Last Updated | 2026-09-03 |
| Created | 2026-05-29 |
| Platforms | claude-code, python |
| Est. Tokens | ~7k |
These tools work well together with q-agent-harness for enhanced workflows:
Looking for a q-agent-harness alternative? If you're comparing q-agent-harness with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
A toolkit that makes Claude Code better at engineering — session memory, dependency analysis, large file navig
DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent
Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f
HeyClaude (formerly Claude Pro Directory) is a searchable collection of pre-built AI skills, agents, MCP serve
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g
Context engineering for coding agents - CLAUDE.md templates, mechanical enforcement, and a field guide to 20+
Explore other popular agent tool tools:
q-agent-harness is Starter kit for building an agent harness, the map, guardrails, and feedback loops that let AI agents ship software reliably.. It is categorized as a Agent Tool with 71 GitHub stars.
q-agent-harness is primarily written in Python. It covers topics such as agent-tooling, ai-agents, ai-engineering.
You can find installation instructions and usage details in the q-agent-harness GitHub repository at github.com/kju4q/q-agent-harness. The project has 71 stars and 11 forks, indicating an active community.
The top alternatives to q-agent-harness on Agent Skills Hub include claude-capsule-kit, deepcontext-mcp, maestro. 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: