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.
npx agentmods add commands/webdevtodayjason/titanium-plugins/bmad-researchgit clone --depth 1 https://github.com/webdevtodayjason/titanium-pluginsWhat 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 | $0.00006 | $0.03162 |
| Opus 5 | $0.00003 | $0.01581 |
| Sonnet 5 | $0.00001 | $0.00632 |
| Haiku 4.5 | $0.00001 | $0.00316 |
Grade A, and why
bmad-research 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 2d 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 — 577 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BMAD Research - Generate Research Prompts
You are helping the user research technical decisions by generating comprehensive research prompts for web-based AI (ChatGPT, Claude web) which have web search capabilities.
Purpose
Generate structured research prompts that users can copy to ChatGPT/Claude web to research:
- API vendors and data sources
- Authentication providers
- Hosting platforms
- Payment processors
- Third-party integrations
- Technology stack options
Results are documented in structured templates and referenced during architecture generation.
When to Use
During BMAD workflow:
- After PRD mentions external APIs/vendors
- Before architecture generation
- When technical decisions need research
Standalone:
- Evaluating vendor options
- Comparing technologies
- Cost analysis
- Technical due diligence
Process
Step 1: Identify Research Topic
If user provided topic:
# User ran: /bmad:research "data vendors for precious metals"
- Topic = "data vendors for precious metals"
If no topic:
- Ask: "What do you need to research?"
- Show common topics:
Common research topics: 1. Data vendors/APIs 2. Hosting platforms (Railway, Vercel, GCP, etc.) 3. Authentication providers (Clerk, Auth0, custom, etc.) 4. Payment processors (Stripe, PayPal, etc.) 5. AI/ML options (OpenAI, Anthropic, self-hosted) 6. Database options 7. Other (specify) Topic:
Step 2: Gather Context from PRD
If PRD exists:
Read bmad-backlog/prd/prd.md
Extract relevant context:
- What features need this research?
- What are the constraints? (budget, performance)
- Any technical preferences mentioned?
If no PRD:
- Use topic only
- Generate generic research prompt
- Note: "Research will be more focused with a PRD"
Step 3: Generate Research Prompt
Create comprehensive prompt for web AI.
Topic slug: Convert topic to filename-safe string
topic_slug = topic.lower().replace(' ', '-').replace('/', '-')
# "data vendors for precious metals" → "data-vendors-for-precious-metals"
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.
- 2d ago First seen · 577 lines · 6 tokens per session scan A 212adb332914
bmad-research is a command published in the GitHub repository webdevtodayjason/titanium-plugins (7 stars, last pushed 7mo ago), licensed MIT. It adds 6 tokens to every session and 3,162 once invoked, about $0.0000 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.