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 skills add pdurlej/jan-subagent --skill bmad-product-briefgit clone --depth 1 https://github.com/pdurlej/jan-subagentWrote 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/skills/pdurlej/jan-subagent/bmad-product-brief)<a href="https://agentmods.dev/skills/pdurlej/jan-subagent/bmad-product-brief"><img src="https://agentmods.dev/badge/skills/pdurlej/jan-subagent/bmad-product-brief/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/skills/pdurlej/jan-subagent/bmad-product-brief"><img src="https://agentmods.dev/badge/skills/pdurlej/jan-subagent/bmad-product-brief.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 | $0.00030 | $0.01200 |
| Opus 5 | $0.00015 | $0.00600 |
| Sonnet 5 | $0.00006 | $0.00240 |
| Haiku 4.5 | $0.00003 | $0.00120 |
Grade A, and why
bmad-product-brief 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 10d 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.
This is a copy
84% identical to bmad-product-brief — 58 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create Product Brief
Overview
This skill helps you create compelling product briefs through collaborative discovery, intelligent artifact analysis, and web research. Act as a product-focused Business Analyst and peer collaborator, guiding users from raw ideas to polished executive summaries. Your output is a 1-2 page executive product brief — and optionally, a token-efficient LLM distillate capturing all the detail for downstream PRD creation.
The user is the domain expert. You bring structured thinking, facilitation, market awareness, and the ability to synthesize large volumes of input into clear, persuasive narrative. Work together as equals.
Design rationale: We always understand intent before scanning artifacts — without knowing what the brief is about, scanning documents is noise, not signal. We capture everything the user shares (even out-of-scope details like requirements or platform preferences) for the distillate, rather than interrupting their creative flow.
Activation Mode Detection
Check activation context immediately:
-
Autonomous mode: If the user passes
--autonomous/-Aflags, or provides structured inputs clearly intended for headless execution:- Ingest all provided inputs, fan out subagents, produce complete brief without interaction
- Route directly to
prompts/contextual-discovery.mdwith{mode}=autonomous
-
Yolo mode: If the user passes
--yoloor says "just draft it" / "draft the whole thing":- Ingest everything, draft complete brief upfront, then walk user through refinement
- Route to Stage 1 below with
{mode}=yolo
-
Guided mode (default): Conversational discovery with soft gates
- Route to Stage 1 below with
{mode}=guided
- Route to Stage 1 below with
On Activation
- Load config from
{project-root}/_bmad/bmm/config.yamland resolve::- Use
{user_name}for greeting - Use
{communication_language}for all communications - Use
{document_output_language}for output documents - Use
{planning_artifacts}for output location and artifact scanning - Use
{project_knowledge}for additional context scanning
- Use
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/artifact-analyzer.md 2.4 KB
- agents/opportunity-reviewer.md 1.7 KB
- agents/skeptic-reviewer.md 1.5 KB
- agents/web-researcher.md 1.6 KB
- bmad-manifest.json 494 B
- prompts/contextual-discovery.md 2.5 KB
- prompts/draft-and-review.md 3.9 KB
- prompts/finalize.md 3.8 KB
- prompts/guided-elicitation.md 3.3 KB
- resources/brief-template.md 2.3 KB
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.
- 10d ago First seen · 88 lines · 30 tokens per session scan A 0324676e912b
bmad-product-brief is a skill published in the GitHub repository pdurlej/jan-subagent (0 stars, last pushed 5mo ago), licensed MIT. It adds 30 tokens to every session and 1,200 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to bmad-product-brief, differing in 58 lines, and is treated as a copy.
Other skills, from other repositories
nemo-curator
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or…
training-llms-megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA…
nemo-evaluator-sdk
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.
nemo-guardrails
NVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.
cudaq-guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
verify
Build, launch, drive, and screenshot the OpenNOW Electron settings UI on Windows.