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 skills add fazer-ai/agents-skills --skill agents-operationgit clone --depth 1 https://github.com/fazer-ai/agents-skillsWrote 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/fazer-ai/agents-skills/agents-operation)<a href="https://agentmods.dev/skills/fazer-ai/agents-skills/agents-operation"><img src="https://agentmods.dev/badge/skills/fazer-ai/agents-skills/agents-operation/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/fazer-ai/agents-skills/agents-operation"><img src="https://agentmods.dev/badge/skills/fazer-ai/agents-skills/agents-operation.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 | $0.00118 | $0.00956 |
| Opus 5 | $0.00059 | $0.00478 |
| Sonnet 5 | $0.00024 | $0.00191 |
| Haiku 4.5 | $0.00012 | $0.00096 |
Grade A, and why
agents-operation 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 9d 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 — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Modo operação do fazer.ai agents
Pega uma instância já em produção que está se comportando de forma inesperada e leva de "a conversa do cliente deu errado" até "causa entendida, ajuste validado e aplicado com aprovação". Audiência: operador de uma instância viva. Para subir uma instância nova use agents-onboarding; para mexer no código-fonte use agents-dev.
⚠️ Segurança de produção (lê primeiro)
Este modo inverte o fence do onboarding: lá o alvo é uma VPS de teste e "nada de produção"; aqui o alvo é produção.
- Investigação read-only é livre (ler conversas, logs, traces, config do agente, queries de leitura). Mutação não.
- Toda mudança precisa de OK explícito do usuário para aquela mudança específica. Autorização a um objetivo (corrigir um comportamento) não é autorização para escolher o método nem para aplicar sozinho. Proponha o diff/ajuste e espere o aval.
- Nunca editar o DB de produção direto para mudar estado da aplicação: use a UI/API/console da própria app (editor de agente, write tools de MCP dry-run por padrão). Write direto no DB fura o passo de publish/validação da app.
- Sem segredo em log, output ou commit; mascarar ao exibir.
O fluxo (references)
Siga em ordem; cada etapa é uma reference. Leia a da etapa antes de executá-la.
references/00-production-safety.md: a postura invertida: read-only livre, toda mutação aprovada item a item, nunca DB direto, dry-run por padrão. Lê primeiro.references/01-diagnose.md: localizar a conversa (display_id), ler oExecutionLog(/logs), traces no Langfuse, config do agente: isolar qual estágio (stt/embed/generate/tts/split/handoff) divergiu.references/02-reproduce.md: reconstituir o turno no playground (modelo real, isolado da conversa real).references/03-adjust.md: corrigir na camada certa: prompt, grants (replace-the-set), behavior, grounding/KB. Console ou MCP (dry-run primeiro).references/04-validate-and-apply.md: re-validar no playground, conversa de teste controlada (Inbox API) quando fizer sentido, aplicar só com aprovação (audit cobre o write).references/05-load-sim.md: (opcional) simular N clientes concorrentes (Inbox API,scripts/simulate-load.py) pra validar carga + que as ferramentas disparam; contorna o/testeativando cada conversa. Use pra estresse ou pra reproduzir bug que só aparece com concorrência.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 44 lines · 118 tokens per session scan A 19497b60486d
agents-operation is a skill published in the GitHub repository fazer-ai/agents-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 118 tokens to every session and 956 once invoked, about $0.0006 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 skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.