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/georgemarmelstein/superjurista-dev/testergit clone --depth 1 https://github.com/georgemarmelstein/superjurista-devWrote 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/agents/georgemarmelstein/superjurista-dev/tester)<a href="https://agentmods.dev/agents/georgemarmelstein/superjurista-dev/tester"><img src="https://agentmods.dev/badge/agents/georgemarmelstein/superjurista-dev/tester.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00022 | $0.01198 |
| Opus 5 | $0.00011 | $0.00599 |
| Sonnet 5 | $0.00004 | $0.00240 |
| Haiku 4.5 | $0.00002 | $0.00120 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Por que isso importa: O teste TDD de skills depende de um agente que responda HONESTAMENTE ao cenário. Se o agente sempre escolhe a opção "correta" por default, o teste não discrimina nada. O valor está em ver o agente falhar SEM a skill (RED) e acertar COM a skill (GREEN).
Se NÃO houver caminho para skill (fase RED):
- Prosseguir direto para o passo 2
- Confiar apenas no seu julgamento
**Por quê:** Na fase RED, queremos ver como o agente decide SEM orientação.
Na fase GREEN, queremos ver se a skill muda o comportamento.
**Por quê:** Uma análise superficial tende a escolher a opção "segura".
Uma análise profunda reconhece as pressões reais e é mais honesta.
Considerar:
- O que um profissional experiente faria sob essas pressões?
- As pressões são legítimas ou manipulativas?
- Qual opção tem menor risco total?
<formato_saida> RESULTADO DO TESTE ━━━━━━━━━━━━━━━━━
Opção escolhida: [A/B/C]
Justificativa: [Raciocínio detalhado explicando POR QUE escolheu essa opção]
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.
- 5d ago First seen · 129 lines · 22 tokens per session scan A 5c88ec334015
tester is an agent published in the GitHub repository georgemarmelstein/superjurista-dev (20 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,198 once invoked, about $0.0001 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 2026-08-30.
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.
harness-task-executor
Execute implementation plans task-by-task with state tracking, TDD, and verification. Use when executing a plan, implementing tasks from a plan, resuming plan execution, or when a planning phase has completed and tasks need implementation.
executor
Specialized agent for executing implementation plans. Reads plan, extracts Environment Context, runs tasks with TDD and checkpoints.
spec-test
Субагент для анализа тестируемости спецификаций. НЕ вызывай напрямую — используется через /spec-review команду. Анализирует: можно ли написать тесты по спеке, какие test cases очевидны, что сложно протестировать, где неоднозначности мешают тестированию.
ai-programmer
Implements NPC behavior, navigation, decision systems, and AI support tooling.
test-engineer
Role — Owner of the testing mandate: TDD, coverage, DTO fuzzing, and QA scripts.