A process for researching technical solutions, comparing architectures, and collecting requirements. It covers factors such as scalability, security, and maintainability, while favoring simple solutions when they are enough.

It helps evaluate technologies, research best practices, design solutions, analyze architectures, and assess scalability, security, and maintainability.

It gives technical research a defined scope, source strategy, and evaluation criteria. This helps avoid unfocused investigation and unsupported design choices.

ck:research — Skill for Claude Code by bestagentkits

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 bestagentkits/ck-skills --skill research

Clone the repo

git clone --depth 1 https://github.com/bestagentkits/ck-skills

Made for: Claude Code.

Or install ck-skills, the plugin that ships this one along with the rest of its 14 skills.

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/bestagentkits/ck-skills/research/github.svg)](https://agentmods.dev/skills/bestagentkits/ck-skills/research)

Your own site

<a href="https://agentmods.dev/skills/bestagentkits/ck-skills/research"><img src="https://agentmods.dev/badge/skills/bestagentkits/ck-skills/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/bestagentkits/ck-skills/research"><img src="https://agentmods.dev/badge/skills/bestagentkits/ck-skills/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,655 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	$0.00035	$0.01655
Opus 5	$0.00017	$0.00827
Sonnet 5	$0.00007	$0.00331
Haiku 4.5	$0.00003	$0.00166

Measured 10d ago against content hash 7f83ea62a3ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ck: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 10d 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.

plugins/ck-skills/skills/research/SKILL.md · 177 lines

How it starts

The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research

Research Methodology

Always honoring YAGNI, KISS, and DRY principles. Be honest, be brutal, straight to the point, and be concise.

Phase 1: Scope Definition

First, you will clearly define the research scope by:

Identifying key terms and concepts to investigate
Determining the recency requirements (how current must information be)
Establishing evaluation criteria for sources
Setting boundaries for the research depth

Phase 2: Systematic Information Gathering

You will employ a multi-source research strategy:

Search Strategy:
- Gemini Toggle: Check .claude/.ck.json (or ~/.claude/.ck.json) for skills.research.useGemini (default: false). If false or absent, skip Gemini and use WebSearch directly.
- Gemini Model: Read from .claude/.ck.json: gemini.model (default: gemini-3-flash-preview)
- If useGemini is true: first validate Gemini CLI works: command -v gemini >/dev/null 2>&1 && cd /tmp && timeout 15 gemini -y -m <gemini.model> --prompt "ping" >/dev/null 2>&1. If validation fails or times out, fall back to WebSearch and warn: "Gemini CLI unavailable or auth failed, using WebSearch."
- If validation passes, execute research from a temp dir to avoid project GEMINI.md interception (note: global ~/.gemini/GEMINI.md still loads): cd /tmp && timeout 180 gemini -y -m <gemini.model> --prompt "...your search prompt..." 2>&1. Check exit code — if non-zero or output contains GaxiosError, RESOURCE_EXHAUSTED, MODEL_CAPACITY_EXHAUSTED, PERMISSION_DENIED, or UNAUTHENTICATED, fall back to WebSearch for that query and warn: "Gemini CLI failed, falling back to WebSearch." Save successful output using Report: path from ## Naming section (including all citations).
- If useGemini is disabled or gemini bash command is not available, use WebSearch tool.
- Run multiple gemini bash commands or WebSearch tools in parallel to search for relevant information.
- Craft precise search queries with relevant keywords
- Include terms like "best practices", "2024", "latest", "security", "performance"
- Search for official documentation, GitHub repositories, and authoritative blogs
- Prioritize results from recognized authorities (official docs, major tech companies, respected developers)
- IMPORTANT: You are allowed to perform at most 5 researches (max 5 tool calls), user might request less than this amount, strictly respect it, think carefully based on the task before performing each related research topic.

Read the full file on GitHub · 177 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.

10d ago First seen · 177 lines · 35 tokens per session scan A 7f83ea62a3ae

Subscribe to this mod's changes

ck:research is a skill published in the GitHub repository bestagentkits/ck-skills (6 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,655 once invoked, about $0.0002 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 Planning Research agent-tools ai-agents claude-skills goclaw plugin-marketplace

adr

Use when the user knows what they want built and says "/adr", "write an ADR for X", "decide and build X", or "ADR-driven". Turns an intent into a grounded, cited, build-ready ADR at docs/adr/YYYY-MM-DD- .md — load-bearing decisions surfaced to the human — then hands off to nightshift:plan's landing step (the plan is…

jasonm4130/claude-skills · 138 tokens

watch

Use when a Nightwatch spec queue is about to run, or is already running, and someone needs to fire it, watch it, and steer it — "launch nightwatch", "watch the run", "/nightwatch:watch", "pause it", "skip that spec". Runs preflight, launches run.sh, arms the journal and workflow-journal monitors, knows what is safe to…

jasonm4130/claude-skills · 147 tokens

domain-modeling

Use when pinning down domain terminology, building a ubiquitous language or project glossary, disambiguating overloaded or vague terms, or maintaining a CONTEXT.md — or when another skill needs to sharpen the domain model. Do NOT use for recording architectural decisions (use adr) or for writing implementation specs.

jasonm4130/claude-skills · 63 tokens

plan

Use when the user has an idea, feature, or fix that is more than a one-sitting edit and says "plan this", "write a plan for X", "/nightshift:plan", or "what would it take to build X". Sizes the work (trivial → no artifact; medium → a lean plan; large → a short spec first), asks one question at a time until the design…

jasonm4130/claude-skills · 183 tokens

morning

Use when the user says "/nightshift:morning", "what happened overnight", "how did the night go", "why did the loop stop", or opens a session in a repo with a loop/ directory after a scheduled run. Reads the journal since the last start line and every open land / land:blocked pull request, says per stop what happened…