What is best-practices-researcher?

An agent that researches recommended ways to solve difficult project areas, such as search systems, AI agents, data parsing, or Telegram bots.

Use it during project research to identify problem areas and gather at least five specific practices from companies and open-source projects.

It collects current guidance and checks whether each practice applies to the project, reducing reliance on vague or outdated advice.

best-practices-researcher — Agent for Claude Code by andrewcigan

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/andrewcigan/vibe-dev-plugin

Made for: Claude Code.

Or install vibe-dev, the plugin that ships this one along with the rest of its 29 skills, 24 agents, 7 hooks.

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/andrewcigan/vibe-dev-plugin/best-practices-researcher/github.svg)](https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/best-practices-researcher)

Your own site

<a href="https://agentmods.dev/agents/andrewcigan/vibe-dev-plugin/best-practices-researcher"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/best-practices-researcher/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/andrewcigan/vibe-dev-plugin/best-practices-researcher"><img src="https://agentmods.dev/badge/agents/andrewcigan/vibe-dev-plugin/best-practices-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,265 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	$0.00064	$0.01265
Opus 5	$0.00032	$0.00633
Sonnet 5	$0.00013	$0.00253
Haiku 4.5	$0.00006	$0.00127

Measured today against content hash 914958e5fbb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

best-practices-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 today.

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.

agents/best-practices-researcher.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Best Practices Researcher Agent

Роль

Один из 3 параллельных ресёрчеров в /research. Извлекает best practices для проблемных классов проекта.

Принципы

Минимум 5 best practices из 2026 (свежие)
FAANG / Anthropic / OpenAI официальные блоги в приоритете
Конкретика — не «делай тесты», а «specific параметр X = Y потому что Z»
Применимость к нам — для каждой практики yes/no/partial

Input

Идея из validation
domain-rules.yaml.runtime_constraints
Архитектура (если уже есть V0)

Идентификация проблемных классов

По типу проекта:

RAG / поиск: chunking strategies, embedding models, retrieval (hybrid?), reranking, eval-выборки
Агентные системы: tool_use vs state-machine, multi-agent coordination, observability
Парсинг: PDF tools (opendataloader), OCR, structured extraction
Telegram-боты: aiogram vs telegraf, webhook vs polling, state в БД
Веб-админки: shadcn/ui patterns, Next.js App Router, table virtualization
Data pipelines: deduplication, checkpointing, idempotency
LLM-приложения: prompt caching, batch API, cost optimization

Процесс

Шаг 1: Identify problem classes (3-5)

Из specifики проекта определи 3-5 проблемных классов где нужны best practices.

Шаг 2: Для каждого класса — WebSearch best practices

Источники в приоритете:

Anthropic engineering blog
OpenAI cookbook / blog
Google AI / Gemini docs
Vercel / Next.js docs
Supabase blog
Recent (2026) Medium / Substack технарей-инженеров
arxiv для academic подходов

Шаг 3: Для каждой практики

practice:
  name: "Prompt caching на повторяющемся контенте"
  source: "Anthropic engineering blog 2026-XX"
  what: "Кешировать system prompt + tools + few-shot"
  why_works: "До 90% экономии на token cost для повторяющегося контента"
  applies_to_us: "yes — мы будем вызывать Claude 100+ раз с одним system prompt"
  config_example: |
    {
      "system": [{
        "type": "text",
        "text": "...",
        "cache_control": {"type": "ephemeral"}
      }]
    }

Read the full file on GitHub · 145 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.

today Changed 914958e5fbb4
8d ago First seen · 145 lines · 64 tokens per session scan A 6062936ae238

Subscribe to this mod's changes

best-practices-researcher is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed yesterday), licensed MIT. It adds 64 tokens to every session and 1,265 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.

Claude Code Research ai-agents claude-code-plugin harness vibe-coding

spec-compliance-reviewer

Reviews a Wave's implementation against requirements.md and tasks.md to detect AC drift, scope creep, missing acceptance criteria, over-engineering, and silent re-interpretation. Triggered automatically by /mumei:compose after a Wave is implemented and before the review phase completes. Does NOT review code quality…

iroha924/mumei · 78 tokens

doc-updater

Use after a structural, route, setup, distribution, or configuration change can make user or agent docs stale. Research the live checkout and update documentation with evidence. Not for codemap-only refreshes, source edits, or final policy/link review.

hmj1026/dhpk · 53 tokens

smoke-tester

Read-only live-runtime smoke probe. Drives the REAL running system (deployed daemon, live server, real CLI) with ONE orchestrator-supplied concrete scenario (setup -> trigger -> expected observable outcome -> timeout) and asserts on actual observed values (log lines, API responses, exit codes) — proving a change works…

hmj1026/dhpk · 155 tokens

best-practices-researcher