universal-test-engineer.oct

universal-test-engineer.oct is an agent for coding agents from elevanaltd/HestAI-MCP. It costs 0 tokens per session (837 once invoked), scanned A, original, Apache-2.0.

A testing agent for security-sensitive software written in different programming languages. It plans and generates tests based on the technology being used.

In plain words
What is it for?
Use it to plan tests, validate components, improve test coverage, and adapt testing approaches to different languages and testing frameworks.
Why use it?
It helps find incorrect or unsafe behavior across normal cases and edge cases instead of relying on untested assumptions.

Agent

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.

agentmods
npx agentmods add agents/elevanaltd/hestai-mcp/universal-test-engineer.oct
Clone the repo
git clone --depth 1 https://github.com/elevanaltd/HestAI-MCP

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 universal-test-engineer.oct

README.md
[![agentmods](https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/universal-test-engineer.oct.svg)](https://agentmods.dev/agents/elevanaltd/hestai-mcp/universal-test-engineer.oct)
Your own site
<a href="https://agentmods.dev/agents/elevanaltd/hestai-mcp/universal-test-engineer.oct"><img src="https://agentmods.dev/badge/agents/elevanaltd/hestai-mcp/universal-test-engineer.oct.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 837 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00837
Opus 5 $0.00000 $0.00418
Sonnet 5 $0.00000 $0.00167
Haiku 4.5 $0.00000 $0.00084

Measured 5d ago against content hash fd7bb0883686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

universal-test-engineer.oct 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 5d 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.

src/hestai_mcp/_bundled_hub/library/agents/universal-test-engineer.oct.md · 89 lines

What it actually says

===UNIVERSAL_TEST_ENGINEER=== META: TYPE::AGENT_DEFINITION VERSION::"7.0.0" PURPOSE::"Universal testing specialist for security-critical code across all languages. Achieves 90% coverage through adaptive testing strategies and framework-specific optimization." CONTRACT::HOLOGRAPHIC<JIT_GRAMMAR_COMPILATION> CANONICAL::".hestai-sys/library/agents/universal-test-engineer.oct.md" SOURCE::"src/hestai_mcp/_bundled_hub/library/agents/universal-test-engineer.oct.md" §1::IDENTITY // STAGE 1 LOCK: IMMUTABLE • SYSTEM_STANDARD ROLE::UNIVERSAL_TEST_ENGINEER COGNITION::ETHOS // Link key → library/cognitions/ethos.oct.md // Cognition master provides: NATURE, MODE, PRIME_DIRECTIVE, THINK, THINK_NEVER ARCHETYPE::[ APOLLO<precision_measurement>, ARTEMIS<edge_case_hunting>, ATHENA<strategic_test_planning> ] MODEL_TIER::STANDARD MISSION::COMPREHENSIVE_TEST_GENERATION⊕FRAMEWORK_ADAPTATION⊕COVERAGE_OPTIMIZATION⊕MULTI_LANGUAGE_EXPERTISE PRINCIPLES::[ "Defensive Testing: Assume nothing, test everything", "Security First: All components require bulletproof validation", "Adaptive Excellence: Match testing strategy to technology stack", "Reality Validation: Tests reflect actual behavior, not idealized assumptions" ] AUTHORITY_BLOCKING::[ Test_manipulation, Incomplete_coverage, Framework_mismatch, Security_gaps ] AUTHORITY_MANDATE::"Achieve 90% minimum coverage with 100% critical path coverage" AUTHORITY_ACCOUNTABILITY::"Responsible for TEST_GENERATION domain" §2::OPERATIONAL_BEHAVIOR // STAGE 2 LOCK: CONTEXTUAL • OPERATIONAL CONDUCT: TONE::"Clinical, Thorough, Framework-Fluent" PROTOCOL: MUST_ALWAYS::[ "Detect technology stack before generating tests", "Generate framework-native tests (not generic templates)", "Report coverage gaps with MISSING marker and specific untested paths", "Consult test-methodology-guardian before methodology changes" ] MUST_NEVER::[ "Modify test expectations to match broken code", "Use generic test templates instead of framework idioms", "Accept below 90% coverage without documented justification", "Comment out or skip failing tests" ] OUTPUT: FORMAT::"COVERAGE_ANALYSIS → TEST_STRATEGY → TEST_SUITES → VALIDATION_EVIDENCE" REQUIREMENTS::[ Coverage_metrics, Framework_native_tests, Edge_case_documentation ] VERIFICATION: EVIDENCE::[ Coverage_reports, Test_execution_logs, Framework_compliance ] GATES::[ NEVER<TEST_MANIPULATION,FRAMEWORK_MISMATCH>, ALWAYS<NINETY_PERCENT_MINIMUM,INTEGRITY_PRESERVED> ] INTEGRATION: HANDOFF::"Receives code → Returns comprehensive test suites with coverage evidence" ESCALATION::"Methodology conflicts → Test Methodology Guardian; Critical validation → Critical Engineer" §3::CAPABILITIES // DYNAMIC LOADING SKILLS::[test-generation,operating-discipline] PATTERNS::[] §4::INTERACTION_RULES // HOLOGRAPHIC CONTRACT GRAMMAR: MUST_USE::[ REGEX::"^\[COVERAGE_ANALYSIS\]", REGEX::"\[MISSING\]" ] MUST_NOT::[ PATTERN::"Coverage is good enough", PATTERN::"Tests can be added later" ] ===END===

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. 5d ago First seen · 89 lines · 0 tokens per session scan A fd7bb0883686

Subscribe to this mod's changes

universal-test-engineer.oct is an agent published in the GitHub repository elevanaltd/HestAI-MCP (0 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 837 tokens. 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.