research

research is a skill for Claude Code, Codex from byronxlg/skillfold. It costs 13 tokens per session (331 once invoked), scanned A, original, MIT.

A process for finding information, judging whether sources are trustworthy, and combining the findings into an answer. Sources can include official documentation, specifications, and working code.

In plain words
What is it for?
Use it to investigate technical questions, compare sources, clarify unclear documentation, and produce conclusions with references.
Why use it?
It reduces the risk of relying on the first search result, confusing opinion with fact, or missing conflicting and incomplete information.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to investigate technical questions, compare sources, clarify unclear documentation, and produce conclusions with references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/byronxlg/skillfold/research
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 byronxlg/skillfold --skill research
Clone the repo
git clone --depth 1 https://github.com/byronxlg/skillfold

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.

agentmods badge for research

README.md
[![agentmods](https://agentmods.dev/badge/skills/byronxlg/skillfold/research.svg)](https://agentmods.dev/skills/byronxlg/skillfold/research)
Your own site
<a href="https://agentmods.dev/skills/byronxlg/skillfold/research"><img src="https://agentmods.dev/badge/skills/byronxlg/skillfold/research.svg" alt="Measured on agentmods" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 331 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 $0.00013 $0.00331
Opus 5 $0.00006 $0.00166
Sonnet 5 $0.00003 $0.00066
Haiku 4.5 $0.00001 $0.00033

Measured 8d ago against content hash f28ed50de8a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, 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.

library/skills/research/SKILL.md · 39 lines

What it actually says

Research

You gather, evaluate, and synthesize information to answer questions and inform decisions. You are thorough but efficient - you search broadly, then focus on what matters.

Principles

  • Search broadly first, then narrow. Do not stop at the first result
  • Evaluate source quality - prefer primary sources, official documentation, and well-tested examples
  • Distinguish facts from opinions and assumptions
  • Note when information is incomplete or conflicting
  • Synthesize findings into actionable conclusions, not raw data dumps

Approach

When researching a topic:

  1. Define the question clearly. What exactly do you need to know, and why?
  2. Identify where the answer is likely to live (documentation, source code, APIs, specifications)
  3. Search multiple sources. Cross-reference findings to confirm accuracy
  4. For code-related research, read the actual source when documentation is ambiguous
  5. Track what you looked at and what you found (or did not find) in each source
  6. Summarize findings with references to where the information came from

Evaluating Sources

  • Official documentation and specifications are authoritative but may be outdated
  • Source code is the ground truth for how something actually works
  • Community answers may be helpful but can be wrong or stale - verify claims
  • If sources conflict, note the discrepancy and explain which you trust and why

Output

Present findings as a structured summary: the question, key findings with source references, confidence level, and any open gaps. Recommend next steps if the answer is incomplete.

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 · 39 lines · 13 tokens per session scan A f28ed50de8a0

Subscribe to this mod's changes

research is a skill published in the GitHub repository byronxlg/skillfold (12 stars, last pushed today), licensed MIT. It adds 13 tokens to every session and 331 once invoked, about $0.0001 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.