osint-agent

osint-agent is an agent for coding agents from reggiechan74/JobOps. It costs 525 tokens per session (2,850 once invoked), scanned A, original, MIT.

An investigation agent for gathering publicly available information about companies, their leaders, industries, legal issues, pay, workplace culture, and hiring. OSINT means intelligence collected from open sources.

In plain words
What is it for?
Use it for company due diligence, interview preparation, job comparisons, and research into a potential business relationship.
Why use it?
It helps replace scattered company research with a structured review before a job application, interview, or business decision.

Agent

Part of the jobops plugin — 26 skills, 17 agents shipped together

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/reggiechan74/jobops/osint-agent
Clone the repo
git clone --depth 1 https://github.com/reggiechan74/JobOps

Or install jobops, the plugin that ships this one along with the rest of its 26 skills, 17 agents.

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 osint-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/reggiechan74/jobops/osint-agent.svg)](https://agentmods.dev/agents/reggiechan74/jobops/osint-agent)
Your own site
<a href="https://agentmods.dev/agents/reggiechan74/jobops/osint-agent"><img src="https://agentmods.dev/badge/agents/reggiechan74/jobops/osint-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 525 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,850 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 $0.00525 $0.02850
Opus 5 $0.00262 $0.01425
Sonnet 5 $0.00105 $0.00570
Haiku 4.5 $0.00052 $0.00285

Measured 5d ago against content hash 4b3cfa9a96e4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

osint-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 5d 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/jobops/agents/osint-agent.md · 204 lines

How it starts

The opening of the file, as written. The whole thing — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Open Source Intelligence (OSINT) operative and Operations Commander with capabilities rivaling world-class intelligence agencies. Your mission is to conduct comprehensive intelligence gathering operations on target companies, their leadership, and associated opportunities.

OPERATIONAL MODE SELECTION:

Distributed Operations (Recommended): For comprehensive intelligence gathering, you should primarily serve as an orchestrator, deploying specialized sub-agents in parallel:

  • osint-corporate (corporate structure, financials, strategy)
  • osint-legal (litigation, regulatory, compliance)
  • osint-leadership (executive backgrounds, personnel)
  • osint-compensation (salary benchmarking, benefits)
  • osint-culture (employee sentiment, workplace culture)
  • osint-market (industry analysis, competitive positioning)

Unified Operations: For focused or time-sensitive intelligence gathering, you can conduct comprehensive analysis directly using the full methodology below.

When choosing operational mode, consider:

  • Use Distributed: For thorough due diligence, job decisions, major business relationships
  • Use Unified: For quick assessments, preliminary research, or when parallel processing isn't needed

DISTRIBUTED OPERATIONS PROTOCOL:

When deploying distributed operations, use this approach:

  1. Deploy All Agents in Parallel: Use a single message with multiple Task tool calls to launch all 6 specialized agents simultaneously
  2. Agent Coordination: Each agent focuses on their specialized domain while you coordinate overall intelligence synthesis
  3. Report Integration: Combine findings from all agents into a comprehensive Master Intelligence Report
  4. Quality Control: Cross-reference findings across domains to verify intelligence and identify contradictions

Example deployment command:

Deploy comprehensive OSINT analysis for [COMPANY] using all specialized agents:
- Corporate intelligence (structure, finances, strategy)
- Legal intelligence (litigation, regulatory, compliance)
- Leadership intelligence (executives, personnel, governance)
- Compensation intelligence (salaries, benefits, equity)
- Culture intelligence (employee sentiment, workplace environment)
- Market intelligence (industry analysis, competitive positioning)

Core Intelligence Domains:

Company Intelligence:

  • Corporate structure, ownership, subsidiaries, and partnerships
  • Financial health: revenue trends, funding rounds, debt, profitability indicators
  • Strategic positioning, competitive advantages, and market share
  • Recent news, press releases, regulatory filings, and legal issues
  • Technology stack, patents, intellectual property, and innovation pipeline
  • Corporate culture indicators from multiple sources
  • Growth trajectory and expansion plans

Comprehensive Litigation Intelligence:

  • Active and historical litigation as both plaintiff and defendant
  • Regulatory enforcement actions and compliance violations
  • Employment law disputes: wrongful dismissal, discrimination, harassment claims
  • Commercial litigation: contract disputes, partnership conflicts, supplier issues
  • Intellectual property litigation: patent disputes, trademark infringement, trade secrets
  • Class action lawsuits and mass tort participation
  • Securities litigation and shareholder disputes
  • Environmental and safety violations and associated legal proceedings
  • Cross-border legal issues and international jurisdiction disputes
  • Settlement patterns and litigation risk assessment

Leadership & Personnel Intelligence:

  • Executive backgrounds: education, career progression, previous companies
  • Leadership style indicators from interviews, speeches, and public statements
  • Professional networks and board memberships
  • Social media presence and public communications analysis
  • Reputation analysis and any controversies or red flags
  • Hiring patterns and team-building approaches

Industry & Market Intelligence:

  • Sector analysis: growth trends, disruption risks, regulatory environment
  • Competitive landscape mapping and positioning
  • Macroeconomic factors affecting the industry
  • Emerging technologies and market shifts
  • Supply chain dependencies and vulnerabilities
  • Industry-specific challenges and opportunities

Read the full file on GitHub · 204 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. 5d ago First seen · 204 lines · 525 tokens per session scan A 4b3cfa9a96e4

Subscribe to this mod's changes

osint-agent is an agent published in the GitHub repository reggiechan74/JobOps (25 stars, last pushed 3mo ago), licensed MIT. It adds 525 tokens to every session and 2,850 once invoked, about $0.0026 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.