sbce

sbce is a skill for Claude Code, Codex from AdamBien/airails. It costs 215 tokens per session (4,282 once invoked), scanned A, original, MIT.

A workflow for defining and implementing one business capability as one business component. Its written specification acts as the agreement for what the component must provide, while tests decide when it is complete.

In plain words
What is it for?
Use it to create or apply a capability specification, identify gaps between the specification and component, write the implementation, and verify completion through the project's tests.
Why use it?
It keeps requirements close to the code and avoids maintaining separate task lists or conflicting specifications.

Skill for Claude CodeCodex

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/adambien/airails/sbce
Any agent
npx skills add AdamBien/airails --skill sbce
Clone the repo
git clone --depth 1 https://github.com/AdamBien/airails

Made for: Claude Code, Codex.

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 sbce

README.md
[![agentmods](https://agentmods.dev/badge/skills/adambien/airails/sbce.svg)](https://agentmods.dev/skills/adambien/airails/sbce)
Your own site
<a href="https://agentmods.dev/skills/adambien/airails/sbce"><img src="https://agentmods.dev/badge/skills/adambien/airails/sbce.svg" alt="Measured on agentmods" height="20"></a>
Per session 215 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,282 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 $0.00215 $0.04282
Opus 5 $0.00108 $0.02141
Sonnet 5 $0.00043 $0.00856
Haiku 4.5 $0.00021 $0.00428

Measured 5d ago against content hash 2e20a87d0b33, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sbce 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.

bce/sbce/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive the spec-driven BCE workflow — one skill owns both the rules and the steps. Invoke as /sbce <mode> <capability> (new or apply), or let it trigger from intent. Apply every rule strictly.

Guiding principles

  • The spec is the boundary contract — what the boundary promises, never how.
  • The spec lives in the BC's package docpackage-info.java (Java, /// Markdown) or package-info.md (web) — co-located with the code it governs. There is no separate specs/ tree and no hand-typed package coordinate. In Java the /// doc renders via javadoc, so the same file is source-of-truth and published contract.
  • One capability spec ≡ one business component, named the same. No translation between "what" and "where".
  • The task list is the gap, read off spec vs BC on demand — never a hand-maintained tasks file.
  • One spec per capability, the single source of truth — never diff or merge two specs.
  • Split by determinism: tooling runs tests and places the BC; this skill writes the spec, the code, and closes the gap.
  • "Done" is a green run of the stack's test loop — never your own opinion.

Spec ↔ BC mapping

The BC name is the only identity — a single lowercase token (checkout), never a dotted path or a bc/capability field. The stack skill owns where it lands:

checkout                                      # BC name == the only identity
  spec = package doc, co-located with code:
    Java: src/main/java/<base>/checkout/package-info.java   # `///` Markdown (JEP 467)
    web:  app/src/checkout/package-info.md                  # Markdown
  code = same folder, {boundary,control,entity}/            # stack skill places it
  • ## Boundary op ↔ one boundary entry-point method.
  • ## Requirements (EARS) ↔ behaviour and the tests covering it.
  • ## Entities ↔ the entity layer.

System doc (base package)

An optional doc one altitude up — the base package's package-info.java / app/src/package-info.md — for concerns that span BCs and have no other home. Add a section only when a real cross-BC concern appears; a one-BC system needs none. Author from references/system-doc-template.md.

Read the full file on GitHub · 183 lines

Files

What ships with it

4 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.

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 · 183 lines · 215 tokens per session scan A 2e20a87d0b33

Subscribe to this mod's changes

sbce is a skill published in the GitHub repository AdamBien/airails (48 stars, last pushed yesterday), licensed MIT. It adds 215 tokens to every session and 4,282 once invoked, about $0.0011 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 2026-08-30.

Related

Other skills, from other repositories

authoring-java-sdk-tasks

Writes Airflow task logic in Java, Kotlin, or any JVM language using the Airflow Java SDK. Use when the user wants to implement Airflow tasks in Java/JVM, asks about @Builder.Dag/@Builder.Task/@Builder.XCom, the Task/BundleBuilder interfaces, reading connections/variables/XComs from Java, the JSON-to-Java type…

astronomer/agents · 152 tokens

configuring-airflow-language-sdks

Configures Airflow to run language SDK tasks (Java, Go, and future native SDKs) — register a coordinator, map a queue to it, ensure the runtime/artifact on workers, and tune coordinator options. Use when the user wants Airflow to route a queue to a native-language coordinator, asks about the [sdk]…

astronomer/agents · 155 tokens

help

OrchestKit help directory with categorized skill listings. Use when discovering skills for a task, finding the right workflow, or browsing capabilities.

yonatangross/orchestkit · 30 tokens

jackson-3-migration

Migrer Jackson 2.x til Jackson 3.x (tools.jackson) i Kotlin/Java-prosjekter — automatisert OpenRewrite-pass pluss manuell Kotlin-spesifikk opprydding og verifisering.

navikt/copilot · 53 tokens

java-to-kotlin

Trinnvis Java-til-Kotlin-migrering med rammeverk-bevisste transformasjoner for Spring, Ktor og Nav-mønstre.

navikt/copilot · 35 tokens

js-gof

Apply Gang of Four and related design patterns in JavaScript and TypeScript. Use when implementing creational, structural, or behavioral patterns, or when the user mentions factories, builder, prototype, flyweight, singleton, object pool, adapter, wrapper, decorator, proxy, bridge, composite, facade, chain of…

metarhia/metaskills · 107 tokens