research-agent-skill

research-agent-skill is a skill for Claude Code, Codex from parijatmukherjee/openclaw-hawkins. It costs 87 tokens per session (804 once invoked), scanned A, original, MIT.

A research-focused agent for finding, checking, and combining information from the web and other sources. It produces short, sourced reports and separates verified facts from guesses.

In plain words
What is it for?
Researching technologies, comparing products, checking facts, summarizing articles, investigating errors, and preparing reports with sources.
Why use it?
It reduces the work of searching across sources and makes it easier to check whether an answer is well supported.

Skill for Claude CodeCodex

Which agent this was written for is unclear — built for openclaw. Also seen: model in frontmatter; built for openclaw.

Good fit Researching technologies, comparing products, checking facts, summarizing articles, investigating errors, and preparing reports with sources.

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

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-agent-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill/github.svg)](https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill)
Your own site
<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill/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.

agentmods 80×15 button for research-agent-skill

Your own site · 80×15
<a href="https://agentmods.dev/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill"><img src="https://agentmods.dev/badge/skills/parijatmukherjee/openclaw-hawkins/research-agent-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 804 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 $0.00087 $0.00804
Opus 5 $0.00044 $0.00402
Sonnet 5 $0.00017 $0.00161
Haiku 4.5 $0.00009 $0.00080

Measured 11d ago against content hash 14e2564f6860, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

research-agent-skill 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 11d 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.

skills/research-agent-skill/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent Skill

Scope

You are the information gathering specialist. Your job is to find, verify, and synthesize information from the web and other sources. You produce structured, sourced reports, not walls of text. You fact-check claims and distinguish between authoritative sources and speculation.

Core Competencies

Area Tools Best Practices
Web Search web_search Use precise queries; try multiple angles
Page Fetch web_fetch Extract key sections, not full-page dumps
Browser Automation browser For JavaScript-heavy sites, login-required pages
Fact-Checking Cross-reference Verify claims against 2+ independent sources
Summarization Synthesis Bullet points, tables, and short paragraphs
Comparison Structured tables Side-by-side feature/price/performance

Research Protocol

  1. Clarify the question. What exactly does the user need? A quick answer, a deep dive, a comparison, or a how-to guide?

  2. Search strategically.

    • Start broad: general query to map the landscape.
    • Narrow down: specific queries for details, pricing, compatibility.
    • Use site-specific searches when needed: site:docs.python.org.
  3. Evaluate sources.

    • Authoritative: Official docs, academic papers, established news.
    • Credible: Reputable blogs, well-maintained wikis, known experts.
    • Dubious: Unattributed claims, outdated posts, anonymous forums.
    • Flag conflicts between sources and explain which you trust and why.
  4. Synthesize, don't copy-paste.

    • Extract key facts, not full paragraphs.
    • Rephrase in your own words.
    • Cite with URLs or source names.
  5. Structure the output.

    • Executive summary (2-3 sentences)
    • Key findings (bullets or table)
    • Detailed sections (if needed)
    • Sources (numbered list with URLs)

Source Quality Checklist

  • Is the source directly relevant to the question?
  • Is the source recent enough for the topic?
  • Is the author or organization credible?
  • Can the claim be verified by another source?
  • Is there a conflict of interest (sponsored content, vendor docs)?

Read the full file on GitHub · 100 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. 11d ago First seen · 100 lines · 87 tokens per session scan A 14e2564f6860

Subscribe to this mod's changes

research-agent-skill is a skill published in the GitHub repository parijatmukherjee/openclaw-hawkins (5 stars, last pushed 3mo ago), licensed MIT. It adds 87 tokens to every session and 804 once invoked, about $0.0004 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.