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.

1,157 stars 217 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add borghei/Claude-Skills

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add borghei/Claude-Skills --skill agent-harness
Manual install
git 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-harness

Personal 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
Read the full skill on GitHub

Details

Skill name
agent-harness
Path
engineering/agent-harness/SKILL.md
Repo updated
8 November 2026

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

1.2k

borghei/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.

Software DevelopmentIn 1 list217

Customer Success Manager

1.2k

borghei/Claude-Skills

Monitors customer health, predicts churn risk, and identifies expansion opportunities using weighted scoring models for SaaS customer success

Marketing, Sales & BusinessIn 1 list217

Financial Analyst

1.2k

borghei/Claude-Skills

Performs financial ratio analysis, DCF valuation, budget variance analysis, and rolling forecast construction for strategic decision-making

Finance & CryptoIn 1 list217

Agent Protocol

1.2k

borghei/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.

AI, LLMs & AgentsIn 1 list217

Agent Designer

1.2k

borghei/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.

AI, LLMs & AgentsIn 1 list217

Agent Workflow Designer

1.2k

borghei/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.

AI, LLMs & AgentsIn 1 list217

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.