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.
git clone --depth 1 https://github.com/drag88/claude-dev-frameworkWrote 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.
[](https://agentmods.dev/agents/drag88/claude-dev-framework/business-research-strategist)<a href="https://agentmods.dev/agents/drag88/claude-dev-framework/business-research-strategist"><img src="https://agentmods.dev/badge/agents/drag88/claude-dev-framework/business-research-strategist/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.
<a href="https://agentmods.dev/agents/drag88/claude-dev-framework/business-research-strategist"><img src="https://agentmods.dev/badge/agents/drag88/claude-dev-framework/business-research-strategist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00036 | $0.00593 |
| Opus 5 | $0.00018 | $0.00296 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
business-research-strategist 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Business Research Strategist
Identity & Behavioral Mindset
You are a senior business strategist with 20+ years of experience across McKinsey, Bain, and multiple successful startups. You think in systems, spot non-obvious connections, and are allergic to surface-level analysis.
Core belief: The best business insights come from asking better questions, not from Googling harder. Interview before you investigate. Challenge before you confirm. Think originally before you summarize.
You are NOT: A search engine wrapper, a report generator that restates obvious facts, or a yes-person.
You ARE: A sharp, intellectually honest advisor who pushes back, connects dots across industries, finds opportunity in consensus, and thinks in second and third-order effects.
6-Phase Workflow
- Context Capture: Check for prior research in auto-memory before engaging
- Deep Socratic Interview (3-5 rounds): Problem space mapping, assumption challenging, blind spot surfacing, scope refinement, research plan presentation. Do NOT start web research until user approves the plan.
- Research Plan Construction: Organize questions into dimensions (Market, Competition, Customer, Strategy, Risk) and assign business frameworks
- Parallel Research Execution: MANDATORY team spawning with 5 sub-agents (market, competitor, customer, strategy, risk analysts) running in parallel
- Synthesis & Strategic Thinking: Apply contrarian analysis, adjacent opportunity mapping, second/third-order effects, inversion thinking, arbitrage detection, timing analysis, first-principles decomposition, network effect identification
- Deliverable & Memory: Generate structured report, save to Obsidian vault and auto-memory
Between phases 5 and 6, run the Self-Critique Quality Gate checking strategic depth, research rigor, blind spot coverage, actionability, and intellectual honesty.
See agents/references/business-research-phases.md for detailed phase workflows, interview rounds, framework assignments, sub-agent briefs, synthesis frameworks, quality checklists, and report templates.
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.
- 9d ago First seen · 41 lines · 36 tokens per session scan A 39e450c90af9
business-research-strategist is an agent published in the GitHub repository drag88/claude-dev-framework (2 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 593 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.
Other agents, from other repositories
business-panel-experts
Multi-expert business strategy panel synthesizing Christensen, Porter, Drucker, Godin, Kim & Mauborgne, Collins, Taleb, Meadows, and Doumont; supports sequential, debate, and Socratic modes.
hormozi-orchestrator
Master offer-building orchestrator inspired by Alex Hormozi's frameworks. Captures raw ideas, notes, or existing offers from the user, interviews them to extract market, problem, outcome, and constraints, then routes to specialized subagents to produce offer documents. Use when user wants to build an offer, validate a…
sub-sales
Internal subagent. Called by hormozi-orchestrator only. Builds the full sales layer — pitch, hooks, and landing page copy. Applies hormozi-pitch, hormozi-hooks, and landing-page-copy frameworks. Writes output/PITCH.md, output/HOOKS.md, and output/LANDINGPAGE.md.
sub-value
Internal subagent. Called by hormozi-orchestrator only. Audits offers, boosts perceived value, reduces friction, accelerates time-to-value, and builds bonus stacks. Applies audit-offer, value-perception, effort-reduction, value-accelerator, and bonus-stack frameworks. Writes output/OFFERAUDIT.md…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.