Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ellmos-ai/bachnpx agentmods add skills/ellmos-ai/bach/test-agentWrote 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.
[](https://agentmods.dev/skills/ellmos-ai/bach/test-agent)<a href="https://agentmods.dev/skills/ellmos-ai/bach/test-agent"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/test-agent/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.
<a href="https://agentmods.dev/skills/ellmos-ai/bach/test-agent"><img src="https://agentmods.dev/badge/skills/ellmos-ai/bach/test-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.03051 |
| Opus 5.5 | $0.00013 | $0.01220 |
| Sonnet 5.5 | $0.00007 | $0.00610 |
| Haiku 4.5 | $0.00003 | $0.00305 |
Grade A, and why
test-agent 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 418 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Test-Agent (QA-Agent)
Zweck: Systematisches Testen von BACH und anderen LLM-OS-Systemen Typ: Orchestrator fuer Test- und Vergleichs-Workflows Version: 1.1.0
FAEHIGKEITEN
| Nr | Faehigkeit | Beschreibung |
|---|---|---|
| 1 | Selbsttest | BACH auf Funktionalitaet pruefen |
| 2 | Systemvergleich | Andere Systeme mit BACH vergleichen |
| 3 | Qualitaetsmetriken | Abdeckungskoeffizienten berechnen |
| 4 | Regressionstests | Nach Aenderungen Integritaet pruefen |
| 5 | Synopse erstellen | Vergleichende Analyse dokumentieren |
DREI TESTPERSPEKTIVEN
┌─────────────────┬─────────────────┬─────────────────┐
│ B-Tests │ O-Tests │ E-Tests │
│ BEOBACHTUNG │ AUSGABE │ ERFAHRUNG │
├─────────────────┼─────────────────┼─────────────────┤
│ Extern │ Funktional │ Intern │
│ Automatisiert │ Input->Output │ Subjektiv │
│ Python-Scripts │ Python-Scripts │ Claude-gefuehrt │
│ "Was existiert?"│ "Funktioniert?" │ "Wie fuehlt es?"│
└─────────────────┴─────────────────┴─────────────────┘
VERFUEGBARE TESTS
B-Tests (Beobachtung) - Automatisiert
| ID | Name | Misst |
|---|---|---|
| B001 | file_inventory | Anzahl, Typen, Groessen |
| B002 | format_consistency | Einheitlichkeit |
| B003 | directory_depth | Max/Avg Tiefe |
| B004 | naming_analysis | Namens-Konsistenz |
| B005 | documentation_check | Doku-Vollstaendigkeit |
| B006 | code_metrics | LOC, Komplexitaet |
| B007 | dependencies | Abhaengigkeiten |
| B008 | age_analysis | Letzte Aenderungen |
O-Tests (Ausgabe) - Funktional
| ID | Name | Prueft |
|---|---|---|
| O001 | task_roundtrip | Task CRUD |
| O002 | memory_persistence | Memory Write/Read |
| O003 | tool_registry | Tool finden/nutzen |
| O004 | backup_restore | Backup/Restore |
| O005 | config_validation | Configs parsbar |
| O006 | export_import | Daten ex-/import |
E-Tests (Erfahrung) - Subjektiv
| ID | Name | Erfasst |
|---|---|---|
| E001 | skill_readability | SKILL.md Lesbarkeit |
| E002 | navigation | Dateisystem-Erkundung |
| E003 | task_create | Aufgabe erstellen |
| E004 | task_find | Aufgabe finden |
| E005 | memory_write | Memory schreiben |
| E006 | memory_read | Memory lesen |
| E007 | tool_use | Tool nutzen |
| E008 | error_recovery | Fehler-Recovery |
| E009 | session_start | Session starten |
| E010 | overall_impression | Gesamteindruck |
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.
- 1mo ago Changed 6c32cb0f829e
- 1mo ago First seen · 418 lines · 33 tokens per session scan A 6e5e7e1569ce
test-agent is a skill published in the GitHub repository ellmos-ai/bach (8 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 3,051 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
pydantic-evals
Test and evaluate AI agents and LLM outputs using code-first evaluation framework with strong typing. Use when the user wants to: (1) Create evaluation datasets with test cases for AI agents, (2) Define evaluators (deterministic, LLM-as-Judge, custom, or span-based), (3) Run evaluations and generate reports, (4)…
mcp-tool-developer
Build Model Context Protocol (MCP) servers and tools from scratch. Full-stack MCP development with TypeScript/Python, testing, deployment, and registry publishing.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work. Also covers hosted cloud browsers for AI agents: the browser-use Python library (Browser(usecloud=True)), Playwright, Puppeteer or any CDP client.
accelerate
Run PyTorch training across GPUs with minimal changes.
python-testing
Python testing best practices using pytest including fixtures, parametrization, mocking, coverage analysis, async testing, and test organization. Use when writing or improving Python tests.