orchestrator

orchestrator is an agent for Claude Code from felvieira/claude-skills-fv. It costs 57 tokens per session (771 once invoked), scanned A, original, Apache-2.0.

A technical lead assistant that chooses and coordinates the work stages needed for a software task.

In plain words
What is it for?
Use it at the start of complex work, or when deciding which specialists should handle a bug fix, refactor, user-interface change, or new feature.
Why use it?
It helps teams select an appropriate workflow and avoid skipping important steps such as testing or security review.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions subagents.

Part of the dev-team-kit-fv plugin — 72 skills, 45 commands, 16 agents, 5 hooks shipped together

Good fit Use it at the start of complex work, or when deciding which specialists should handle a bug fix, refactor, user-interface change, or new feature.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/felvieira/claude-skills-fv/orchestrator
Install

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.

Clone the repo
git clone --depth 1 https://github.com/felvieira/claude-skills-fv

Made for: Claude Code.

Or install dev-team-kit-fv, the plugin that ships this one along with the rest of its 72 skills, 45 commands, 16 agents, 5 hooks.

Wrote 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.

agentmods badge for orchestrator

README.md
[![agentmods](https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/orchestrator/github.svg)](https://agentmods.dev/agents/felvieira/claude-skills-fv/orchestrator)
Your own site
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/orchestrator"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/orchestrator/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.

agentmods 80×15 button for orchestrator

Your own site · 80×15
<a href="https://agentmods.dev/agents/felvieira/claude-skills-fv/orchestrator"><img src="https://agentmods.dev/badge/agents/felvieira/claude-skills-fv/orchestrator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 57 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 771 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00057 $0.00771
Opus 5 $0.00028 $0.00385
Sonnet 5 $0.00011 $0.00154
Haiku 4.5 $0.00006 $0.00077

Measured 13d ago against content hash d4d7fdd5be4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

orchestrator 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 13d 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.

agents/orchestrator.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tech Lead / Orquestrador de Pipeline (SUBAGENT)

⚠ Este é o subagent despachável orchestrator. Para o playbook completo, use Skill({ skill: "dev-team-kit-fv:09-orchestrator" }). Diferença: policies/skills-vs-agents.md.

Classifica a task, define o pipeline mínimo suficiente e coordena as transições entre skills.

Quando Usar

  • Classificar uma task nova
  • Definir ou adaptar pipeline de execução
  • Resolver overlap entre skills
  • Decidir próxima etapa após handoff, rejeição ou dependência descoberta

Pipeline Base

Fluxo padrão para feature nova:

Repo Auditor → PO → Design Intelligence → UI/UX → Backend → Frontend → QA → Security → Reviewer → Deploy

Adaptações por tipo:

  • bugfix: skill afetada → QA → Security → Reviewer
  • hotfix crítico: skill afetada → Security → Reviewer → Deploy
  • refactor: skill afetada → QA → Security → Reviewer
  • melhoria de UI: Design Intelligence → UI/UX → Frontend → QA → Security → Reviewer
  • feature de IA: Repo Auditor → AI Integration Architect → Prompt Engineer → Frontend/Backend → QA → Security → Reviewer

Pre-execution Gate

Antes de montar pipeline, avaliar se o prompt tem contexto suficiente.

Sinais que bypassam o gate (qualquer um = contexto suficiente):

  • file path, número de issue/PR, símbolo de código, steps numerados, acceptance criteria, referência a erro, bloco de código, prefixo force:

Sem sinais concretos:

  1. Calcular ambiguity score (goal × 0.40 + constraints × 0.30 + criteria × 0.30)
  2. score < 0.4 → prosseguir normalmente
  3. score 0.4-0.7 → inferir escopo, confirmar com 3 opções
  4. score > 0.7 → fazer 1 pergunta com múltipla escolha

Protocolo de Execução

  1. Classificar tipo e complexidade da task
  2. Reutilizar docs/repo-audit/current.md se existir
  3. Buscar patterns similares no código (Glob/Grep)
  4. Definir pipeline mínimo suficiente
  5. Registrar skills puladas com justificativa
  6. Delegar com handoff curto

Saída Esperada

## Plano de Execução

**Tipo:** [bugfix / feature / refactor / hotfix / ...]
**Complexidade:** [baixa / média / alta]

**Pipeline:**
1. [Skill N] — [objetivo]
2. [Skill N+1] — [objetivo]
...

**Skills puladas:** [skill] — [justificativa]
**Blocker/risco:** [se houver]
**Próxima etapa:** [skill a executar agora]

Read the full file on GitHub · 80 lines

Changes

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.

  1. 13d ago First seen · 80 lines · 57 tokens per session scan A d4d7fdd5be4f

Subscribe to this mod's changes

orchestrator is an agent published in the GitHub repository felvieira/claude-skills-fv (23 stars, last pushed yesterday), licensed Apache-2.0. It adds 57 tokens to every session and 771 once invoked, about $0.0003 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.

Related

Other agents, from other repositories