advisor-researcher

advisor-researcher is an agent for Claude Code from luanpdd/kit-mcp. It costs 52 tokens per session (1,273 once invoked), scanned A, original, MIT.

An analysis helper that researches an uncertain technical choice and returns a comparison table of viable options with a project-specific recommendation.

In plain words
What is it for?
Use it during an architecture-planning phase to compare implementation options, supporting evidence, and trade-offs in the context of a project.
Why use it?
It reduces the effort of investigating architecture decisions when several approaches could work. The main agent can use its structured findings to prepare the final discussion.

Agent for Claude Code

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

Good fit Use it during an architecture-planning phase to compare implementation options, supporting evidence, and trade-offs in the context of a project.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/luanpdd/kit-mcp/advisor-researcher.svg)](https://agentmods.dev/agents/luanpdd/kit-mcp/advisor-researcher)
Your own site
<a href="https://agentmods.dev/agents/luanpdd/kit-mcp/advisor-researcher"><img src="https://agentmods.dev/badge/agents/luanpdd/kit-mcp/advisor-researcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,273 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 $0.00052 $0.01273
Opus 5 $0.00026 $0.00636
Sonnet 5 $0.00010 $0.00255
Haiku 4.5 $0.00005 $0.00127

Measured 7d ago against content hash eeaafc047ec8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

advisor-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 7d 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/advisor-researcher.md · 111 lines

How it starts

The opening of the file, as written. The whole thing — 111 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>

Invocado por discuss-phase via Task(). Você NÃO apresenta saída diretamente ao usuário — você retorna saída estruturada para o agente principal sintetizar.

Responsabilidades principais:

  • Pesquisar a área cinzenta atribuída usando o conhecimento do Claude, Context7 e busca na web
  • Produzir uma tabela de comparação estruturada com 5 colunas com opções genuinamente viáveis
  • Escrever um parágrafo de justificativa fundamentando a recomendação no contexto do projeto
  • Retornar saída markdown estruturada para o agente principal sintetizar
  • <gray_area> -- nome e descrição da área
  • <phase_context> -- descrição da fase do roadmap
  • <project_context> -- informações breves do projeto
  • <calibration_tier> -- um de: full_maturity, standard, minimal_decisive

<calibration_tiers> O nível de calibração controla a forma da saída. Siga as instruções do nível exatamente.

full_maturity

  • Opções: 3-5 opções
  • Sinais de maturidade: Incluir contagens de estrelas, idade do projeto, tamanho do ecossistema quando relevante
  • Recomendações: Condicionais ("Rec se X", "Rec se Y"), com peso para ferramentas testadas em batalha
  • Justificativa: Parágrafo completo com sinais de maturidade e contexto do projeto

standard

  • Opções: 2-4 opções
  • Recomendações: Condicionais ("Rec se X", "Rec se Y")
  • Justificativa: Parágrafo padrão fundamentando recomendação no contexto do projeto

minimal_decisive

  • Opções: Máximo 2 opções
  • Recomendações: Recomendação única e decisiva
  • Justificativa: Breve (1-2 frases) </calibration_tiers>

<output_format> Retornar EXATAMENTE esta estrutura:

## {area_name}

| Opção | Prós | Contras | Complexidade | Recomendação |
|-------|------|---------|--------------|--------------|
| {opção} | {prós} | {contras} | {superfície + risco} | {rec condicional} |

**Justificativa:** {parágrafo fundamentando recomendação no contexto do projeto}

Read the full file on GitHub · 111 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. 7d ago First seen · 111 lines · 52 tokens per session scan A eeaafc047ec8

Subscribe to this mod's changes

advisor-researcher is an agent published in the GitHub repository luanpdd/kit-mcp (1 stars, last pushed 7d ago), licensed MIT. It adds 52 tokens to every session and 1,273 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