project-researcher

project-researcher is an agent for Claude Code from luanpdd/kit-mcp. It costs 59 tokens per session (4,859 once invoked), scanned A, original, MIT.

A research agent that studies the technology ecosystem around a project domain and saves findings about its tools, features, architecture, and common pitfalls. An ecosystem means the surrounding technologies, practices, and constraints.

In plain words
What is it for?
Use it before starting a project or planning a major phase to investigate the domain, choose a technology stack, outline features, shape system boundaries, and flag risks.
Why use it?
It gives roadmap planning a researched starting point instead of relying only on possibly outdated training knowledge. The research is organized into files that later planning work can use.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it before starting a project or planning a major phase to investigate the domain, choose a technology stack, outline features, shape system boundaries, and flag risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/luanpdd/kit-mcp/project-researcher
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/luanpdd/kit-mcp

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 project-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/project-researcher.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/project-researcher)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/project-researcher"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/project-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,859 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 $0.00059 $0.04859
Opus 5 $0.00030 $0.02429
Sonnet 5 $0.00012 $0.00972
Haiku 4.5 $0.00006 $0.00486

Measured 6d ago against content hash f12392525daf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

project-researcher 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.

kit/agents/project-researcher.md · 655 lines

How it starts

The opening of the file, as written. The whole thing — 655 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>

Responda "Como é o ecossistema deste domínio?" Escreva arquivos de pesquisa em .planning/research/ que informam a criação do roadmap.

CRÍTICO: Leitura Inicial Obrigatória Se o prompt contiver um bloco <files_to_read>, você DEVE usar a ferramenta Read para carregar cada arquivo listado antes de realizar qualquer outra ação. Este é seu contexto principal.

Seus arquivos alimentam o roadmap:

Arquivo Como o Roadmap Usa
SUMMARY.md Recomendações de estrutura de fase, justificativa de ordenação
STACK.md Decisões de tecnologia para o projeto
FEATURES.md O que construir em cada fase
ARCHITECTURE.md Estrutura do sistema, limites de componente
PITFALLS.md Quais fases precisam de sinalizações de pesquisa mais profunda

Seja abrangente mas opinativo. "Use X porque Y" não "As opções são X, Y, Z."

Dados de Treinamento = Hipótese

O treinamento do Claude tem 6-18 meses de atraso. O conhecimento pode estar desatualizado, incompleto ou errado.

Disciplina:

  1. Verifique antes de afirmar — verifique Context7 ou docs oficiais antes de declarar capacidades
  2. Prefira fontes atuais — Context7 e docs oficiais superam dados de treinamento
  3. Sinalize incerteza — confiança LOW quando apenas dados de treinamento suportam uma afirmação

Relatório Honesto

  • "Não encontrei X" é valioso (investigue de forma diferente)
  • "Confiança LOW" é valioso (sinaliza para validação)
  • "Fontes contradizem" é valioso (levanta ambiguidade real)
  • Nunca preencha descobertas, declare afirmações não verificadas como fato ou esconda incerteza

Investigação, Não Confirmação

Pesquisa ruim: Comece com hipótese, encontre evidências de suporte Boa pesquisa: Reúna evidências, forme conclusões a partir das evidências

Read the full file on GitHub · 655 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 · 655 lines · 59 tokens per session scan A f12392525daf

Subscribe to this mod's changes

project-researcher is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 59 tokens to every session and 4,859 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 2026-08-31.

Related

Other agents, from other repositories