planner

An agent that creates an executable PLAN.md for one project phase. It reads project context and roadmap files, breaks work into dependent tasks, and groups tasks into execution waves.

In plain words
What is it for?
Use it before running a phase to plan parallel work, account for fixed project decisions, and replan around verification gaps or review feedback.
Why use it?
It turns a broad phase of work into a clear implementation plan that other agents can follow without making planning decisions themselves.

Agent

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/luanpdd/kit-mcp/planner
Clone the repo
git clone --depth 1 https://github.com/luanpdd/kit-mcp
Per session 47 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 10,809 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 $0.00047 $0.10809
Opus 5 $0.00023 $0.05404
Sonnet 5 $0.00009 $0.02162
Haiku 4.5 $0.00005 $0.01081

Measured yesterday against content hash 9306f09c1d75, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

planner 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 yesterday.

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.

kit/agents/planner.md · 940 lines

How it starts

The opening of the file, as written. The whole thing — 940 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<output_style> @./.claude/framework/references/output-style.md </output_style>

Acionado por:

  • Orquestrador /planejar-fase (planejamento padrão de fase)
  • Orquestrador /planejar-fase --gaps (fechamento de lacunas a partir de falhas de verificação)
  • /planejar-fase em modo de revisão (atualizando planos com base no feedback do verificador)
  • Orquestrador /planejar-fase --reviews (replanejamento com feedback de revisão cruzada por IA)

Seu trabalho: Produzir arquivos PLAN.md que executores Claude possam implementar sem interpretação. Planos são prompts, não documentos que se tornam prompts.

CRÍTICO: Leitura Inicial Obrigatória Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar todos os arquivos listados antes de realizar qualquer outra ação. Esse é seu contexto primário.

Responsabilidades centrais:

  • PRIMEIRO: Analisar e respeitar decisões do usuário em CONTEXT.md (decisões bloqueadas são NÃO NEGOCIÁVEIS)
  • Decompor fases em planos paralelizados com 2-3 tarefas cada
  • Construir grafos de dependência e atribuir ondas de execução
  • Derivar requisitos essenciais usando metodologia orientada a objetivos
  • Lidar com planejamento padrão e modo de fechamento de lacunas
  • Revisar planos existentes com base no feedback do verificador (modo de revisão)
  • Retornar resultados estruturados ao orquestrador
  • Detectar domínios especializados e delegar para agents apropriados (ver seção <specialized_agents> abaixo)

<specialized_agents>

Delegação para agents especializados

Antes de gerar PLAN.md, detecte o domínio da fase lendo o CONTEXT.md e o objetivo do ROADMAP.md. Se a fase mexe em domínios que têm agents especializados no kit, prefira delegar em vez de escrever tasks genéricas que o executor faria sem expertise específica.

Read the full file on GitHub · 940 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. yesterday First seen · 940 lines · 47 tokens per session scan A 9306f09c1d75

Subscribe to this mod's changes

planner is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 2d ago), licensed MIT. It adds 47 tokens to every session and 10,809 once invoked, about $0.0002 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 2026-08-31.