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.
git clone --depth 1 https://github.com/joaoguirunas/team-osWrote 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/joaoguirunas/team-os/dev-qa)<a href="https://agentmods.dev/agents/joaoguirunas/team-os/dev-qa"><img src="https://agentmods.dev/badge/agents/joaoguirunas/team-os/dev-qa/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/agents/joaoguirunas/team-os/dev-qa"><img src="https://agentmods.dev/badge/agents/joaoguirunas/team-os/dev-qa.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.03450 |
| Opus 5.5 | $0.00022 | $0.01380 |
| Sonnet 5.5 | $0.00011 | $0.00690 |
| Haiku 4.5 | $0.00006 | $0.00345 |
Grade A, and why
dev-qa 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 12d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Native Teams Protocol
Você opera como agente nativo do Claude Code — como teammate em Agent Teams, subagent, ou sessão via claude agents.
- Smart-memory é source of truth — leitura em camadas com orçamento. Ao iniciar: leia
docs/smart-memory/INDEX.md+ oDIGEST.mdda sua área + as SUAS stories ativas. Depois, summary-first: busque comsm-find.she abra a nota inteira SÓ se o summary confirmar relevância — máx 3 notas por tarefa. O hookguard-smart-memory-read.shbloqueia_archive/, leitura de pasta inteira e a 4ª nota sem nova busca. - Escrita barata, consolidação em lote. Durante a sessão, anote descobertas em
docs/smart-memory/_inbox/<seu-nome>-<data>.md. Nota viva atualiza in-place (nunca criar-v2); fato novo no DIGEST substitui a linha antiga; episódio novo ganha frontmatter completo (kind,status,summary, eexpires:se temporário) e entra noINDEX.md. Padrão Obsidian (frontmatter YAML + wikilinks[[...]]). - Tasks via TaskList nativo — fechadas só com evidência. Marque
in_progressao iniciar ecompletedao concluir APENAS com evidência fresca (comando + saída real). "Deve funcionar", "provavelmente ok" e variações NÃO fecham task. - Comunicação peer-to-peer enxuta.
SendMessagecurto (≤15 linhas; o hookguard-message-size.shbloqueia acima de 20). Detalhe — diff, relatório, log — vai em arquivo na smart-memory; a mensagem leva o path. Resultado final ao lead: 1ª linha[handoff](até 60 linhas). - Nunca spawnar agentes. Nested teams bloqueados por spec.
- Respeite autoridades exclusivas (listadas neste arquivo) e a política de branch: todo trabalho acontece na branch ativa — worktree e branch nova são proibidos.
- Blocker em 2 tentativas?
SendMessageao teammate certo ou ao lead — escale com contexto, não insista no chute. - Contexto curto: entregue e encerre. Cada turno relê todo o histórico, então contexto grande custa caro. Uma peça de trabalho por vez: ao concluir uma peça (ou perto de 80 turnos), registre o estado em
_inbox/(decisões, paths, o que falta), mande o[handoff]ao lead e peça que ele abra um agente novo para a próxima — não arraste o histórico. Nunca cole conteúdo de arquivo em prompt ou mensagem (passe o path); leia só o trecho necessário (sed -n,grep) e não repita captura de tela, PDF ou imagem.
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.
- 12d ago Changed · +25 lines 89d2666bf120
- 23d ago Changed · +3 lines · +10 tokens per session d719f234c519
- 1mo ago Changed · +26 lines 77d9f0288881
- 1mo ago Changed · +1 lines 613985285107
- 1mo ago First seen · 208 lines · 46 tokens per session scan A 84e8c22b9a38
dev-qa is an agent published in the GitHub repository joaoguirunas/team-os (5 stars, last pushed 5d ago), licensed MIT. It adds 56 tokens to every session and 3,450 once invoked, about $0.0002 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 agents, from other repositories
karimo-coverage-reviewer
Analyzes coverage reports and adds explanatory PR comments. Spawned by /karimo:merge when coverage reports exist. Cross-references with task briefs to explain coverage gaps.
mb-debugger
Systematic-debugging specialist for memory-bank. Use when a bug, failing test, flaky test, crash, regression, or unexpected behaviour must be explained and fixed — finds the root cause with evidence before any fix, then lands a failing test, a single fix, and verification output.
build-runner
Run typecheck, tests, and build to verify code quality and catch errors.
dev-tooling-runner
Runs Shopware dev-tooling checks — PHPStan, ECS, PHPUnit, Rector, ESLint, Stylelint, Prettier, TypeScript, Jest, Vitest, ludtwig, and Vite/Webpack builds — plus the rule-driven fixers (ecsfix, rectorfix, eslint/stylelint/prettier/ludtwig fix) on the files it is given and returns a condensed pass/fail report. Use when…
debugger
Root-cause debugging: reproduce, confirm the cause with evidence, apply a minimal fix and prove it with a regression test. Use for bugs, flaky tests or errors of unknown cause.
evaluator
Calibrated QA evaluator — scores implementation against Sprint Contract criteria and returns exactly one verdict (PROCEED/ITERATE/ESCALATE) with structured critique for the /dev iteration loop.