A research workflow for searching the live web and extracting information from pages. It supports quick scans for short overviews and deep research for comparing several sources.

Use it to investigate a topic, gather sources, compare conflicting information, and produce a focused summary with useful context.

It reduces the time spent collecting reliable sources and provides a fallback when one search service is unavailable.

researcher — Skill for Codex by howdeploy/kisa-stack

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 howdeploy/kisa-stack --skill researcher

Clone the repo

git clone --depth 1 https://github.com/howdeploy/kisa-stack

Made for: 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/howdeploy/kisa-stack/researcher/github.svg)](https://agentmods.dev/skills/howdeploy/kisa-stack/researcher)

Your own site

<a href="https://agentmods.dev/skills/howdeploy/kisa-stack/researcher"><img src="https://agentmods.dev/badge/skills/howdeploy/kisa-stack/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/skills/howdeploy/kisa-stack/researcher"><img src="https://agentmods.dev/badge/skills/howdeploy/kisa-stack/researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 8,842 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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	$0.00114	$0.08842
Opus 5.5	$0.00046	$0.03537
Sonnet 5.5	$0.00023	$0.01768
Haiku 4.5	$0.00011	$0.00884

Measured 1mo ago against content hash 0bea7b17a959, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

researcher scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

description: "Гибкий ресерч через Tavily/Hermes web_search и web_extract, с обязательным живым smoke test и фолбэком на Brave/DuckDuckGo через terminal/curl/requests. Основные режимы: quick-scan и deep-research. Всегда р

skills/researcher/SKILL.md · 484 lines

How it starts

The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Researcher

Примечание по инструментам. Скилл писался в среде Hermes: web_search / web_extract / terminal / execute_code / delegate_task — ее инструменты. В Claude Code / Codex используй аналоги: веб-поиск (Tavily / WebSearch), извлечение страниц (tavily_extract / WebFetch), shell (Bash), субагенты (Agent). Логика скилла от рантайма не зависит.

Короткий и практичный ресерч без ступора, если один источник поиска умер.

Основные режимы

1. `quick-scan`

Когда нужен быстрый, но нормальный обзор.

Что делать:

быстро проверить тему через web_search
взять 3–5 сильных источников
дать короткую выжимку
оставить достаточно контекста, чтобы потом можно было углубиться без повторного старта с нуля

Когда использовать:

нужно быстро понять, стоит ли тема внимания
нужен короткий обзор без перегруза
нужно подобрать, куда копать дальше

2. `deep-research`

Когда нужен уже не обзор, а нормальное погружение.

Что делать:

собрать несколько качественных источников с разных углов
сравнить версии, подходы, противоречия
выделить практические выводы
сохранить достаточно контекста в ответе, чтобы пользователь мог продолжить разговор с уже собранной базой

Когда использовать:

нужно реально разобраться в теме
нужно сравнить инструменты / подходы / мнения
нужен ресерч для статьи, дайджеста, решения или стратегии

Триггеры

Используй естественные фразы, не требуй от пользователя специального синтаксиса.

Триггеры для quick-scan

быстро посмотри тему
дай быстрый ресерч по ...
коротко разберись, что там с ...
глянь, стоит ли вообще в это копать
быстрый обзор по ...
собери краткую выжимку по ...

Триггеры для deep-research

глубоко исследуй ...
нормально раскопай тему ...
собери глубокий ресерч по ...
сравни и разберись подробно ...
хочу разобраться в ... глубже
сделай полноценный ресерч по ...

Выбор режима

Если пользователь явно не назвал режим, выбирай его сама:

если запрос звучит как быстрый обзор или первичная разведка — quick-scan
если нужно сравнение, решение, подбор workflow, исследование с нескольких сторон или тема явно сложная — deep-research

Read the full file on GitHub · 484 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

1mo ago Changed · -26 lines 0bea7b17a959
1mo ago First seen · 510 lines · 114 tokens per session scan A c7954b0a4f44

Subscribe to this mod's changes

researcher is a skill published in the GitHub repository howdeploy/kisa-stack (57 stars, last pushed 3d ago), licensed MIT. It adds 114 tokens to every session and 8,842 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Research

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

researcher