eval-harness

eval-harness is a skill for Claude Code from a5c-ai/babysitter. It costs 23 tokens per session (472 once invoked), scanned A, original, MIT.

A test harness for measuring the quality of coding agents and their skills with fixed examples, known answers, regression tests, and scores. A regression test checks that a change has not broken behavior that previously worked.

In plain words
What is it for?
Use it to run benchmarks, compare agents with a baseline, test edge cases, maintain regression suites, and verify complete workflows.
Why use it?
It replaces subjective checks with repeatable comparisons of accuracy, completeness, relevance, consistency, and harmful or incorrect outputs.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to run benchmarks, compare agents with a baseline, test edge cases, maintain regression suites, and verify complete workflows.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/a5c-ai/babysitter/eval-harness
About the project

Babysitter is a workflow engine for AI coding agents that enforces predefined steps, quality checks, human approvals, and decision records. It is used to coordinate complex, repeatable agent workflows across supported coding tools. The catalogue contains skills, agents, instructions, settings, a plugin, and an MCP integration for its workflow.

a5c-ai/babysitter · 1,777 stars · on GitHub · a5c.ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add a5c-ai/babysitter --skill eval-harness
Clone the repo
git clone --depth 1 https://github.com/a5c-ai/babysitter

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for eval-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/a5c-ai/babysitter/eval-harness.svg)](https://agentmods.dev/skills/a5c-ai/babysitter/eval-harness)
Your own site
<a href="https://agentmods.dev/skills/a5c-ai/babysitter/eval-harness"><img src="https://agentmods.dev/badge/skills/a5c-ai/babysitter/eval-harness.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 472 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.00472
Opus 5 $0.00012 $0.00236
Sonnet 5 $0.00005 $0.00094
Haiku 4.5 $0.00002 $0.00047

Measured 4d ago against content hash feafb468c646, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

eval-harness scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

library/methodologies/everything-claude-code/skills/eval-harness/SKILL.md · 70 lines

What it actually says

  • Define test cases with known-correct outputs
  • Run agent against each test case
  • Score: accuracy, completeness, relevance
  • Compare against baseline performance
  • Track performance over time

2. Skill Quality Testing

  • Verify skill instructions produce expected outcomes
  • Test edge cases and boundary conditions
  • Measure consistency across multiple runs
  • Check for harmful or incorrect outputs
  • Validate against ground truth

3. Regression Suite

  • Collection of previously-passing test cases
  • Run after any agent/skill modification
  • Flag regressions with before/after comparison
  • Maintain pass rate threshold (>= 95%)

4. Process Verification

  • End-to-end process execution with known inputs
  • Verify each phase produces expected outputs
  • Check task ordering and dependency satisfaction
  • Measure total execution time

Quality Scoring

Accuracy Score (0-100)

  • Correctness of output vs expected
  • Partial credit for partially correct outputs
  • Penalty for hallucinated or fabricated content

Completeness Score (0-100)

  • Coverage of required output elements
  • Missing sections flagged and scored
  • Bonus for useful additional context

Consistency Score (0-100)

  • Run same input 3 times
  • Compare outputs for semantic similarity
  • Flag inconsistencies

Composite Score

  • (accuracy * 0.4 + completeness * 0.3 + consistency * 0.3)
  • Threshold: 80 to pass

When to Use

  • After creating new agents or skills
  • After modifying existing agents or skills
  • Periodic quality audits
  • Before promoting skills to production

Agents Used

  • Used by process-level evaluation orchestrators
  • No specific agent dependency (evaluates other agents)
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 70 lines · 23 tokens per session scan A feafb468c646

Subscribe to this mod's changes

eval-harness is a skill published in the GitHub repository a5c-ai/babysitter (1,777 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 472 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.