Agent Harness
Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is vibe-checked, before shipping a prompt or model change, or when evals drift.
Install
/plugin marketplace add borghei/Claude-SkillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add borghei/Claude-Skills --skill agent-harnessgit clone --depth 1 https://github.com/borghei/Claude-Skills.git /tmp/Claude-Skills
mkdir -p ~/.claude/skills
cp -r /tmp/Claude-Skills/engineering/agent-harness ~/.claude/skills/agent-harnessPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Agent Harness Most agents ship on vibes: someone tries eight prompts, the output looks good, it goes to production, and the next prompt tweak silently breaks a refusal nobody re-tested. This skill builds the harness around an agent so its behaviour becomes measurable — scenario suites with structural assertions, deterministic replay of recorded tool calls, paired regression diffing across prompt and model changes, and per-scenario cost and latency budgets. The tools here score an agent; they never invoke one, so they run offline on every commit. ## When to use this skill - An agent is going to production and the only quality evidence is manual spot-checking - A prompt, tool schema, or model version is changing and you need to know what broke - Two model or configuration options need a defensible comparison, not a demo - An incident happened and you need the behaviour encoded as a permanent regression test - Agent cost or latency is climbing across releases and nobody can point to when - An existing eval suite reports a healthy pass rate that nobody trusts ## Inputs the skill expects - The agent's tool inventory — names, arguments, and which tools are irreversible - Recorded transcripts per scenario: tool calls, final output, turns, latency, cost, error state - The behavioural rules the agent must hold (refusals, escalation triggers, policy boundaries) - Known failure history — past incidents, customer complaints, internal bug reports
Details
- Skill name
agent-harness- Repository
- borghei/Claude-Skills
- Path
engineering/agent-harness/SKILL.md- Repo updated
- 8 November 2026
- Listed in
- BehiSecc/awesome-claude-skills
FAQ
What does the Agent Harness skill do?
Test and evaluation harness for AI agents — scenario suites, deterministic replay, regression diffing, cost and latency budgets. Use when agent quality is vibe-checked, before shipping a prompt or model change, or when evals drift.
How do I install the Agent Harness skill?
Claude Code plugin: /plugin marketplace add borghei/Claude-Skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Agent Harness popular?
It lives in borghei/Claude-Skills, which has 1,157 GitHub stars and 217 forks, and is included in 1 curated skill list.
Related skills
Cto Advisor
1.2kborghei/Claude-Skills
Technical leadership guidance for engineering teams, architecture decisions, and technology strategy. Use when assessing technical debt, scaling engineering teams, evaluating technologies, or making architecture decisions.
Customer Success Manager
1.2kborghei/Claude-Skills
Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success
Financial Analyst
1.2kborghei/Claude-Skills
Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making
Agent Protocol
1.2kborghei/Claude-Skills
Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.
Agent Designer
1.2kborghei/Claude-Skills
Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent performance.
Agent Workflow Designer
1.2kborghei/Claude-Skills
Designs multi-agent workflow DAGs (routing, hand-offs, state, retries) and validates and costs them before build. Use when planning a pipeline of specialised agents, fan-out/fan-in, or a lead with subagents.
Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.