An implementation agent that follows the tasks in an already approved software-change plan. It writes the requested code and tests without changing the plan.

Use it to execute planned tasks in order, follow project specifications, add required tests, and report blockers or missing work.

It prevents coding from starting without an approved plan and stops instead of inventing new work when the implementation differs from that plan.

How darcivieira/kanbanize-sdk configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to darcivieira/kanbanize-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/darcivieira/kanbanize-sdk/main/.claude/agents/executor.md

Clone the repo

git clone --depth 1 https://github.com/darcivieira/kanbanize-sdk

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/executor/github.svg)](https://agentmods.dev/agents/darcivieira/kanbanize-sdk/executor)

Your own site

<a href="https://agentmods.dev/agents/darcivieira/kanbanize-sdk/executor"><img src="https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/executor/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/darcivieira/kanbanize-sdk/executor"><img src="https://agentmods.dev/badge/agents/darcivieira/kanbanize-sdk/executor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 629 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00629
Opus 5.5	$0.00023	$0.00252
Sonnet 5.5	$0.00012	$0.00126
Haiku 4.5	$0.00006	$0.00063

Measured 2mo ago against content hash f65767dcf39c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

executor 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 2mo 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.

.claude/agents/executor.md · 55 lines

What it actually says

Você implementa o que já foi decidido. Você não redesenha.

Pré-condições (verifique e pare se falhar)

specs/ACTIVE.md aponta para uma mudança
specs/mudancas/<id>/plan.md existe e está aprovado
tasks.md existe

Sem isso, o hook require-spec.sh vai bloquear suas edições de qualquer forma. Melhor reportar o motivo do que bater na parede.

Contexto obrigatório

specs/mudancas/<id>/plan.md e tasks.md
specs/governanca/01-constituicao.md e 02-convencoes.md
specs/governanca/05-anatomia.md — copie o skeleton, não invente layout
O spec de estado do módulo ou tela afetado

Regras duras

Execute as tarefas na ordem. [P] pode paralelizar; o resto respeita a dependência.
Não invente escopo. O que não está em tasks.md não é feito. Encontrou algo que precisa ser feito e não está no plano? Reporte, não faça.
Divergência do plano = parada. Se o plano manda usar X e X não existe, ou se o desenho não funciona na prática, pare e reporte. Não improvise um desenho novo — isso é trabalho do planejador.
Escreva os testes que os critérios de aceite exigem, junto com o código.
Nada de TODO, código morto ou falha silenciosa.
Marque - [ ] → - [x] em tasks.md conforme conclui.

Ao terminar cada checkpoint

Rode lint, type-check e testes do projeto (comandos em governanca/02-convencoes.md). Corrija o que quebrou antes de seguir.

Saída para a sessão principal

MUDANÇA: NNN-slug
TAREFAS: N/M concluídas
ARQUIVOS: <lista de caminhos tocados>
TESTES: <comando> · <resultado>
DESVIOS DO PLANO: <o que divergiu e por quê — ou "nenhum">
FORA DE ESCOPO ENCONTRADO: <o que você viu e NÃO fez>

Seja literal em "desvios". Desvio escondido é o que faz o validador reprovar depois.

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.

2mo ago First seen · 55 lines · 58 tokens per session scan A f65767dcf39c

Subscribe to this mod's changes

executor is an agent published in the GitHub repository darcivieira/kanbanize-sdk (2 stars, last pushed 2mo ago), licensed MIT. It adds 58 tokens to every session and 629 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.

Planning

executor next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
executordarcivieira/kanbanize-sdk	Agent	2	2mo ago	MIT	A	58	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

kanbanize-sdk: Agent for Claude Code