web-research

A structured method for researching topics on the web and presenting organized findings with citations.

In plain words
What is it for?
Use it for current information, product or concept comparisons, documentation research, news, and cited summaries.
Why use it?
It gives research a defined question, focused subtopics, suitable source types, credibility checks, and traceable sources.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/ap3x-dev/ag3nt/web-research
Any agent
npx skills add AP3X-Dev/AG3NT --skill web-research
Clone the repo
git clone --depth 1 https://github.com/AP3X-Dev/AG3NT

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 831 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00017 $0.00831
Opus 5 $0.00009 $0.00415
Sonnet 5 $0.00003 $0.00166
Haiku 4.5 $0.00002 $0.00083

Measured 3d ago against content hash 296e96d2aa85, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

web-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 3d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate-report.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/web-research/SKILL.md · 118 lines

How it starts

The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Web Research Skill

Use this skill when the user needs:

  • Current information on any topic
  • Comparison between products, services, or concepts
  • Documentation or official sources
  • News or recent developments
  • Cited summaries with sources

Research Workflow

Step 1: Plan Your Research

Before searching, define:

  1. Main question: What specifically does the user want to know?
  2. Subtopics: Break complex topics into 2-3 focused areas
  3. Source types: What kinds of sources are most relevant?
    • Documentation (official docs, specs)
    • News (recent articles, announcements)
    • Academic (papers, research)
    • Community (forums, discussions, reviews)

Step 2: Search and Gather

For each subtopic:

  1. Run 2-3 targeted searches using the web_search tool
  2. Evaluate sources for credibility:
    • Official domains (.gov, .edu, company sites)
    • Publication date (prefer recent for evolving topics)
    • Author expertise
  3. Extract key information and note the source URL

Step 3: Organize Findings

Create a structured output:

## Research: [Topic Name]

### Key Findings
- Finding 1 [Source](url)
- Finding 2 [Source](url)

### Detailed Summary
[Synthesis of information with inline citations]

### Sources
1. [Title](url) - Brief description of what this source provided
2. [Title](url) - Brief description of what this source provided

Step 4: Synthesize and Respond

When presenting to the user:

  1. Lead with the answer - Don't bury the key information
  2. Provide context - Why is this relevant?
  3. Cite sources - Use inline links or footnotes
  4. Note limitations - If information is incomplete or conflicting, say so

Citation Format

Use this format for citations:

  • Inline: According to [Source Name](url), ...
  • Footnote: Key fact here[^1] with [^1]: Source Name - url
  • List: See references/citation-format.md for detailed examples

Quality Checklist

Before finishing research:

  • Answered the user's core question
  • Used at least 2-3 distinct sources
  • Cited all factual claims
  • Noted if information is dated or incomplete
  • Provided actionable next steps if relevant

Read the full file on GitHub · 118 lines

Files

What ships with it

2 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.

  1. 3d ago First seen · 118 lines · 17 tokens per session scan A 296e96d2aa85

Subscribe to this mod's changes

web-research is a skill published in the GitHub repository AP3X-Dev/AG3NT (9 stars, last pushed 3mo ago), licensed MIT. It adds 17 tokens to every session and 831 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 2026-08-31.