bp-build

bp-build is a skill for Claude Code, Codex from ynishi/mlua-swarm. It costs 72 tokens per session (802 once invoked), scanned A, original, Apache-2.0.

A workflow for handing a fully designed Blueprint implementation to a separate coding agent called @bp-coder. Blueprint is the implementation format used by the workflow.

In plain words
What is it for?
Use it to implement a named Blueprint once its node structure, worker types, pass conditions, and output path are settled.
Why use it?
It prevents implementation from starting before the flow, workers, expected results, and output location are decided. A verification tool called bp_doctor checks the generated result.

Skill for Claude CodeCodex

Part of the mse plugin — 2 skills, 2 agents shipped together

Install

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.

agentmods
npx agentmods add skills/ynishi/mlua-swarm/bp-build
Any agent
npx skills add ynishi/mlua-swarm --skill bp-build
Clone the repo
git clone --depth 1 https://github.com/ynishi/mlua-swarm

Made for: Claude Code, Codex.

Or install mse, the plugin that ships this one along with the rest of its 2 skills, 2 agents.

Wrote 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.

agentmods badge for bp-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/ynishi/mlua-swarm/bp-build.svg)](https://agentmods.dev/skills/ynishi/mlua-swarm/bp-build)
Your own site
<a href="https://agentmods.dev/skills/ynishi/mlua-swarm/bp-build"><img src="https://agentmods.dev/badge/skills/ynishi/mlua-swarm/bp-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 802 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.00802
Opus 5 $0.00036 $0.00401
Sonnet 5 $0.00014 $0.00160
Haiku 4.5 $0.00007 $0.00080

Measured 5d ago against content hash b62c2af0dbf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

bp-build 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.

plugins/mse/skills/bp-build/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/bp-build — Blueprint Implementation Kick

Hands a mature design_para and a resolved output_path to @bp-coder and lets it write the Blueprint in an isolated context, using bp_doctor as the verify gate.

Either the User invokes /bp-build "<design_para>" --out=<path> literally, or the AI invokes it on the User's behalf once the design conversation has matured (see "Maturity Self-check" below).

Run only when main-thread dialogue (User ↔ AI) has condensed the design into a single paragraph. Never trigger mid-conversation with a vague intent, unnamed flow shape, or missing pass conditions.

Maturity Self-check (AI-invoked path)

Before assembling the kick prompt on the User's behalf, verify all of the following from the conversation context. If any item is missing, do not invoke — return one short question to the User to fill the gap, then resume.

  1. Blueprint name / id is decided (kebab-case, no collision concern).
  2. Flow shape is stated (which node kinds compose the top-level flow — step / seq / branch / loop / fanout / try / assign).
  3. Worker binding is stated (each agent's kind: Lua / Automate / MainAi / AgentBlock / subprocess backend — or an explicit "reuse existing agent id" declaration).
  4. Verdict / projection expectations are stated (what shape lands in final_ctx; which per-step outputs are named parts vs. plain body).
  5. Output path is decided (absolute path ending .json or .bp.lua).
  6. Smoke intent is decided (smoke: true = run once after doctor clears with a minimal init_ctx; default false).

If any of 1–6 is missing, ask one short question rather than guessing.

Kick prompt shape

Dispatched to @bp-coder with the following literal template:

Blueprint output path: <absolute path, .json or .bp.lua>
Format: <json|lua>       # derived from the path suffix
Smoke: <true|false>      # default false

Design paragraph:
<design_para verbatim>

Optional grounding refs (Read before writing):
- <mse://guides/... URIs the design references, when applicable>
- <mse://blueprints/samples/... URIs the design references, when applicable>

Read the full file on GitHub · 73 lines

Changes

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.

  1. 5d ago First seen · 73 lines · 72 tokens per session scan A b62c2af0dbf1

Subscribe to this mod's changes

bp-build is a skill published in the GitHub repository ynishi/mlua-swarm (1 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 802 once invoked, about $0.0004 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.