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 skills/pdurlej/jan-subagent/bmad-initnpx skills add pdurlej/jan-subagent --skill bmad-initgit 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-init)<a href="https://agentmods.dev/skills/pdurlej/jan-subagent/bmad-init"><img src="https://agentmods.dev/badge/skills/pdurlej/jan-subagent/bmad-init.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.01104 |
| Opus 5 | $0.00017 | $0.00552 |
| Sonnet 5 | $0.00007 | $0.00221 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
bmad-init 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.
This is a copy
100% identical to bmad-init — 0 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill is the configuration entry point for all BMad skills. It has two modes:
- Fast path: Config exists for the requested module — returns vars as JSON. Done.
- Init path: Config is missing — walks the user through configuration, writes config files, then returns vars.
Every BMad skill should call this on activation to get its config vars. The caller never needs to know whether init happened — they just get their config back.
The script bmad_init.py is located in this skill's scripts/ directory. Locate and run it using python for all commands below.
On Activation — Fast Path
Run the bmad_init.py script with the load subcommand. Pass --project-root set to the project root directory.
- If a module code was provided by the calling skill, include
--module {module_code} - To load all vars, include
--all - To request specific variables with defaults, use
--vars var1:default1,var2 - If no module was specified, omit
--moduleto get core vars only
If the script returns JSON vars — store them as {var-name} and return to the calling skill. Done.
If the script returns an error or init_required — proceed to the Init Path below.
Init Path — First-Time Setup
When the fast path fails (config missing for a module), run this init flow.
Step 1: Check what needs setup
Run bmad_init.py with the check subcommand, passing --module {module_code}, --skill-path {calling_skill_path}, and --project-root.
The response tells you what's needed:
"status": "ready"— Config is fine. Re-run load."status": "no_project"— Can't find project root. Ask user to confirm the project path."status": "core_missing"— Core config doesn't exist. Must ask core questions first."status": "module_missing"— Core exists but module config doesn't. Ask module questions.
The response includes:
core_module— Core module.yaml questions (when core setup needed)target_module— Target module.yaml questions (when module setup needed, discovered from--skill-pathor_bmad/{module}/)core_vars— Existing core config values (when core exists but module doesn't)
What ships with it
3 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.
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.
- 5d ago First seen · 101 lines · 34 tokens per session scan A fd3c96b86bc0
bmad-init is a skill published in the GitHub repository pdurlej/jan-subagent (0 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 1,104 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to bmad-init, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
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-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…
cudaq-guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
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.
verify
Build, launch, drive, and screenshot the OpenNOW Electron settings UI on Windows.