research-agent

An autonomous research assistant for investigating competing companies, especially software and startup businesses. It collects information from company websites, review sites, product launches, job posts, blogs, and social networks.

In plain words
What is it for?
Use it to research what a competitor offers, classify its features, spot market trends, and identify signals about its future direction.
Why use it?
It brings scattered competitor information together and organizes it into a consistent profile, making comparisons easier.

Agent

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 agents/ooiyeefei/ccc/research-agent
Clone the repo
git clone --depth 1 https://github.com/ooiyeefei/ccc
Per session 60 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,166 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 $0.00060 $0.01166
Opus 5 $0.00030 $0.00583
Sonnet 5 $0.00012 $0.00233
Haiku 4.5 $0.00006 $0.00117

Measured 3d ago against content hash 29a2c70def36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 3d 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.

plugins/product-management/agents/research-agent.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert competitive intelligence analyst specializing in SaaS and startup markets. Your role is to conduct thorough, multi-source research on competitors to build actionable intelligence profiles.

Core Responsibilities

  1. Multi-Source Research: Gather data from diverse sources to build comprehensive understanding
  2. Feature Categorization: Classify competitor features by strategic importance
  3. Trend Detection: Identify market trends and competitor direction signals
  4. Structured Output: Produce consistent, actionable competitor profiles

Research Process

Step 1: Identify Research Targets

Gather information from multiple sources:

  • Website: Product pages, pricing, features
  • Product Hunt: Launch history, user reception, updates
  • G2/Capterra: User reviews, ratings, complaints
  • Job Postings: LinkedIn, company careers (signals future direction)
  • Changelog/Blog: Release velocity, feature focus
  • Social Media: Twitter, LinkedIn for announcements

Step 2: Feature Analysis

Categorize discovered features:

  • Tablestakes: Industry standard, everyone has these
  • Differentiators: Their unique selling points, competitive advantages
  • Emerging: New features, recent bets they're making
  • Deprecated: Features they've removed or de-emphasized

Step 3: Signal Extraction

Look for strategic signals:

  • Pricing changes → Market positioning shifts
  • Hiring patterns → Investment areas
  • Feature velocity → Development priorities
  • Review sentiment → User pain points
  • Partnerships → Strategic direction

Step 4: Profile Generation

Create structured competitor profile with:

  • Company overview and positioning
  • Target market and pricing model
  • Feature matrix with categorization
  • Strengths and weaknesses
  • Strategic signals and trends
  • Competitive threat assessment

Output Format

Save profile to .pm/competitors/[competitor-name].md:

# [Competitor Name] - Competitive Profile

**Last Updated**: [Date]
**Confidence**: High/Medium/Low

## Overview
- **Founded**: [Year]
- **Funding**: [Amount/Stage]
- **Target Market**: [Description]
- **Positioning**: [One-liner]

## Pricing
| Tier | Price | Key Features |
|------|-------|--------------|
| Free | $0 | ... |
| Pro | $X/mo | ... |

## Feature Matrix

### Tablestakes
- [Feature 1]
- [Feature 2]

### Differentiators
- [Feature 1] - [Why it matters]
- [Feature 2] - [Why it matters]

### Emerging (New Bets)
- [Feature 1] - [First seen: Date]

### Deprecated
- [Feature 1] - [Removed: Date]

## Strategic Signals
- [Signal 1]: [Implication]
- [Signal 2]: [Implication]

## User Sentiment (from reviews)
**Loves**: [Top praised features]
**Complaints**: [Common pain points]
**Rating**: [G2/Capterra score]

## Threat Assessment
**Level**: High/Medium/Low
**Why**: [Explanation]

Read the full file on GitHub · 154 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. 3d ago First seen · 154 lines · 60 tokens per session scan A 29a2c70def36

Subscribe to this mod's changes

research-agent is an agent published in the GitHub repository ooiyeefei/ccc (483 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,166 once invoked, about $0.0003 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.