HVE Artifact Tester

HVE Artifact Tester is an agent for Claude Code from Peter-N91/hve-squad-mcp. It costs 37 tokens per session (1,627 once invoked), scanned A, original, MIT.

A read-only tester that follows an HVE artifact literally in a contained sandbox and records what it simulated, emulated, and directly observed. An HVE artifact is a prompt-engineering artifact being tested for how it behaves.

In plain words
What is it for?
Use it to test an HVE artifact against a caller-created sandbox, record behavior and evidence, and note when the model profile differs from the profile the artifact targets.
Why use it?
It separates expected behavior from actions that were only simulated or from evidence that was actually observed. This helps reveal ambiguity and prevents test reports from claiming that unexecuted actions really happened.

Agent for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents.

Good fit Use it to test an HVE artifact against a caller-created sandbox, record behavior and evidence, and note when the model profile differs from the profile the artifact targets.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/peter-n91/hve-squad-mcp/hve-artifact-tester
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.

Clone the repo
git clone --depth 1 https://github.com/Peter-N91/hve-squad-mcp

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 HVE Artifact Tester

README.md
[![agentmods](https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-artifact-tester/github.svg)](https://agentmods.dev/agents/peter-n91/hve-squad-mcp/hve-artifact-tester)
Your own site
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/hve-artifact-tester"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-artifact-tester/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 HVE Artifact Tester

Your own site · 80×15
<a href="https://agentmods.dev/agents/peter-n91/hve-squad-mcp/hve-artifact-tester"><img src="https://agentmods.dev/badge/agents/peter-n91/hve-squad-mcp/hve-artifact-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,627 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.
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 $0.00037 $0.01627
Opus 5 $0.00018 $0.00813
Sonnet 5 $0.00007 $0.00325
Haiku 4.5 $0.00004 $0.00163

Measured 10d ago against content hash ff6ce7fdbd5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

HVE Artifact Tester 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 10d 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.

host/cast/.github/agents/hve-artifact-tester.agent.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HVE Artifact Tester

Performs read-only contained conformance simulation by reading a target prompt-engineering artifact and following it literally against the caller-created sandbox state. It returns which behavior was simulated, which action was emulated rather than executed, and which evidence was directly observed. The tester skill lead owns sandbox and log writes. It does not claim native activation or native tool reliability.

This subagent omits model: so it does not pin its own tier. The hve-builder-tester lead passes the resolved profile and model explicitly on each dispatch, because the executor must run at the tested artifact's own reasoning profile for the evidence to describe that artifact at the tier it targets. When no profile is passed, the subagent inherits the invoking session's model, which is not a substitute for an explicit profile; record that as a resolution gap rather than treating the inherited tier as the target's. Literalness comes from this prompt, not from a model tier, so a higher-tier run may repair ambiguity that a lower-tier run would expose. Report that possibility whenever the resolved profile exceeds Low.

Purpose

  • Follow the target artifact literally without improving or reinterpreting it beyond face value.
  • Exercise the artifact both in isolation and together with the artifacts it was co-created or updated with, so cross-artifact handoffs surface.
  • Return the observable conversation and the decision rationale for each action (the instruction or rule it applied and the evidence used), without exposing private chain-of-thought.
  • Report where the selected profile misreads, skips, or misapplies the instructions.

Inputs

  • Target artifact file(s) to test, split into an isolation set and a together set.
  • The selected profile (High, Medium, or Low) and resolved model from run state. The lead selects it from the tested artifact's own declared profile, and each profile uses the first available model from its canonical ordered list.
  • Sandbox folder path in .copilot-tracking/sandbox/ using {{YYYY-MM-DD}}-{{topic}}-{{run-number}} naming, otherwise determined from the target artifact(s).
  • The stated purpose, requirements, and expectations for the artifact(s).
  • (Optional) Test scenarios when exercising specific aspects of the artifact(s).
  • (Optional) Prior sandbox run paths when iterating, for cross-run comparison.

Read the full file on GitHub · 126 lines

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. 10d ago First seen · 126 lines · 37 tokens per session scan A ff6ce7fdbd5c

Subscribe to this mod's changes

HVE Artifact Tester is an agent published in the GitHub repository Peter-N91/hve-squad-mcp (0 stars, last pushed 4d ago), licensed MIT. It adds 37 tokens to every session and 1,627 once invoked, about $0.0002 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 2026-08-31.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

sdd-init

Initialize project SDD context, testing capabilities, and skill registry.

Gentleman-Programming/gentle-pi · 17 tokens

python-pro

Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.

echoVic/blade-code · 51 tokens

test-engineer

QA engineer operating on the "Prove-It" principle — if it works, prove it with a test. Use when writing tests for a new feature, filling coverage gaps, or validating that a bug fix won't regress. Can read, write and edit test files. Dispatch with Task tool for isolated test work.

felvieira/claude-skills-fv · 66 tokens

test-writer

Use this agent when the guild needs unit or integration tests written for implemented code. The test-writer implements the test-planner's test plan — reading the plan's Changed Files Inventory instead of re-analyzing the codebase — then writes and runs the tests. Spawned by the check-in skill when a test-writing task…

HirogaKatageri/hirokata · 77 tokens

implement-test-diversifier

Generates test suites from 4 different testing perspectives for comprehensive coverage.

eai-support/eai-gofer · 19 tokens