agentmods.dev

research-agent

research-agent is an agent for Claude Code from Kit4Some/Oh-my-ClaudeClaw. It costs 30 tokens per session (1,100 once invoked), scanned A, original, MIT.

A research-focused agent that searches the web from several angles, checks existing knowledge, rates evidence, and organizes findings into reports.

In plain words
What is it for?
Use it for investigating a topic, comparing options, checking sources, and storing connected findings for later use.
Why use it?
It reduces repeated research, missed alternatives, outdated information, and decisions based on weak sources.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; built for openclaw.

Part of the openclaw-cc plugin — 22 skills, 4 agents, 5 MCP servers shipped together

not rated 4repo 5mo ago A scan 30 tokens original MIT

Good fit Use it for investigating a topic, comparing options, checking sources, and storing connected findings for later use.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kit4some/oh-my-claudeclaw/research-agent
View source ↗ Kit4Some/Oh-my-ClaudeClaw
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.

Clone the repo
git clone --depth 1 https://github.com/Kit4Some/Oh-my-ClaudeClaw

Made for: Claude Code.

Or install openclaw-cc, the plugin that ships this one along with the rest of its 22 skills, 4 agents, 5 MCP servers.

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

README.md
[![agentmods](https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/research-agent.svg)](https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/research-agent)
Your own site
<a href="https://agentmods.dev/agents/kit4some/oh-my-claudeclaw/research-agent"><img src="https://agentmods.dev/badge/agents/kit4some/oh-my-claudeclaw/research-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 30 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,100 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 $0.00030 $0.01100
Opus 5 $0.00015 $0.00550
Sonnet 5 $0.00006 $0.00220
Haiku 4.5 $0.00003 $0.00110

Measured 7d ago against content hash 7eaff63e1bec, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

research-agent 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 7d 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/agents/research-agent.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Agent

Role

You conduct comprehensive web research with automatic deduplication against existing memory, evidence-quality ranking, and knowledge graph integration. Every research output is structured, stored, and connected.

Why_This_Matters

Research quality directly impacts decision-making. Poor research leads to: building on outdated information, missing critical alternatives, duplicating known knowledge, and wasting time re-discovering what was already found. Your evidence ranking prevents the team from acting on weak signals.

Success_Criteria

  • Every research finding has an evidence strength rating
  • Zero duplicate storage (always check memory_similar before storing)
  • All findings linked to related memories via memory_link
  • Multi-angle coverage: at least 3 different search queries per topic
  • Sources cited with URLs, dates, and reliability assessment

Investigation_Protocol

Research Workflow

  1. Check existing knowledge first:

    • memory_search(query, associative: true) — what do we already know?
    • memory_search(tag: "{topic}") — tagged prior research
    • If sufficient recent knowledge exists, synthesize rather than re-research

  2. Multi-angle search (minimum 3 queries):

    • Query 1: Direct topic search (English)
    • Query 2: Alternative framing or competitor angle
    • Query 3: Recent developments ("{topic} 2026 latest")

  3. Content collection:

    • Fetch top 3-5 results per query
    • Extract key facts, data points, and conclusions
    • Note source URL, publication date, author credibility

  4. Evidence ranking (apply to each finding):

    • Tier 1 (Strongest): Primary source data, official documentation, peer-reviewed
    • Tier 2: Multiple independent sources converging on same conclusion
    • Tier 3: Single credible source with detailed methodology
    • Tier 4: Blog posts, opinions, anecdotal evidence
    • Tier 5 (Weakest): Undated content, unknown authors, speculation

  5. Deduplication:

    • memory_similar(text: finding_summary, threshold: 0.7) for each key finding
    • If similar exists: memory_update to append new data
    • If new: memory_store with proper categorization

Read the full file on GitHub · 101 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. 7d ago First seen · 101 lines · 30 tokens per session scan A 7eaff63e1bec

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository Kit4Some/Oh-my-ClaudeClaw (4 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 1,100 once invoked, about $0.0002 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.

Claude CodeResearchai-agentai-assistantautonomous-agentclaude-code-plugindiscord-bot
Related

Other agents, from other repositories

gemini-reviewer

Use proactively when finalizing a diff or PR for a generalist third-reviewer pass that the other agents do not cover: security, threading correctness, library/version drift, doc accuracy, dead code, and complexity. NOT for research (use gemini-researcher), claim validation (use gemini-validator), or devil's-advocate…

azmym/gemini-plugin · 99 tokens

gemini-summarizer

Use proactively at session start (BUILDRISKMAP) and before context compaction (SUMMARIZESESSIONSTATE). Compresses session history into structured summaries preserving decisions, discarded alternatives, and unresolved debt. Writes risk maps for new repositories.

azmym/gemini-plugin · 57 tokens

gemini-challenger

Use proactively before destructive operations, when evaluating architectural choices, or when the main agent appears stuck in a pattern. Devil's advocate that argues at least 2 alternative approaches and 1 reason the current path is wrong. Returns structured JSON {alternatives, objections, mustaddress}.

azmym/gemini-plugin · 64 tokens

gemini-researcher

Use proactively when a question involves post-training-cutoff information, live API docs, recent CVEs, library releases, or any claim that needs a primary source. Performs search-grounded research and deep research via Gemini. Never opines without a citation. Returns answer + citations.

azmym/gemini-plugin · 64 tokens

gemini-validator

Use proactively after a plan is finalized, after Claude claims a task is done, or before a destructive change. Validates the artifact against the original ask and flags gaps, hallucinations, and missed acceptance criteria. Returns structured JSON {verdict, gaps, hallucinations, nextactions}.

azmym/gemini-plugin · 63 tokens

version-reviewer

Use before tagging a release, merging a release PR, or whenever the user asks to audit dependency freshness. Runs the version-sentinel check across all manifests in the working directory, interprets DRIFT vs intentional-pin rows, and produces a structured report with recommended actions. Read-only — does not edit…

KSEGIT/Version-Sentinel · 65 tokens