A research workflow for investigating a topic with language models while checking for bias and preserving the results in a knowledge base. It covers broad learning research and research for choosing between options.

Use it to research a topic, gather best practices, compare approaches, or collect information for a decision. It guides the investigation and saves the results.

It adds a repeatable method for finding reliable information instead of relying on attractive but unsupported answers, and keeps the work available later.

research — Skill for Claude Code and Codex by dzhokhov

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.

Any agent

npx skills add dzhokhov/markdown-agent-vault-ru --skill research

Clone the repo

git clone --depth 1 https://github.com/dzhokhov/markdown-agent-vault-ru

Made for: Claude Code, Codex.

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/skills/dzhokhov/markdown-agent-vault-ru/research/github.svg)](https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/research)

Your own site

<a href="https://agentmods.dev/skills/dzhokhov/markdown-agent-vault-ru/research"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/research/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/skills/dzhokhov/markdown-agent-vault-ru/research"><img src="https://agentmods.dev/badge/skills/dzhokhov/markdown-agent-vault-ru/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 174 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,568 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	$0.00174	$0.03568
Opus 5	$0.00087	$0.01784
Sonnet 5	$0.00035	$0.00714
Haiku 4.5	$0.00017	$0.00357

Measured 9d ago against content hash f355f84d49eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

research 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 9d 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.

skills/research/SKILL.md · 255 lines

How it starts

The opening of the file, as written. The whole thing — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research — скилл качественного LLM-исследования

Зачем этот скилл

LLM-ресёрч без методологии порождает красивые, но ненадёжные результаты: галлюцинации выглядят как факты, коммерческий контент маскируется под best practices, vocal minority подменяет реальную картину. Этот скилл применяет проверенную методологию, чтобы результат был не только полным, но и достоверным — и сохраняет его в базу знаний, чтобы работа не пропала с закрытием чата.

Полная методология с источниками: 03_knowledge/llm-research-methodology.md. Прочитай её перед первым использованием скилла, чтобы понимать теоретическую базу. Ниже — операционный протокол.

Фаза 0. Классификация запроса

Перед началом определи тип исследования — от него зависит глубина, критерии остановки и формат результата.

Исследование-знание («Как устроены Personal CRM?») → Широкий обзор, множество точек зрения, максимальный охват. Критерий остановки: насыщение (новые запросы не дают новой информации).

Исследование-решение («Какую CRM мне выбрать?») → Узкий фокус на ограничениях пользователя, чёткие критерии, быстрый выход на действие. Критерий остановки: достаточно данных для принятия решения.

Зафиксируй тип в начале работы. Типичная ловушка: начать с решения, скатиться в бесконечное накопление знаний.

Для исследования-решения сразу уточни у пользователя:

Какие критерии выбора?
Какие ограничения (бюджет, время, навыки, экосистема)?
Какой допустимый уровень неопределённости?

Создай файл результата ДО начала сбора (обязательно)

🛑 Это действие выполняется СЕЙЧАС, до перехода к Фазе 1. Если файл не создан — дальше не двигайся.

Определи имя файла: research-{тема-kebab-case}.md
Определи путь по task-routing-модели (см. task-routing-methodology-2026-04.md §2):
- Standalone ресёрч (переживёт любой проект, переиспользуемое знание) → 03_knowledge/
- Ресёрч в контексте проекта, но знание переиспользуемое → 03_knowledge/, а из <project>/context.md ставь ссылку. Не дублируй в папку проекта.
- Ресёрч, тесно привязанный к проекту и не переиспользуемый (например, конкретные цифры по одному клиенту) → <project>/research/
- Если знание меняет вектор проекта (новый вариант решения, пересмотр подхода) — в <project>/plan.md добавляется open question или Contingency ветка со ссылкой на research-файл
Зафиксируй resolved path целиком: <директория>/<filename>.md. Это и есть канонический путь документа для frontmatter, индексации и мультисессионного продолжения.
Создай файл с YAML-frontmatter из шаблона Фазы 4 (тело пока пустое)
Добавь в TodoList задачу: «Записать результат в {resolved_path}»
Сообщи пользователю: «Результат буду писать в {resolved_path}»

Read the full file on GitHub · 255 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.

9d ago First seen · 255 lines · 174 tokens per session scan A f355f84d49eb

Subscribe to this mod's changes

research is a skill published in the GitHub repository dzhokhov/markdown-agent-vault-ru (2 stars, last pushed 2d ago), licensed MIT. It adds 174 tokens to every session and 3,568 once invoked, about $0.0009 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.

Research agent-skills agentsmd ai-agents knowledge-management markdown obsidian

pos-verify

Use this immediately after files are created, edited, moved, deleted, or materially rewritten inside PersonalOS. Verifies that new truth was routed to the correct owner, written in the correct file shape, and still follows POS conventions. Do NOT use for whole-vault deep audits; use system-health-check.

vincentmumme/personalos-boilerplate · 65 tokens

skillify

Use this when {{username}} asks to skillify a repeated workflow, determine whether it deserves a reusable PersonalOS skill, or harden an existing workflow into a tested resolver-reachable capability. Do NOT use for one-off notes, ordinary execution, or already-specified skill authoring; use write-skill.

vincentmumme/personalos-boilerplate · 66 tokens

write-skill

Use this when the user wants to create a new shared PersonalOS skill under skills/ or revise a specified PersonalOS skill and the scope is already clear. Do NOT use for raw workflow capture or deciding whether work should become a skill; use skillify first. Do NOT use for repo-local or agent-local skills unless…

vincentmumme/personalos-boilerplate · 78 tokens

priority-dashboard

Use this to rebuild, inspect, or temporarily steer {{username}}'s current PersonalOS priority dashboard from canonical Actions, Attention Triggers, and owner context. Do NOT use it to create, complete, or independently manage tasks; use task-manager for Action and Trigger lifecycle changes.

vincentmumme/personalos-boilerplate · 60 tokens

lint-brain

Run health checks over the brain vault - find orphan notes, broken wikilinks, missing frontmatter, stale projects, and missing cross-links. Use when asked to "lint the brain", "health check", "vault hygiene", or "/lint-brain".

michaeljauk/brain-starter · 56 tokens

log

Use this when a PersonalOS work session, chat outcome, personal reflection, or provided source should be persisted into the modular Daily context and any already-owned canonical files. Do NOT use for single-call processing, single-source knowledge ingestion, Gmail/WhatsApp propagation, or Lexware booking.

vincentmumme/personalos-boilerplate · 59 tokens