ALBA: Skill for Claude Code

.claude/skills/research/SKILL.md

research is a skill for Claude Code from onurpolat05/ALBA. It costs 117 tokens per session (1,112 once invoked), scanned A, original, MIT.

A structured web-research workflow that gathers sources and produces a cited summary with confidence levels. It supports a quick mode and a deeper mode with more sources and saved analysis.

In plain words
What is it for?
Use it to research a topic, investigate its current state, or find information that needs source-backed reporting.
Why use it?
It organizes online investigation and makes the supporting sources and certainty of conclusions explicit.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: agent in frontmatter; mentions CLAUDE.md; mentions subagents.

This is onurpolat05/ALBA's own configuration. It tells Claude Code how to work on ALBA itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ALBA configures →

Reuse

Borrowing it

Nothing to install: this file belongs to onurpolat05/ALBA. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/onurpolat05/ALBA/main/.claude/skills/research/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/onurpolat05/ALBA

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 research

README.md
[![agentmods](https://agentmods.dev/badge/skills/onurpolat05/alba/research.svg)](https://agentmods.dev/skills/onurpolat05/alba/research)
Your own site
<a href="https://agentmods.dev/skills/onurpolat05/alba/research"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 117 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,112 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 $0.00117 $0.01112
Opus 5 $0.00059 $0.00556
Sonnet 5 $0.00023 $0.00222
Haiku 4.5 $0.00012 $0.00111

Measured 8d ago against content hash 5db44911feb7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, 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 8d 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.

.claude/skills/research/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/research - Web Research

Perform structured web research on any topic. Runs as a subagent (fork) to keep main context clean.

Why background: false

context: fork alone is not enough. Since Claude Code v2.1.218, forked skills default to background: true — they run detached and the result arrives as a later notification instead of in the turn that invoked the skill. Research is a request for an answer now, so this skill pins background: false: the fork still keeps its search noise out of the main context, but the conversation waits for the report and hands it back inline.

If you copy this skill into a workflow where you genuinely want fire-and-forget research (e.g. kicked off by a scheduled task), drop the background: false line.

Requires Claude Code v2.1.218 or later. On older versions the field is ignored and the skill runs inline-blocking as it always did.

Input

/research [topic]
/research [topic] deep

$ARGUMENTS carries the whole invocation; the trailing word deep selects deep mode.

  • Default (quick): 3-5 sources, summary format
  • Deep: 8-10 sources, full analysis with confidence ratings

Process

1. Search Strategy

Use available tools with graceful fallback:

Priority Tool Best For
1st mcp__exa__web_search_exa Semantic search, finding relevant articles
2nd mcp__firecrawl__firecrawl_search Search + scrape combined
3rd WebSearch (built-in) Basic web search
4th WebFetch (built-in) Fetch specific URLs

Fallback rule: If an MCP tool is unavailable, skip it and use the next available. WebSearch + WebFetch are always available as baseline.

The Exa and Firecrawl entries in allowed-tools are there so the chain works for people who do have those MCP servers connected. MCP servers are optional in ALBA — if you never install them, those entries simply never match anything and the skill runs on the built-in tools.

2. Gather & Validate

Read the full file on GitHub · 136 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. 8d ago First seen · 136 lines · 117 tokens per session scan A 5db44911feb7

Subscribe to this mod's changes

research is a skill published in the GitHub repository onurpolat05/ALBA (20 stars, last pushed 1mo ago), licensed MIT. It adds 117 tokens to every session and 1,112 once invoked, about $0.0006 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 2026-08-30.