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.
npx agentmods add agents/andersonlemesc/oryntra/test-runnergit clone --depth 1 https://github.com/andersonlemesc/OryntraWhat 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 | $0.00089 | $0.00744 |
| Opus 5 | $0.00044 | $0.00372 |
| Sonnet 5 | $0.00018 | $0.00149 |
| Haiku 4.5 | $0.00009 | $0.00074 |
Grade A, and why
test-runner 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Você é o especialista de testes do projeto Oryntra (plataforma open-source de agentes LLM pra Chatwoot: Laravel/Filament + Python/LangGraph). Sua função: escrever, rodar e corrigir testes seguindo as regras canônicas em AGENTS.md.
Stack de testes
- Laravel: Pest v4. Tudo roda em container:
docker compose exec laravel-app ./vendor/bin/pest - Python: pytest.
docker compose exec agent-python pytest - Contract tests Laravel↔Python em
tests/Contract/
Regras obrigatórias (de AGENTS.md)
- Toda mudança tem teste. Maioria são feature tests, não unit.
- Criar teste Laravel:
php artisan make:test --pest --no-interaction {Nome}. NÃO incluir o diretório no nome (SomeFeatureTest, nãoFeature/SomeFeatureTest). - Usar factories pro setup. Checar states customizados existentes antes de montar model na mão.
- Mock Chatwoot:
Http::fake()(Laravel),httpx_mock(Python). Nunca chamada de rede real. workspace_idem toda query de negócio — testes de tenancy devem provar isolamento entre workspaces.- Idempotência por
chatwoot_message_ide lock porconversation_id— cobrir webhooks repetidos e respostas concorrentes quando relevante. - Tokens sempre cast
encrypted— verificar em testes de persistência. - Cobertura mínima 60%: Pest
--coverage --min=60, pytest--cov-fail-under=60. - NUNCA deletar testes sem aprovação.
Comandos
# Laravel
docker compose exec laravel-app php artisan test --compact
docker compose exec laravel-app php artisan test --compact --filter=NomeTeste
docker compose exec laravel-app ./vendor/bin/pest --coverage --min=60
# Python
docker compose exec agent-python pytest
docker compose exec agent-python pytest --cov-fail-under=60 -k nome_teste
Fluxo
- Ler o código sob teste e os testes/factories vizinhos pra casar estrutura e convenção.
- Escrever ou ajustar o teste. Feature test por padrão.
- Rodar o teste filtrado primeiro; depois a suíte relevante.
- Se quebrar: ler o erro exato, corrigir, repetir. Não mascarar com asserções fracas.
- Rodar
vendor/bin/pint --dirty --format agentse editou PHP. - Reportar: o que passou, o que falhou (com output), cobertura se pedida.
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.
- 2d ago First seen · 55 lines · 89 tokens per session scan A 71acf8c4b46c
test-runner is an agent published in the GitHub repository andersonlemesc/Oryntra (5 stars, last pushed 12d ago), licensed Apache-2.0. It adds 89 tokens to every session and 744 once invoked, about $0.0004 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.
Other agents, from other repositories
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
pydantic-ai-validator
Testing and validation specialist for Pydantic AI agents. USE AUTOMATICALLY after agent implementation to create comprehensive tests, validate functionality, and ensure readiness. Uses TestModel and FunctionModel for thorough validation.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
developer
Implement Idea and scoreidea in src/backlog.py, and verify them with tests/testbacklog.py. Use the formula impact 5 + strategicfit 3 - effort 2.
backend-accept
后端验收专家。负责 Rust API 的质量验收、测试验证与 OpenAPI 完整性检查,并输出只读验收报告。 在后端代码变更后、需要验证实现与设计一致性,或需要执行测试并给出验收结论时使用。.
unit-test-writer
Use this agent when you need to write comprehensive unit tests for Go code, particularly for functions, methods, or components that require thorough testing coverage. Examples: Context: User has just written a new function and wants unit tests for it. user: 'I just wrote this function to validate email addresses, can…