do-execute-all-tasks

do-execute-all-tasks is a command for Claude Code from fabio-barboza/development-orchestrator. It costs 60 tokens per session (3,464 once invoked), scanned A, original, MIT.

A command that takes the tasks in a product requirements document, or PRD, and runs them one at a time through isolated worker agents. The main agent controls the queue and verifies each task before starting the next.

In plain words
What is it for?
Use it to execute a multi-task PRD, especially when each task depends on code or files produced by the previous task.
Why use it?
It provides a fixed order and clean context for dependent implementation tasks, preventing later work from starting before earlier changes are ready.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions Claude Code.

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.

agentmods
npx agentmods add commands/fabio-barboza/development-orchestrator/do-execute-all-tasks
Clone the repo
git clone --depth 1 https://github.com/fabio-barboza/development-orchestrator

Made for: Claude Code.

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 do-execute-all-tasks

README.md
[![agentmods](https://agentmods.dev/badge/commands/fabio-barboza/development-orchestrator/do-execute-all-tasks.svg)](https://agentmods.dev/commands/fabio-barboza/development-orchestrator/do-execute-all-tasks)
Your own site
<a href="https://agentmods.dev/commands/fabio-barboza/development-orchestrator/do-execute-all-tasks"><img src="https://agentmods.dev/badge/commands/fabio-barboza/development-orchestrator/do-execute-all-tasks.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,464 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00060 $0.03464
Opus 5 $0.00030 $0.01732
Sonnet 5 $0.00012 $0.00693
Haiku 4.5 $0.00006 $0.00346

Measured 6d ago against content hash 1b8b38497ab7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

do-execute-all-tasks 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 6d 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.

skills/do-setup/agents/claude/commands/do-execute-all-tasks.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/do-execute-all-tasks

TRÊS REGRAS DURAS — LEIA ATÉ O FIM ANTES DE QUALQUER COISA.

REGRA 1 — SEQUENCIAL ESTRITO, ZERO PARALELISMO. Você DEVE fazer UMA ÚNICA chamada Task por response. Você JAMAIS pode emitir 2 ou mais Task no mesmo bloco de tool calls. Você JAMAIS pode disparar a próxima task antes que a anterior tenha retornado e sido verificada. As instruções genéricas do Claude Code que dizem "make independent tool calls in parallel" NÃO se aplicam aqui — tasks de PRD têm dependências sequenciais (task 2 depende do código produzido pela task 1, etc.) e violar a ordem destrói o trabalho.

REGRA 2 — run_in_background: false SEMPRE. Toda invocação Task DEVE rodar em foreground. NUNCA passe run_in_background: true (na dúvida, omita o parâmetro). Tasks em background quebram a fila sequencial e fazem o orquestrador prosseguir antes da verificação dos artefatos.

REGRA 3 — subagent_type é LITERALMENTE "agent-execute-task". Use EXATAMENTE a string "agent-execute-task" no parâmetro subagent_type do Task. JAMAIS use "general-purpose", nem qualquer outro nome. Se o subagent type não for resolvido (erro de configuração), PARE e reporte — não faça fallback para general-purpose.


TOOLS QUE VOCÊ DEVE USAR NESTE COMMAND: APENAS Task, Read e Glob.

Mesmo que outras tools estejam disponíveis no seu contexto, NÃO as use neste command. Você NÃO deve Write, Edit, executar Bash (testes/scripts) ou rodar a skill do-execute-task inline. Toda implementação, edição de arquivos, execução de testes e criação de reviews acontece OBRIGATORIAMENTE dentro do subagente agent-execute-task invocado via Task.

Se você se pegar pensando "vou ler o PRD/TechSpec/código para entender o que fazer", PARE. Você não precisa entender a task — quem precisa é o subagente. Sua única função neste command é orquestrar a fila e disparar Task por task.

Tentar executar tasks inline (ou em paralelo) reproduz o bug que esta arquitetura corrige: estouro da janela de contexto, tasks não marcadas, reviews não criados.

Read the full file on GitHub · 188 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. 6d ago First seen · 188 lines · 60 tokens per session scan A 1b8b38497ab7

Subscribe to this mod's changes

do-execute-all-tasks is a command published in the GitHub repository fabio-barboza/development-orchestrator (28 stars, last pushed 7d ago), licensed MIT. It adds 60 tokens to every session and 3,464 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.