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.
curl -O https://raw.githubusercontent.com/onurpolat05/ALBA/main/.claude/skills/research/SKILL.mdgit clone --depth 1 https://github.com/onurpolat05/ALBAWrote 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.
[](https://agentmods.dev/skills/onurpolat05/alba/research)<a href="https://agentmods.dev/skills/onurpolat05/alba/research"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/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.
<a href="https://agentmods.dev/skills/onurpolat05/alba/research"><img src="https://agentmods.dev/badge/skills/onurpolat05/alba/research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00117 | $0.01112 |
| Opus 5.5 | $0.00047 | $0.00445 |
| Sonnet 5.5 | $0.00023 | $0.00222 |
| Haiku 4.5 | $0.00012 | $0.00111 |
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 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.
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.
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
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 First seen · 136 lines · 117 tokens per session scan A 5db44911feb7
research is a skill published in the GitHub repository onurpolat05/ALBA (23 stars, last pushed 3mo ago), licensed MIT. It adds 117 tokens to every session and 1,112 once invoked, about $0.0005 per session on Opus 5.5. 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.
Other skills, from other repositories
loongsuite-pilot-insight
A reporting workflow for turning LoongSuite Pilot and AI coding-agent logs into structured reports about events, teams, data quality, development efficiency, and AI use. It defines the meaning of the log fields and the measurements used in dashboards.
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
skill-creator
A skill for creating or improving reusable instructions for an agent. It covers capturing the intended workflow, writing a draft, testing it, and refining its trigger description.
repo
Repository operating rules for verified Mythos edits.
talk-stage5-script
Produces a complete 5-act pitch with speaker notes, a slide-by-slide specification, and a ready-to-paste Kimi prompt for AI slide generation. Requires validated angle and title from Stage 4. Use when you have a confirmed talk angle and need the full script, slide spec, and AI-generated presentation prompt.