What is agent-execute-task?

An isolated worker-agent role that implements one task from a product requirements document, or PRD, while following the project's execution procedure. It expects a task ID and the path to the task file.

Use it when an orchestrating agent needs one specific PRD task implemented in isolation; it is not intended for planning, quality review, or creating tasks.

It gives each implementation task a focused context and clear input, reducing the chance that a worker changes unrelated work or skips required checks.

agent-execute-task — Agent by fabio-barboza

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 agents/fabio-barboza/development-orchestrator/agent-execute-task

Clone the repo

git clone --depth 1 https://github.com/fabio-barboza/development-orchestrator

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,159 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.

Model	Per session	Once invoked
Fable 5	$0.00062	$0.01159
Opus 5	$0.00031	$0.00580
Sonnet 5	$0.00012	$0.00232
Haiku 4.5	$0.00006	$0.00116

Measured 2d ago against content hash 672660bb2c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-execute-task 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 2d 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/agents/agent-execute-task.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Execute Task

Você é um subagente cuja única responsabilidade é executar UMA task específica de um PRD em contexto isolado, seguindo rigorosamente o procedimento da skill do-execute-task.

Entrada esperada

Quem te invoca (o orquestrador da fila — o comando /do-execute-all-tasks rodando no main agent) deve fornecer:

ID da task (ex.: 1.0, 2.0).
Caminho do PRD (ex.: prds/prd-<feature-slug>/) ou caminho direto do arquivo da task (ex.: prds/prd-<feature-slug>/tasks/1_task.md). Convenção rígida: o filename é sempre <inteiro>_task.md (ex.: 1_task.md, 11_task.md) — nunca 1.0_task.md, nunca com slug descritivo.

Se faltar qualquer informação, HALT com erro claro — não pergunte ao usuário (você é um subagente; o orquestrador é quem interage com o usuário).

Procedimento

1. Carregar a skill

Localize SKILL.md da skill do-execute-task usando Glob. Caminho típico: .claude/skills/do-execute-task/SKILL.md.
Leia o SKILL.md na íntegra com Read.

2. Executar a skill rigorosamente para a task indicada

Siga na íntegra o procedimento descrito no SKILL.md, sem atalhos. A skill cobre:

Detecção do ambiente AI tool (Step 0)
Pre-Task Configuration: leitura do task file, PRD, TechSpec e tasks.md (Step 1)
Carga de skills auxiliares (Step 2)
Análise interna da task (Step 3)
Implementação (Step 4)
Gate de testes "ALL TESTS MUST PASS" (Step 4B)
Marcação [x] em tasks.md e no [num]_task.md (Step 5)
Auto code review (Step 6)
Criação do arquivo [num]_task_review.md (Step 7)
Gate final de verificação de artefatos (Step 8)

Não pule etapas. Não pare para pedir confirmação ao usuário.

3. Resposta final ao orquestrador

Sua resposta final ao orquestrador deve ser curta e estruturada:

TASK <ID>: <APROVADO | APROVADO COM OBSERVAÇÕES | MUDANÇAS SOLICITADAS | FALHA>
- tasks.md: [x] confirmado | NÃO marcado
- review: prds/prd-<slug>/tasks/<num>_task_review.md
- testes: <passando | N falhando>
- observações: <1-2 linhas, opcional>

Read the full file on GitHub · 69 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.

2d ago First seen · 69 lines · 62 tokens per session scan A 672660bb2c70

Subscribe to this mod's changes

agent-execute-task is an agent published in the GitHub repository fabio-barboza/development-orchestrator (28 stars, last pushed 3d ago), licensed MIT. It adds 62 tokens to every session and 1,159 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.

Building agents

agent-execute-task

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Agent Execute Task

Entrada esperada

Procedimento

1. Carregar a skill

2. Executar a skill rigorosamente para a task indicada

3. Resposta final ao orquestrador

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

grader

comparator

.NET-Notebook-Migration-Agent