Langfuse
avivsinai/langfuse-mcp
Investigate AI traces, observations, exceptions, latency, sessions, prompts, datasets, annotation queues, and scores through Langfuse MCP.
Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente.
Install Agents Operation
$ npx skills add fazer-ai/agents --skill agents-operation -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install fazer-ai/agents agents-operation --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agents-operation .claude/skills/agents-operation && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .claude/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operationType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add fazer-ai/agents --skill agents-operation -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install fazer-ai/agents agents-operation --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/agents-operation .agents/skills/agents-operation && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .agents/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fazer-ai/agents --skill agents-operation -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install fazer-ai/agents agents-operation --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/agents-operation .cursor/skills/agents-operation && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .cursor/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/fazer-ai/agents.git --path .claude/skills/agents-operation--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add fazer-ai/agents --skill agents-operation -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install fazer-ai/agents agents-operation --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/agents-operation .gemini/skills/agents-operation && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .gemini/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install fazer-ai/agents agents-operationInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add fazer-ai/agents --skill agents-operation -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/agents-operation .github/skills/agents-operation && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .github/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add fazer-ai/agents --skill agents-operation -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install fazer-ai/agents agents-operation --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/fazer-ai/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/agents-operation .opencode/skills/agents-operation && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "agents-operation" agent skill from https://github.com/fazer-ai/agents/tree/main/.claude/skills/agents-operation into .opencode/skills/agents-operation/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agents-operation", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
agents-operation- GitHub stars
- 118
- Token cost
- ~1.3k tokens
- SKILL.md length
- 544 words
- Files
- 12 (incl. scripts, references)
- Skills in repo
- 3
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente.
- Works in 6 steps: references/00-production-safety.md: a… → references/01-diagnose.md: localizar a… → references/02-reproduce.md: reconstituir… → …
- Tasks that involve LLM observability
- SKILL.md covers ⚠️ Segurança de produção (lê…, O fluxo (references), Guardrails and Skills irmãs
- Runs Python scripts from its folder
What it does
Agents Operation is an agent skill from fazer-ai/agents. Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente. Investiga (conversa no Chatwoot + ExecutionLog/flowlog + traces no Langfuse), reproduz no playground, ajusta o agente (prompt/ferramentas/behavior/KB) e re-valida, com toda mutação aprovada; quando o problema é do produto, redige a issue para o GitHub com o log e o agente exportados. Use quando uma instância JÁ em produção se comporta de forma inesperada (o agente não responde, a ferramenta dá erro, a…
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts and reference files (for example `gotchas.md`, `guardrails.md` and `references/00-production-safety.md`).
It sits in AI & LLM Engineering, covering LLM observability. It works with Model Context Protocol, Langfuse and GitHub. The repository describes itself as: fazer.ai agents. Apache 2.0. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve LLM observability
Example prompts
- “/agents-operation”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- references/00-production-safety.md: a postura invertida: read-only livre, toda mutação aprovada item a item, nunca DB direto, dry-run por…
- references/01-diagnose.md: localizar a conversa (display_id), ler o ExecutionLog (/logs), traces no Langfuse, config do agente: isolar…
- 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, modelo de documento (montado…
- references/04-validate-and-apply.md: re-validar no playground, conversa de teste controlada (Inbox API) quando fizer sentido, aplicar só…
- references/05-load-sim.md: (opcional) simular N clientes concorrentes (Inbox API, scripts/simulate-load.py) pra validar carga + que as…
What it can do on your machine
Read from SKILL.md and the folder at commit 246c664. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Agents Operation loads about 1.3k tokens when it runs, and up to ~11k if it reads all its reference files. Until then it costs about 242 tokens; SKILL.md has 544 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from fazer-ai/agents at commit 246c664, republished under its Apache-2.0 licence (© fazer-ai). 544 words, ~1,311 tokens.
Download SKILL.mdSave it as
.claude/skills/agents-operation/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.- name
- agents-operation
- description
- Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente. Investiga (conversa no Chatwoot + ExecutionLog/flowlog + traces no Langfuse), reproduz no playground, ajusta o agente (prompt/ferramentas/behavior/KB) e re-valida, com toda mutação aprovada; quando o problema é do produto, redige a issue para o GitHub com o log e o agente exportados. Use quando uma instância JÁ em produção se comporta de forma inesperada (o agente não responde, a ferramenta dá erro, a resposta foge do configurado) e precisa de diagnóstico/ajuste, quando o usuário quer testar o agente antes de liberar para clientes, quando quer montar ou ajustar um modelo de documento (orçamento, proposta, recibo) que o agente emite, o que no console só se edita o texto e se constrói pelo MCP, ou quando quer relatar um bug ou pedir uma melhoria do fazer.ai agents. Não é onboarding (subir do zero) nem desenvolvimento de código.
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, modelo de documento (montado pelo MCP: o console só edita o texto). 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.
Show full SKILL.md (200 more words)Show less
Fora do fluxo, manutenção:
references/07-report-issue.md: relatar um bug ou pedir uma melhoria: separar configuração de produto, conferir a versão, procurar issues abertas e fechadas, redigir título e descrição, exportar o log e o agente para anexar (revisados, o repositório é público) e entregar o link da nova issue já preenchida, para o usuário revisar e enviar (o agente nunca cria a issue). Vulnerabilidade vai para support@fazer.ai.references/06-reprice.md: recalcular o custo em dólar das chamadas já gravadas quando uma release corrige o preço de um modelo (scripts/reprice-usage.ts, simulação por padrão,--applysó com OK).
Fronteiras duras em guardrails.md; armadilhas de diagnóstico em gotchas.md.
Guardrails
Resumo (detalhe em guardrails.md):
- Produção-first: read-only livre; toda mutação aprovada item a item; nunca DB de produção direto.
- Dry-run: toda write tool de MCP previewa; aplica só com OK.
- Estilo: PT-BR com acentuação; sem em-dash;
fazer.aiminúsculo.
Skills irmãs
agents-onboarding: subir uma instância nova num VPS (do zero ao agente) e revalidar a infraestrutura de uma que já está no ar. Problema de infraestrutura (serviço fora do ar, Coolify sem acesso ao próprio servidor, deploy ou atualização falhando, DNS/TLS) é com ela; esta skill cuida do comportamento do agente.agents-dev: trabalhar no código-fonte (Free/Full, implementar, gerar imagem).
© fazer-ai, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 11 other files (scripts, references) in .claude/skills/agents-operation of fazer-ai/agents.
- SKILL.md
- gotchas.md
- guardrails.md
- references/00-production-safety.md
- references/01-diagnose.md
- references/02-reproduce.md
- references/03-adjust.md
- references/04-validate-and-apply.md
- references/05-load-sim.md
- references/06-reprice.md
- references/07-report-issue.md
- scripts/simulate-load.py
Open the folder on GitHubat commit 246c664
Compare with similar skills
Agents Operation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Agents Operation this skillfazer-ai/agents | 118 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | |
| Langfuseavivsinai/langfuse-mcp | 113 | 1 repos | ~580 | Automated safety check: Pass | MIT | |
| Debug Issue With Datadoglangfuse/langfuse | 36k | — | ~1.6k | Automated safety check: Pass | Custom licence | |
| Managed Deep Agentslangchain-ai/langchain-skills | 1.3k | — | ~8.7k | Automated safety check: Notes | MIT | |
| Cursor Agents Workflowlangfuse/langfuse | 36k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Create Repo Agentlangfuse/langfuse | 36k | — | ~730 | Automated safety check: Pass | Custom licence |
Similar skills
Debug Issue With Datadog
langfuse/langfuse
Establish root cause by combining Datadog telemetry with the Langfuse repo.
- Official
Managed Deep Agents
langchain-ai/langchain-skills
INVOKE THIS SKILL when building, testing, or deploying Managed Deep Agents in LangSmith.
Cursor Agents Workflow
langfuse/langfuse
Human handoff, Linear branch names, reviewable (non-draft) PRs, the cursor GitHub label, Claude, Greptile, and Codex review comments, preview test steps, proof of work posted on the GitHub PR, and…
Create Repo Agent
langfuse/langfuse
Design, implement, review, or harden Langfuse repo-owned autonomous agents.
Phoenix Release Notes
Arize-ai/phoenix
Create Phoenix release documentation grounded in actual code changes.
More from fazer-ai/agents
Agents Onboarding
fazer-ai/agents
Conduz a jornada de onboarding 'do zero ao agente de atendimento' do fazer.ai agents num VPS, escolhendo o orquestrador de deploy (Tier A Coolify, B Portainer, C compose genérico para VM crua ou…
Agents Dev
fazer-ai/agents
Modo desenvolvedor do fazer.ai agents: trabalhar no código-fonte.
Related
Works with
Categories
Questions about Agents Operation
What does Agents Operation do?
Modo operação do fazer.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente. Agents Operation is an agent skill from fazer-ai/agents.ai agents: debugar conversas em produção e corrigir comportamentos inesperados do agente.
When should I use Agents Operation?
Agents Operation fits situations like: tasks that involve LLM observability.
How do I install Agents Operation in Claude Code?
Run `npx skills add fazer-ai/agents --skill agents-operation -a claude-code`. Or copy the skill folder (.claude/skills/agents-operation in fazer-ai/agents) into .claude/skills/agents-operation in your project. Claude Code loads it when a task matches its description.
How do I install Agents Operation in Codex?
Run `npx skills add fazer-ai/agents --skill agents-operation -a codex`. Or copy the skill folder (.claude/skills/agents-operation in fazer-ai/agents) into .agents/skills/agents-operation in your project. Codex loads it when a task matches its description.
Can I use Agents Operation in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add fazer-ai/agents --skill agents-operation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agents-operation, .gemini/skills/agents-operation, .github/skills/agents-operation and .opencode/skills/agents-operation in your project.
What does Agents Operation need to run?
Going by SKILL.md and its folder, Agents Operation needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Agents Operation access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Agents Operation safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Agents Operation use?
Agents Operation is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Agents Operation use?
About 1.3k tokens (SKILL.md is roughly 5.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 9.3k tokens, read only when the agent opens those files.
What are the alternatives to Agents Operation?
Skills that share tags, products or a category with Agents Operation: Langfuse (avivsinai/langfuse-mcp, 113 stars), Debug Issue With Datadog (langfuse/langfuse, 36k stars), Managed Deep Agents (langchain-ai/langchain-skills, 1.3k stars) and Cursor Agents Workflow (langfuse/langfuse, 36k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Agents Operation?
fazer-ai (a GitHub organization) maintains it in fazer-ai/agents, which has 118 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 9, 2026.
Source: fazer-ai/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.