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 LarsCowe/bmalph --skill bmad-create-prdgit clone --depth 1 https://github.com/LarsCowe/bmalphWrote 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/larscowe/bmalph/bmad-create-prd)<a href="https://agentmods.dev/skills/larscowe/bmalph/bmad-create-prd"><img src="https://agentmods.dev/badge/skills/larscowe/bmalph/bmad-create-prd/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/larscowe/bmalph/bmad-create-prd"><img src="https://agentmods.dev/badge/skills/larscowe/bmalph/bmad-create-prd.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.00053 |
| Opus 5.5 | $0.00015 | $0.00021 |
| Sonnet 5.5 | $0.00007 | $0.00011 |
| Haiku 4.5 | $0.00004 | $0.00005 |
Grade A, and why
bmad-create-prd 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 1mo 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.
Copies of this mod
8 near-identical copies found in the catalogue:
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical, 0 lines differ
- bmad-create-prd — 100% identical
- bmad-create-prd — 100% identical, 0 lines differ
What it actually says
Follow the instructions in ./workflow.md.
What ships with it
21 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.
- bmad-skill-manifest.yaml 12 B
- data/domain-complexity.csv 7.2 KB
- data/prd-purpose.md 7.1 KB
- data/project-types.csv 3.1 KB
- steps-c/step-01-init.md 7.6 KB
- steps-c/step-01b-continue.md 5.6 KB
- steps-c/step-02-discovery.md 7.9 KB
- steps-c/step-02b-vision.md 6.6 KB
- steps-c/step-02c-executive-summary.md 7.1 KB
- steps-c/step-03-success.md 9.0 KB
- steps-c/step-04-journeys.md 8.8 KB
- steps-c/step-05-domain.md 6.8 KB
- steps-c/step-06-innovation.md 8.5 KB
- steps-c/step-07-project-type.md 8.6 KB
- steps-c/step-08-scoping.md 7.7 KB
- steps-c/step-09-functional.md 9.0 KB
- steps-c/step-10-nonfunctional.md 8.8 KB
- steps-c/step-11-polish.md 9.1 KB
- steps-c/step-12-complete.md 4.7 KB
- templates/prd-template.md 164 B
- workflow.md 2.8 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.
- 1mo ago First seen · 7 lines · 37 tokens per session scan A 24de81d7553b
bmad-create-prd is a skill published in the GitHub repository LarsCowe/bmalph (405 stars, last pushed 14d ago), licensed MIT. It adds 37 tokens to every session and 53 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
ensemble-beads-build
Drive an existing bead hierarchy to completion through the full builder, code-review, and close pipeline (Codex skill for /ensemble:beads-build).
ensemble-beads-plan
Analyze an existing bead hierarchy and produce bv analysis and wheel instructions without executing any implementation (Codex skill for /ensemble:beads-plan).
ensemble-implement-bead
Implement a single beads task by ID through analysis, implementation, and PR creation (Codex skill for /ensemble:implement-bead).
ensemble-refine-beads
Approval-gated Beads graph refinement before execution (Codex skill for /ensemble:refine-beads).
complete-beads
Goal-oriented skill that drives every scoped bead to closed or a truthful terminal state. Recovers in-progress work, selects tasks via BV triage/planning, dispatches isolated workers in parallel, integrates serially, and rolls up completed containers. Produces one machine-readable result sentinel.
managing-jira-issues
Jira issue management using the jira CLI with JSON output. Use for creating, viewing, updating, searching issues, fetching complete hierarchies, and managing sprints.