agentmods.dev

verify-harness

verify-harness is a skill for Claude Code, Codex from zvadaadam/az-skills. It costs 126 tokens per session (4,232 once invoked), scanned A, original, no licence file.

A repository verification harness: a command-line driver that runs the real application in an isolated session and interacts with it as a person or coding agent would. It also maintains a map of features, their entry points, and ways to prove they work.

In plain words
What is it for?
Use it to set up or maintain end-to-end checks for an application and document how each user-facing feature can be reached and verified.
Why use it?
It gives agents a repeatable way to check the application instead of relying on guesses or temporary scripts. The feature map records what should be tested and what could mislead someone.

Skill for Claude CodeCodex

Which agent this was written for is unclear — body not stored (licence); the path alone says nothing.

not rated 51repo 26d ago A scan 126 tokens no licence

Good fit Use it to set up or maintain end-to-end checks for an application and document how each user-facing feature can be reached and verified.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/zvadaadam/az-skills/verify-harness
View source ↗ zvadaadam/az-skills
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 zvadaadam/az-skills --skill verify-harness
Clone the repo
git clone --depth 1 https://github.com/zvadaadam/az-skills

Made for: Claude Code, Codex.

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 verify-harness

README.md
[![agentmods](https://agentmods.dev/badge/skills/zvadaadam/az-skills/verify-harness/github.svg)](https://agentmods.dev/skills/zvadaadam/az-skills/verify-harness)
Your own site
<a href="https://agentmods.dev/skills/zvadaadam/az-skills/verify-harness"><img src="https://agentmods.dev/badge/skills/zvadaadam/az-skills/verify-harness/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for verify-harness

Your own site · 80×15
<a href="https://agentmods.dev/skills/zvadaadam/az-skills/verify-harness"><img src="https://agentmods.dev/badge/skills/zvadaadam/az-skills/verify-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,232 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin unknown 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 $0.00126 $0.04232
Opus 5.5 $0.00050 $0.01693
Sonnet 5.5 $0.00025 $0.00846
Haiku 4.5 $0.00013 $0.00423

Measured 26d ago against content hash 29d2c7b2abfd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

verify-harness scanned grade A with 1 finding 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 26d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Agents that change a product need to prove the change the way a person would see it. Without a harness they write a fresh Playwright or curl script every task, look at one screenshot, and throw the script away. The next
skills/engineering/verify-harness/SKILL.md · 194 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

Files

What ships with it

5 files 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. 26d ago First seen · 194 lines · 126 tokens per session scan A 29d2c7b2abfd

Subscribe to this mod's changes

verify-harness is a skill published in the GitHub repository zvadaadam/az-skills (51 stars, last pushed 26d ago), with no licence file. It adds 126 tokens to every session and 4,232 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-12.

E2E testingTesting
Related

verify-harness compared with skills from other repositories

verify-harness next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
verify-harnesszvadaadam/az-skillsSkill5126d agononeA126Claude Code, Codex
verify-omnigentomnigent-ai/omnigentSkill11kyesterdayApache-2.0A100Claude Code, Codex
test-masterJeffallan/claude-skillsSkill12k7d agoMITA104Claude Code
eval-dataset-designbojieli/ai-agent-bookSkill57k29d agoApache-2.0A138Claude Code, Codex
dogfoodcallstack/agent-deviceSkill5.3kyesterdayMITA55Claude Code
cua-driverdavidondrej/skillsSkill4.3k3d agoMITA68Claude Code, Codex
test-warp-uiwarpdotdev/warpSkill66kyesterdayAGPL-3.0A55Claude Code