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/mmornati/leanproxy-mcp/bmad-loop-setupnpx skills add mmornati/leanproxy-mcp --skill bmad-loop-setupgit clone --depth 1 https://github.com/mmornati/leanproxy-mcpWrote 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/mmornati/leanproxy-mcp/bmad-loop-setup)<a href="https://agentmods.dev/skills/mmornati/leanproxy-mcp/bmad-loop-setup"><img src="https://agentmods.dev/badge/skills/mmornati/leanproxy-mcp/bmad-loop-setup.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 | $0.00045 | $0.05497 |
| Opus 5 | $0.00023 | $0.02749 |
| Sonnet 5 | $0.00009 | $0.01099 |
| Haiku 4.5 | $0.00005 | $0.00550 |
Grade C, and why
bmad-loop-setup scanned grade C with 2 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 3d 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Ask the user for values. Show defaults in brackets. Present all values together so the user can respond once with only the values they want to change (e.g. "change language to Swahili, rest are fine"). Never tell the use Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
python3 ./scripts/cleanup-legacy.py --bmad-dir "{project-root}/_bmad" --module-code bmad-loop --also-remove _config --skills-dir "{project-root}/.claude/skills" How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Module Setup
Overview
Installs, configures, and upgrades a BMad module in a project. This module is special: alongside the four automation skills it relies on the bmad-loop orchestrator tool (the Python program that drives the loop), installed as the bmad-loop package from its public Git repository. So setup does two jobs — (1) register module config + help entries, and (2) install or upgrade the orchestrator tool and bootstrap the project so it is ready to run.
The same skill handles both first-time setup and upgrades. When it detects an existing bmad-loop install (or you ask it to upgrade), it upgrades the orchestrator tool, refreshes the per-project bmad-loop-* skill copies, and re-stamps config — the two-step upgrade ritual, run for you. A plain re-run on an already-installed project is treated as an upgrade.
Module identity (name, code, version) comes from ./assets/module.yaml. Collects user preferences and writes them to three files:
{project-root}/_bmad/config.yaml— shared project config: core settings at root (e.g.output_folder,document_output_language) plus a section per module with metadata and module-specific values. User-only keys (user_name,communication_language) are never written here.{project-root}/_bmad/config.user.yaml— personal settings intended to be gitignored:user_name,communication_language, and any module variable markeduser_setting: truein./assets/module.yaml. These values live exclusively here.{project-root}/_bmad/module-help.csv— registers module capabilities for the help system.
Both config scripts use an anti-zombie pattern — existing entries for this module are removed before writing fresh ones, so stale values never persist.
{project-root} is a literal token in config values (the data written into the files above) — never substitute it there. It signals to the consuming LLM that the value is relative to the project root, not the skill root. This does not apply to the filesystem path arguments passed to the scripts below (the --*-path, --*-dir, and --target arguments): those are real paths, so you must resolve {project-root} to the actual project root before running, or the scripts will write to a literal {project-root}/ directory under the skill folder. The scripts reject an unresolved token with an error.
What ships with it
5 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.
- 3d ago First seen · 214 lines · 45 tokens per session scan C 84aa3d70f2c1
bmad-loop-setup is a skill published in the GitHub repository mmornati/leanproxy-mcp (5 stars, last pushed 4d ago), licensed MIT. It adds 45 tokens to every session and 5,497 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 2 findings (subtle steering, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
release-notes
Draft concise release notes.
use-modern-go
Use the Modern Go Guidelines CLI whenever writing, modifying, fixing, or refactoring Go code. Apply its version-specific guidance to generated changes.
jwx-guide-v4
Guide for developing Go applications with github.com/lestrrat-go/jwx v4 — parse/sign JWTs, work with JWS/JWE/JWK, pick algorithms, and avoid the common footguns. For developers using jwx, not for developing the library itself.
jwx-companion-bulk
Apply bulk operations across all jwx companion modules. Args.
golang-gomlx
Machine learning models training and inference using GoMLX for Go. It provides an abstraction to create vectorized computation graphs, that can then be JIT-compiled (Just-In-Time) and executed very fast, with backends using XLA (for CPU/CUDA/TPU), Go and others. Includes a reach set of vector (tensors) operations on…
readme-generate
從原始碼分析自動生成雙語 README。當使用者請求為專案建立 README、需要從程式碼庫生成 README.md（英文）和 README.zh.md（中文）、或希望為其函式庫/套件建立一致的多語言文件時使用。.